MARTINI_enrich_BERTopic_ptpatriots

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_ptpatriots")

topic_model.get_topic_info()

Topic overview

• Number of topics: 66
• Number of training documents: 9428

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	democrats - cnn - voting - gop - states	20	-1_democrats_cnn_voting_gop
0	mariupol - zelensky - nordstream - russian - ww3	5566	0_mariupol_zelensky_nordstream_russian
1	bidens - bribery - fbi - whistleblower - zlochevsky	229	1_bidens_bribery_fbi_whistleblower
2	illegals - texas - daca - border - deportation	209	2_illegals_texas_daca_border
3	pedophilia - transgender - gays - minors - indoctrination	205	3_pedophilia_transgender_gays_minors
4	convoy - hagerstown - protesters - freedom - trudeau	162	4_convoy_hagerstown_protesters_freedom
5	musk - tweet - dorsey - taibbi - shareholders	141	5_musk_tweet_dorsey_taibbi
6	biden - eagles - heckled - teleprompter - stupid	137	6_biden_eagles_heckled_teleprompter
7	primetimepatriots - 7pm - updates - operationtba - youtube	123	7_primetimepatriots_7pm_updates_operationtba
8	doj - trump - melania - redacted - archives	120	8_doj_trump_melania_redacted
9	fauci - coronaviruses - pompeo - researchers - origins	108	9_fauci_coronaviruses_pompeo_researchers
10	insurrection - jail - capitol - misdemeanor - smollett	102	10_insurrection_jail_capitol_misdemeanor
11	petroleum - prices - venezuela - granholm - gallon	100	11_petroleum_prices_venezuela_granholm
12	trump - mueller - mcmahon - 2021 - rigged	90	12_trump_mueller_mcmahon_2021
13	tweets - dorsey - banning - employees - vf	89	13_tweets_dorsey_banning_employees
14	kabul - taliban - evacuated - pentagon - terrorist	81	14_kabul_taliban_evacuated_pentagon
15	desantis - gwb - bureaucrats - fakemagas - radicalized	74	15_desantis_gwb_bureaucrats_fakemagas
16	vaers - pfizer - myocarditis - deaths - clots	71	16_vaers_pfizer_myocarditis_deaths
17	republicans - incumbent - fairfax - mcauliffe - 2022	65	17_republicans_incumbent_fairfax_mcauliffe
18	hamas - israelis - megiddo - tlaib - atrocities	64	18_hamas_israelis_megiddo_tlaib
19	katie - gubernatorial - maricopa - hobbs - winner	61	19_katie_gubernatorial_maricopa_hobbs
20	abortions - mccorvey - kavanaugh - overruling - defunded	61	20_abortions_mccorvey_kavanaugh_overruling
21	bidenflation - stagflation - recession - wage - dow	60	21_bidenflation_stagflation_recession_wage
22	representatives - gop - mccarthy - votes - speaker	58	22_representatives_gop_mccarthy_votes
23	fbi - hacked - blinken - whistleblower - colluded	57	23_fbi_hacked_blinken_whistleblower
24	dioxins - hazmat - derailed - deadly - ohio	57	24_dioxins_hazmat_derailed_deadly
25	fbi - agencies - twitter - influence - threats	55	25_fbi_agencies_twitter_influence
26	outvote - ballots - yall - november - winners	54	26_outvote_ballots_yall_november
27	died - defibrillator - nfl - sudden - collapsing	48	27_died_defibrillator_nfl_sudden
28	ballots - recount - gwinnett - counties - adjudicated	48	28_ballots_recount_gwinnett_counties
29	ballots - pennsylvania - mailed - precincts - fraud	46	29_ballots_pennsylvania_mailed_precincts
30	billions - zelenskyy - gdp - subsidizing - war	45	30_billions_zelenskyy_gdp_subsidizing
31	gunman - columbine - deputies - swat - teacher	45	31_gunman_columbine_deputies_swat
