Create README.md

README.md

@@ -0,0 +1,129 @@
+---
+library_name: tensorflow
+tags:
+- sentiment-analysis
+- aspect-based-sentiment-analysis
+- tensorflow
+- keras
+language:
+- tr
+metrics:
+- accuracy
+pipeline_tag: text-classification
+datasets:
+- Sengil/Turkish-ABSA-Wsynthetic
+---
+
+
+# 🇹🇷 Turkish Aspect-Based Sentiment Analysis (ABSA) – BiLSTM + Word2Vec
+
+This model performs aspect-based sentiment analysis (ABSA) on Turkish sentences. Given a sentence and a specific aspect, it predicts the sentiment polarity (Negative, Neutral, Positive) associated with that aspect.
+
+## 🧠 Model Details
+
+- **Model Type:** BiLSTM (Bidirectional Long Short-Term Memory) + Word2Vec
+- **Developer:** [Sengil](https://huggingface.co/Sengil)
+- **Library:** Keras
+- **Input Format:** `"Sentence [ASP] Aspect"`
+- **Labels:** 0 = Negative, 1 = Neutral, 2 = Positive
+- **Training Dataset:** [Sengil/Turkish-ABSA-Wsynthetic](https://huggingface.co/datasets/Sengil/Turkish-ABSA-Wsynthetic)
+
+## 📊 Evaluation Results
+
+The model achieved the following performance on the test set:
+
+| Class    | Precision | Recall | F1-Score | Support |
+|----------|-----------|--------|----------|---------|
+| Negative | 0.89      | 0.91   | 0.90     | 896     |
+| Neutral  | 0.70      | 0.64   | 0.67     | 140     |
+| Positive | 0.92      | 0.92   | 0.92     | 1178    |
+| **Overall** |           |        | **0.90** | 2214    |
+
+- **Overall Accuracy:** 90%
+- **Macro-Averaged F1-Score:** 83%
+- **Weighted-Averaged F1-Score:** 90%
+
+## 🚀 Usage Example
+
+```python
+import pickle
+import numpy as np
+from tensorflow.keras.models import load_model
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+
+# Load the model and tokenizer
+model = load_model("absa_bilstm_model.keras")
+with open("tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+# Maximum sentence length used during training
+max_len = 84  # Adjust this value based on your training configuration
+
+# Prediction function
+def predict_sentiment(sentence, aspect):
+    input_text = f"{sentence} [ASP] {aspect}"
+    sequence = tokenizer.texts_to_sequences([input_text])
+    padded_sequence = pad_sequences(sequence, maxlen=max_len, padding='post')
+    prediction = model.predict(padded_sequence)
+    label = np.argmax(prediction, axis=1)[0]
+    labels = {0: "Negative", 1: "Neutral", 2: "Positive"}
+    return labels[label]
+
+# Example usage
+sentence = "Manzara şahane evet ama servis rezalet."
+aspect = "Servis"
+print(f"Sentiment for '{aspect}': {predict_sentiment(sentence, aspect)}")
+````
+
+## 🏋️‍♀️ Training Details
+
+* **Embedding:** Word2Vec (dimension: 100)
+* **Model Architecture:**
+
+  * Embedding layer (initialized with pre-trained Word2Vec weights)
+  * 2 x BiLSTM layers (each with 100 units, dropout: 0.3)
+  * Conv1D layer (100 filters, kernel size: 5)
+  * Global Max Pooling
+  * Dense layer (16 units, ReLU activation)
+  * Output layer (3 units, softmax activation)
+* **Training Parameters:**
+
+  * Loss Function: `sparse_categorical_crossentropy`
+  * Optimizer: Adam
+  * Epochs: 35 (with early stopping)
+  * Batch Size: 128
+  * Learning Rate: 1e-3 (adjusted dynamically with ReduceLROnPlateau)
+
+## 📚 Training Data
+
+The model was trained on the [Sengil/Turkish-ABSA-Wsynthetic](https://huggingface.co/datasets/Sengil/Turkish-ABSA-Wsynthetic) dataset, which comprises semi-synthetic Turkish sentences annotated for aspect-based sentiment analysis, particularly in the restaurant domain.
+
+## ⚠️ Limitations
+
+* Performance on the Neutral class is lower compared to other classes, possibly due to class imbalance in the training data.
+* The model may struggle with rare or ambiguous aspects not well represented in the training set.
+* Complex sentence structures or ironic expressions may affect the model's accuracy.
+
+## 📄 Citation
+
+```
+@misc{turkish_absa_bilstm_word2vec,
+  title  = {Turkish Aspect-Based Sentiment Analysis using BiLSTM + Word2Vec},
+  author = {Sengil},
+  year   = {2025},
+  url    = {https://huggingface.co/Sengil/Turkish-ABSA-BiLSTM-Word2Vec}
+}
+```
+
+## 📬 Contact
+
+For questions or feedback, please reach out via [Hugging Face profile](https://huggingface.co/Sengil).
+
+```
+
+---
+
+You can save this content as a `README.md` file and include it in your Hugging Face model repository. Ensure that you also upload the `absa_bilstm_model.keras` and `tokenizer.pkl` files to the repository. For guidance on uploading models to Hugging Face, refer to their [Model Sharing Documentation](https://huggingface.co/docs/hub/models-sharing).
+::contentReference[oaicite:0]{index=0}
+ 
+```