MARTINI_enrich_BERTopic_qanonplus

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_qanonplus")

topic_model.get_topic_info()

Topic overview

• Number of topics: 118
• Number of training documents: 16268

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	trump - fbi - epstein - news - states	20	-1_trump_fbi_epstein_news
0	illegals - deported - cbp - matamoros - smuggled	9495	0_illegals_deported_cbp_matamoros
1	ukraine - donetsk - mariupol - russians - missiles	303	1_ukraine_donetsk_mariupol_russians
2	stabbed - robbers - bronx - gunpoint - homicide	280	2_stabbed_robbers_bronx_gunpoint
3	biden - kamala - jill - reporters - vp	213	3_biden_kamala_jill_reporters
4	fauci - coronaviruses - darpa - bioweapon - institutes	182	4_fauci_coronaviruses_darpa_bioweapon
5	comey - counterintelligence - dossier - fisa - danchenko	181	5_comey_counterintelligence_dossier_fisa
6	gaza - airstrikes - hezbollah - israeli - qassam	180	6_gaza_airstrikes_hezbollah_israeli
7	musk - twittergate - dorsey - shareholders - takeover	157	7_musk_twittergate_dorsey_shareholders
8	bailouts - fdic - depositors - bancorp - yellen	149	8_bailouts_fdic_depositors_bancorp
9	bidens - bribery - laundering - oligarchs - vp	131	9_bidens_bribery_laundering_oligarchs
10	trudeau - truckersforfreedom - ontario - protestors - crackdown	125	10_trudeau_truckersforfreedom_ontario_protestors
11	pfizer - mercola - virologist - delisted - freedommed	122	11_pfizer_mercola_virologist_delisted
12	trannies - ftm - estradiol - female - castrate	120	12_trannies_ftm_estradiol_female
13	trump - judge - indicted - prosecutors - watergate	119	13_trump_judge_indicted_prosecutors
14	davos - globalists - agenda - documentary - cbdc	119	14_davos_globalists_agenda_documentary
15	patriotbusiness - cryptocoins - chatroom - reposted - 39k	116	15_patriotbusiness_cryptocoins_chatroom_reposted
16	explosions - refinery - firefighters - flames - evacuations	116	16_explosions_refinery_firefighters_flames
17	taliban - kandahar - milley - zabihullah - helicopters	109	17_taliban_kandahar_milley_zabihullah
18	yangtze - qinghai - headwaters - floods - henan	106	18_yangtze_qinghai_headwaters_floods
19	taiwan - warfare - invade - destroyers - pacific	102	19_taiwan_warfare_invade_destroyers
20	migrants - lampedusa - islamist - stabbed - perpetrator	101	20_migrants_lampedusa_islamist_stabbed
21	petroleum - bidenflation - prices - saudis - gallon	97	21_petroleum_bidenflation_prices_saudis
22	patriot - believing - sheeple - hold - hardships	92	22_patriot_believing_sheeple_hold
23	france - riots - bastille - marseille - liberte	92	23_france_riots_bastille_marseille
24	bolsonaro - argentineans - venezuela - electoral - janeiro	89	24_bolsonaro_argentineans_venezuela_electoral
25	fbi - capitol - prisoner - rioters - january	85	25_fbi_capitol_prisoner_rioters
26	aspartame - sweeteners - gummies - synthetic - pepsi	81	26_aspartame_sweeteners_gummies_synthetic
27	ivermectin - hydroxychloroquine - ritonavir - fenbendazole - 5000iu	77	27_ivermectin_hydroxychloroquine_ritonavir_fenbendazole
28	cabal - cnn - soros - plandemic - jfkjr	68	28_cabal_cnn_soros_plandemic
29	riots - counterprotesters - minnesota - officer - floyd	65	29_riots_counterprotesters_minnesota_officer
30	ballots - pennsylvania - defendflorida - affidavits - precincts	64	30_ballots_pennsylvania_defendflorida_affidavits
31	patriots - chatroom - bots - 11k - blackpillers	60	31_patriots_chatroom_bots_11k
32	donaldjtrump - rallies - newsmax - watchlive - mcmaster	59	32_donaldjtrump_rallies_newsmax_watchlive
33	biden - laptop - blackmailers - rudy - reveals	58	33_biden_laptop_blackmailers_rudy
34	pompeo - 27th - fawkes - date - q1314	58	34_pompeo_27th_fawkes_date
35	kilauea - soufriere - eruptionis - palma - cataclysm	57	35_kilauea_soufriere_eruptionis_palma
36	whatsapp - deleting - appstore - uninstall - protonmail	55	36_whatsapp_deleting_appstore_uninstall
37	donald - federalizing - proclamation - military - 2020	54	37_donald_federalizing_proclamation_military
38	ghislaine - epstein - alleged - jurors - multimillionaire	53	38_ghislaine_epstein_alleged_jurors