32	debt - taxpayers - forgiven - trillion - yale	41	32_debt_taxpayers_forgiven_trillion
33	davos - worldwide - paramilitary - societies - satanists	41	33_davos_worldwide_paramilitary_societies
34	ftx - megadonors - bankrupts - laundering - kraken	40	34_ftx_megadonors_bankrupts_laundering
35	maricopa - ballots - undervoted - sabotaged - bluest	38	35_maricopa_ballots_undervoted_sabotaged
36	mandates - unvaxxed - ruling - sotomayor - medicare	38	36_mandates_unvaxxed_ruling_sotomayor
37	comey - spygate - collusion - dossier - discredited	38	37_comey_spygate_collusion_dossier
38	epstein - ghislaine - rape - manafort - conspirators	37	38_epstein_ghislaine_rape_manafort
39	bolsonaro - janeiro - colombia - protesters - fearmongering	36	39_bolsonaro_janeiro_colombia_protesters
40	nevertrumpers - president - fascists - momentous - fakemaga	34	40_nevertrumpers_president_fascists_momentous
41	handguns - shootings - disarmed - winchester - laws	34	41_handguns_shootings_disarmed_winchester
42	baloon - missile - sputnik - pentagon - beijing	33	42_baloon_missile_sputnik_pentagon
43	enlisted - troops - airmen - pentagon - racism	33	43_enlisted_troops_airmen_pentagon
44	maskless - mandates - inoculations - curfew - arizonans	33	44_maskless_mandates_inoculations_curfew
45	tuckercarlson - newsmax - bongino - propagandist - lunatic	31	45_tuckercarlson_newsmax_bongino_propagandist
46	immunized - covid - unvaccinated - reinfection - epitopes	29	46_immunized_covid_unvaccinated_reinfection
47	bannon - stephen - jury - murdoch - assassinated	29	47_bannon_stephen_jury_murdoch
48	impeachments - suing - maddow - felony - unprecedented	28	48_impeachments_suing_maddow_felony
49	maricopa - ballots - auditors - recount - subpoena	28	49_maricopa_ballots_auditors_recount
50	schumer - voted - earmarks - amendments - trillion	28	50_schumer_voted_earmarks_amendments
51	pray - archangel - satan - ephesians - righteousness	28	51_pray_archangel_satan_ephesians
52	veritas - defamation - tweet - charliekirk - founded	28	52_veritas_defamation_tweet_charliekirk
53	lockdowns - wuhan - zhejiang - xinjiang - protests	25	53_lockdowns_wuhan_zhejiang_xinjiang
54	ivermectin - hydroxychloroquine - chemoprophylaxis - azithromycin - prescribed	25	54_ivermectin_hydroxychloroquine_chemoprophylaxis_azithromycin
55	milwaukee - ballots - deputy - zapata - ineligible	24	55_milwaukee_ballots_deputy_zapata
56	sfsu - chancellor - hoaxer - assaulted - oppression	23	56_sfsu_chancellor_hoaxer_assaulted
57	pelosi - pizzagate - attacker - david - pinned	23	57_pelosi_pizzagate_attacker_david
58	taiwan - bombers - invasion - missile - warships	23	58_taiwan_bombers_invasion_missile
59	bomb - evacuated - barricade - suspicious - sirens	23	59_bomb_evacuated_barricade_suspicious
60	antifa - atlanta - terrorists - attacked - prosecuting	22	60_antifa_atlanta_terrorists_attacked
61	fbi - informants - capitol - january - infiltrated	22	61_fbi_informants_capitol_january
62	georgia - hershel - vote - warnock - thegatewaypundit	21	62_georgia_hershel_vote_warnock
63	murderer - manifesto - shooters - nashville - schoolhouse	21	63_murderer_manifesto_shooters_nashville
64	impeachment - senators - mcconnell - congresswoman - traitors	20	64_impeachment_senators_mcconnell_congresswoman

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