id
stringlengths 29
32
| messages
listlengths 2
2
|
|---|---|
data_synthesis_sft_ticker_894_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $PLSE with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$PLSE - Pulse Biosciences up 6% on rights offering \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_895_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $PLSQF with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$PLSQF - Plus500 rockets 40% as revenue soars nearly 500% in Q1 \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_896_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $QTRH with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$QTRH - WiLAN signs wireless license with LG; shares +7% PM \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_897_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $RNWK with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$RNWK - RealNetworks CEO Rob Glaser to invest into the Company; shares +12% \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_898_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SLG with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SLG - SL Green rises 3.5% in two-day advance \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_899_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SLGG with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SLGG - Surge At Super League As Stay At Home Orders Go Coast To Coast. #business #stocks #stockmarket\", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_900_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SNY with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SNY - Sanofi upsizes debt offerings to; share up 2% \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_901_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SONN with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SONN up after hours on no news. Tempting but got to check if it has warrants and how clean the share structure is.\\u2026 \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_902_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SONO with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SONO: Sonos displaying relative strength as shares jump 8% to 52-week highs in the wake of Wednesday's earnings... \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_903_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SPCE with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SPCE - Virgin Galactic takes off again; +11% \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_904_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SRPT with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SRPT higher by 4.5% today clearing 21 MA and nearing Feb OpEx value range breakout\", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_905_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $TEUM with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$TEUM - Pareteum +8% after CEO termination \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_906_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $TIGR with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$TIGR (+8.7% pre) UP Fintech Holding Limited Reports Unaudited Third Quarter 2019 Financial Results - SI\\n\\n\", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_907_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $TRVN with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$TRVN - Trevena refilies U.S. application for IV oliceridine; shares up 6% \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_908_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $TRXC with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$TRXC - TransEnterix up 2% after hours on $25M stock sales deal \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_909_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $W with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$W - Wayfair +4% after BofA bump \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_909_1 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $W with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$W (+4.9% pre) BofA Securities Upgrades Wayfair (W) to Buy\\n\\n\", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_909_2 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $W with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"Shares of Wayfair $W jumped after the online furniture retailer said its revenue-growth rate more than doubled towa\\u2026 \", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_910_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $ZGNX with bullish (1) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$ZGNX big move w/ news this morning, name with size Jan and Apr bullish call OI\", \"sentiment\": 1}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_911_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $CTRC with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$CTRC $KODK $TEN - Eastman Kodak among consumer gainers; China Automotive Systems only loser \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_912_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $DAO with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$DAO $EGAN $ACMR - Youdao and eGain among Tech gainers; Technical Communications and Digital Ally among losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_913_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $EVH with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$EVH $PGNY $JG - Domo and Evolent Health Tech gainers; GlobalSCAPE and Yext among losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_914_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $HOV with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$HOV $GTES $TWI - Hovnanian Enterprises leads industrial gainers; losers none \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_915_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $NLTX with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$NLTX $ITRM $EQ - Healthcare - Top 5 Gainers / Losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_916_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $POLA with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$POLA $OSS - StoneCo and i3 Verticals among Tech gainers; VirnetX and Pure Storage among losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_917_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $RRC with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$RRC $FET $TUSK - Range Resources and Forum Energy Technologies among Energy/Materials gainers; Pacific Drilling an\\u2026 \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_918_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $SOLO with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$SOLO $DTEA $NLS - Electrameccanica Vehicles leads consumer gainers; Pyxus International in losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_919_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $STOK with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$STOK $TROV $BNTC - vTv Therapeutics leads healthcare gainers; Myomo and Biohaven Pharmaceutical among losers \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
data_synthesis_sft_ticker_920_0 | [
{
"content": "Generate one realistic financial news headline about stock tickers following real-world financial reporting for sentiment analysis.\n\nGuidelines for Generating Headlines:\n\n1. Format & Style:\n\t•\tHeadlines must be concise and mimic real financial news.\n\t•\tUse sentence case formatting (capitalize only the first word and proper nouns).\n\t•\tSome headlines should start with a stock ticker (e.g., $AAPL -), while others should begin with the company name or a broader market trend.\n\n2. Ticker Inclusion:\n\t•\tAt least one headline should include a stock ticker (e.g., $TSLA - or $NVDA -).\n\t•\tSome headlines should refer to companies by name instead of tickers (e.g., “Alphabet and Meta see price targets cut at Barclays”).\n\n3. Common Financial Themes:\n\nEnsure headlines reflect realistic financial news topics, including:\n\t•\tStock downgrades/upgrades\n\t•\tPrice target adjustments\n\t•\tMarket trends/economic outlook\n\t•\tCompany performance concerns\n\t•\tCompany news\n\t•\tCompany announcements\n\t•\tCompany events\n\n4. Source Attribution:\n\t•\tWhen relevant, mention an investment firm, analyst, or research group (e.g., Morgan Stanley, Barclays, Oppenheimer).\n\t•\tDo not fabricate research firms—use only well-known institutions.\n\n5. Sentiment Labeling:\n\nEach headline must be assigned a sentiment label based on its tone:\n\t•\tBearish (0): Indicates negative sentiment about a stock or market trend.\n\t•\tBullish (1): Indicates positive sentiment about a stock or market trend.\n\t•\tNeutral (2): Indicates neutral or informational tone.\n\nFormat:\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"headline\": {\"description\": \"financial news headline\", \"title\": \"Headline\", \"type\": \"string\"}, \"sentiment\": {\"description\": \"sentiment (0=bearish, 1=bullish, 2=neutral)\", \"title\": \"Sentiment\", \"type\": \"string\"}}, \"required\": [\"headline\", \"sentiment\"]}\n```\n\nNow, generate one financial news headline about stock tickers: $WEBK with neutral (2) label following these guidelines. \nYour JSON output:",
"role": "user"
},
{
"content": "{\"headline\": \"$WEBK $EZPW $BRP - Wellesley Bancorp leads financial gainers; Weidai the only loser \", \"sentiment\": 2}",
"role": "assistant"
}
]
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.