39	vaccine - perimyocarditis - mrna - inflammation - cardiologist	52	39_vaccine_perimyocarditis_mrna_inflammation
40	duckduckgo - pichai - yahoo_youtube - blacklisted - presearch	51	40_duckduckgo_pichai_yahoo_youtube_blacklisted
41	maui - hawaiians - lahaina - wildfire - landowners	50	41_maui_hawaiians_lahaina_wildfire
42	ukraine - biolaboratories - pentagon - anthrax - proliferation	47	42_ukraine_biolaboratories_pentagon_anthrax
43	zelensky - million - pinchuk - mironyuk - pensions	44	43_zelensky_million_pinchuk_mironyuk
44	pompeo - dunford - genflynn - nsa - loyalists	44	44_pompeo_dunford_genflynn_nsa
45	chinese - jingwei - zhengdong - espionage - defector	43	45_chinese_jingwei_zhengdong_espionage
46	scotus - gorsuch - docket - dismissed - brett	41	46_scotus_gorsuch_docket_dismissed
47	zuckerberg - fb - meta - censorship - lnstagram	40	47_zuckerberg_fb_meta_censorship
48	qanon - posts - shill - surrender - disseminate	40	48_qanon_posts_shill_surrender
49	fauci - _vaccine - news - mandates - falsified	40	49_fauci__vaccine_news_mandates
50	thepatriotlight - tyrants - 21 - pray - everywhere	40	50_thepatriotlight_tyrants_21_pray
51	rupaul - lgbtqxyz - paedophiles - christmas - parading	39	51_rupaul_lgbtqxyz_paedophiles_christmas
52	vaers - deaths - janssen - ad26 - pericarditis	39	52_vaers_deaths_janssen_ad26
53	representatives - impeach - murkowski - voted - 5251	39	53_representatives_impeach_murkowski_voted
54	derailments - hazmat - metra - dakota - spills	38	54_derailments_hazmat_metra_dakota
55	vaxxers - vacunados - shingles - smerconish - needle	37	55_vaxxers_vacunados_shingles_smerconish
56	covidvaccinevictims - astrazeneca - 2021 - stephanie - coma	37	56_covidvaccinevictims_astrazeneca_2021_stephanie
57	obamas - drowned - martha - paddleboarder - accidental	37	57_obamas_drowned_martha_paddleboarder
58	stimulus - billion - obamacare - americorp - fy2019	37	58_stimulus_billion_obamacare_americorp
59	australia - nsw - lockdown - protesters - busselton	36	59_australia_nsw_lockdown_protesters
60	royal - coronation - buckingham - meghan - sceptre	36	60_royal_coronation_buckingham_meghan
61	pelosi - nancy - paulie - husband - drunken	36	61_pelosi_nancy_paulie_husband
62	monkeypox - smallpox - vaccinate - transmissibility - nonproliferation	36	62_monkeypox_smallpox_vaccinate_transmissibility
63	humantraffickinghotline - arrested - prostituted - kidnapping - ohio	35	63_humantraffickinghotline_arrested_prostituted_kidnapping
64	squadrons - awacs - stratotanker - rc135s - dornier	35	64_squadrons_awacs_stratotanker_rc135s
65	sextortion - molestation - convicted - imprisonment - victims	35	65_sextortion_molestation_convicted_imprisonment
66	blockfi - winklevoss - laundered - scams - 32billion	35	66_blockfi_winklevoss_laundered_scams
67	cryptocrash - coinmarketcap - litecoin - hashrate - xlm	34	67_cryptocrash_coinmarketcap_litecoin_hashrate
68	iraq - airstrikes - khorramabad - dhahran - kurdish	33	68_iraq_airstrikes_khorramabad_dhahran
69	lockdown - guangzhou - sichuan - tibet - xishuangbanna	33	69_lockdown_guangzhou_sichuan_tibet
70	biden - delaware - folders - mishandled - chung	33	70_biden_delaware_folders_mishandled
71	earthquakes - aftershocks - tsunamis - usgs - panama	32	71_earthquakes_aftershocks_tsunamis_usgs
72	netherlands - rotterdam - rotterdammers - joris - ministers	32	72_netherlands_rotterdam_rotterdammers_joris
73	epidemics - nipah - h5n1 - dengue - deadliest	32	73_epidemics_nipah_h5n1_dengue
74	covidvaxexposed - vaccinate - injections - children - mandating	32	74_covidvaxexposed_vaccinate_injections_children
75	unvaccinated - covid - hospitalizations - breakthrough - fully	31	75_unvaccinated_covid_hospitalizations_breakthrough
76	eurosceptic - netherland - coalition - polls - geert	31	76_eurosceptic_netherland_coalition_polls
77	electionguard - hackable - computerized - techcrunch - audited	30	77_electionguard_hackable_computerized_techcrunch
78	sunspot - auroras - comet - magnetometers - nasa	30	78_sunspot_auroras_comet_magnetometers
79	maricopa - auditors - subpoena - truthhammer - bennett	30	79_maricopa_auditors_subpoena_truthhammer
