MARTINI_enrich_BERTopic_chiefnerd

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_chiefnerd")

topic_model.get_topic_info()

Topic overview

• Number of topics: 45
• Number of training documents: 5779

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	vaccinated - pfizer - myocarditis - doctors - 2021	20	-1_vaccinated_pfizer_myocarditis_doctors
0	twitter - censorship - musk - taibbi - shareholders	2904	0_twitter_censorship_musk_taibbi
1	ukraine - kremlin - zelensky - sanctions - blinken	249	1_ukraine_kremlin_zelensky_sanctions
2	trudeau - ottawa - convoy - alberta - freedom	187	2_trudeau_ottawa_convoy_alberta
3	died - defibrillator - footballer - bronny - sudden	156	3_died_defibrillator_footballer_bronny
4	rogan - misinformation - podcast - cnn - meidastouch	132	4_rogan_misinformation_podcast_cnn
5	fauci - coronaviruses - bats - laboratory - pentagon	130	5_fauci_coronaviruses_bats_laboratory
6	mandates - unvaccinated - hochul - repeal - medicare	125	6_mandates_unvaccinated_hochul_repeal
7	maricopa - ballots - karrin - deputies - pelosi	113	7_maricopa_ballots_karrin_deputies
8	rfk - undebatable - propagandists - snowden - debbie	103	8_rfk_undebatable_propagandists_snowden
9	ford - tesla - electricity - fuels - prices	102	9_ford_tesla_electricity_fuels
10	transgender - virginia - mandates - born - schools	99	10_transgender_virginia_mandates_born
11	scammers - deleted - telegram - spamming - subscribers	82	11_scammers_deleted_telegram_spamming
12	illegals - migrant - border - biden - dhs	78	12_illegals_migrant_border_biden
13	pfizer - whistleblower - lawsuit - falsified - jackson	77	13_pfizer_whistleblower_lawsuit_falsified
14	vaccinated - omicron - hospitalizations - contagious - israel	67	14_vaccinated_omicron_hospitalizations_contagious
15	noaa - co2 - gmo - greenland - globalism	67	15_noaa_co2_gmo_greenland
16	scotus - overturned - abortions - filibuster - voted	64	16_scotus_overturned_abortions_filibuster
17	worldcouncilforhealth - doctors - mccullough - denying - malpractice	64	17_worldcouncilforhealth_doctors_mccullough_denying
18	fdic - yellen - depositors - collapse - blackrock	62	18_fdic_yellen_depositors_collapse
19	myocarditis - myopericarditis - troponin - electrocardiogram - vaccination	62	19_myocarditis_myopericarditis_troponin_electrocardiogram
20	pfizer - booster - injections - ages - updated	60	20_pfizer_booster_injections_ages
21	hydroxychloroquine - ivermectin - paxlovid - remdesivir - molnupiravir	55	21_hydroxychloroquine_ivermectin_paxlovid_remdesivir
22	mortuaries - 2022 - matthews - insurers - increase	53	22_mortuaries_2022_matthews_insurers
23	bidens - fbi - dailymail - hacked - zuckerberg	50	23_bidens_fbi_dailymail_hacked
24	vaccinated - nfl - durant - mvp - kevin	49	24_vaccinated_nfl_durant_mvp
25	gates - billion - epstein - pandemics - donation	48	25_gates_billion_epstein_pandemics
26	thimerosal - immunizing - autism - rfk - shingles	47	26_thimerosal_immunizing_autism_rfk
27	miscarriages - menstruators - pcos - diethylstilbestrol - hysterectomies	40	27_miscarriages_menstruators_pcos_diethylstilbestrol
28	ufo - airship - missile - landed - pentagon	37	28_ufo_airship_missile_landed
29	shootings - sheriff - murdered - manhunt - maine	33	29_shootings_sheriff_murdered_manhunt
30	monkeypox - leishmaniasis - symptoms - pustules - ghebreyesus	31	30_monkeypox_leishmaniasis_symptoms_pustules
31	hannity - tucker - nielsen - newscast - viewers	31	31_hannity_tucker_nielsen_newscast
32	impeachment - donald - testifying - epstein - defendant	30	32_impeachment_donald_testifying_epstein
33	immunogenic - mrna - exosomes - sars - phagocytes	30	33_immunogenic_mrna_exosomes_sars
34	fbi - whistleblowers - prosecuting - wray - christopher	28	34_fbi_whistleblowers_prosecuting_wray
35	pfizer - revenue - billion - injectable - 529	27	35_pfizer_revenue_billion_injectable
36	vaers - reported - doses - 049 - shingles	26	36_vaers_reported_doses_049
37	clotting - thrombocytopenia - heparin - complications - astrazeneca	26	37_clotting_thrombocytopenia_heparin_complications
38	mayor - immigrants - bronx - hochul - shelters	24	38_mayor_immigrants_bronx_hochul
39	superfund - ohio - hazardous - derailed - tanker	24	39_superfund_ohio_hazardous_derailed
40	budweiser - distributors - mulvaney - lite - downgraded	23	40_budweiser_distributors_mulvaney_lite
41	biden - pandemic - vaccinate - announce - coordinator	22	41_biden_pandemic_vaccinate_announce
42	omicron - mutated - virulent - subvariants - genomic	22	42_omicron_mutated_virulent_subvariants
43	cdc - walensky - director - advised - proclamations	20	43_cdc_walensky_director_advised

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