80	trumps - products - memorabilia - patriot - donate	30	80_trumps_products_memorabilia_patriot
81	papal - archbishopric - scandals - nuns - defrocked	30	81_papal_archbishopric_scandals_nuns
82	protests - lockdown - milan - boomrome - denmark	30	82_protests_lockdown_milan_boomrome
83	ep - trap - ds - 2943b - treason	30	83_ep_trap_ds_2943b
84	impeachment - vindman - liar - julie - swalwell	30	84_impeachment_vindman_liar_julie
85	pilots - jetblue - unvaccinated - boarded - mandates	29	85_pilots_jetblue_unvaccinated_boarded
86	miscarriages - pfizer - immunized - placenta - trimester	28	86_miscarriages_pfizer_immunized_placenta
87	vaccinated - mandates - fda - tyson - workers	28	87_vaccinated_mandates_fda_tyson
88	maersk - dockworkers - longshore - containers - backlogged	27	88_maersk_dockworkers_longshore_containers
89	jury - courttv - kenosha - dismissed - youngkin	27	89_jury_courttv_kenosha_dismissed
90	mortality - vaxx - dowd - policyholders - 2022	27	90_mortality_vaxx_dowd_policyholders
91	capitol - inauguration - guardsmen - dunford - _mil	27	91_capitol_inauguration_guardsmen_dunford
92	ballots - votesecure - maricopa - counted - ineligible	27	92_ballots_votesecure_maricopa_counted
93	download - members - signal - cellphones - virginia	26	93_download_members_signal_cellphones
94	jpmorgan - epstein - pedophile - magnate - trustees	26	94_jpmorgan_epstein_pedophile_magnate
95	omicron - mutated - marburg - botswana - clade	26	95_omicron_mutated_marburg_botswana
96	poweroutage - generators - texas - supplies - temperatures	26	96_poweroutage_generators_texas_supplies
97	extradited - snowden - courts - juilan - ecuador	25	97_extradited_snowden_courts_juilan
98	fentanyl - sinaloa - naloxone - oxycodone - overdose	25	98_fentanyl_sinaloa_naloxone_oxycodone
99	australians - quarantine - victoria - deported - djokovic	25	99_australians_quarantine_victoria_deported
100	shootings - parkland - aiden - classroom - superintendent	24	100_shootings_parkland_aiden_classroom
101	inflation - skyrocketed - unaffordable - costco - 40	24	101_inflation_skyrocketed_unaffordable_costco
102	shortages - rationed - soybeans - growers - tesco	24	102_shortages_rationed_soybeans_growers
103	pcr - piandemic - false - influenza - detected	23	103_pcr_piandemic_false_influenza
104	tunnelsb - submersible - worldriotsbegin - implosions - maglev	23	104_tunnelsb_submersible_worldriotsbegin_implosions
105	trump - bullllshit - naysayers - victory - loosing	23	105_trump_bullllshit_naysayers_victory
106	praying - demonic - attacks - 21 - awake	22	106_praying_demonic_attacks_21
107	trafficked - underage - bondage - bastrop - rangers	22	107_trafficked_underage_bondage_bastrop
108	michaeljlindell - frankspeech - tonight - kimmel - streaming	22	108_michaeljlindell_frankspeech_tonight_kimmel
109	footballer - athletes - myocarditis - collapsed - sergio	22	109_footballer_athletes_myocarditis_collapsed
110	desantis - governors - wfla - fda - maga	22	110_desantis_governors_wfla_fda
111	cuomo - allegations - albany - andrew - groped	21	111_cuomo_allegations_albany_andrew
112	webull - gamestonk - robinhood - brokers - delisting	21	112_webull_gamestonk_robinhood_brokers
113	mcafee - killswitch - 04b0400009d0400007a0c0000f90d0000af1000005e1200000414000068170000 - decode - john	21	113_mcafee_killswitch_04b0400009d0400007a0c0000f90d0000af1000005e1200000414000068170000_decode
114	fbi - extremism - biased - redactions - infiltrated	21	114_fbi_extremism_biased_redactions
115	whistleblower - bidens - irs - investigation - transcript	21	115_whistleblower_bidens_irs_investigation
116	gauteng - riots - looted - jabulani - zuma	21	116_gauteng_riots_looted_jabulani

Training hyperparameters

• calculate_probabilities: True
• language: None
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: None
• seed_topic_list: None
• top_n_words: 10
• verbose: False
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 1.26.4
• HDBSCAN: 0.8.40
• UMAP: 0.5.7
• Pandas: 2.2.3
• Scikit-Learn: 1.5.2
• Sentence-transformers: 3.3.1
• Transformers: 4.46.3
• Numba: 0.60.0
• Plotly: 5.24.1
• Python: 3.10.12