MARTINI_enrich_BERTopic_MurderTheMedia

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_MurderTheMedia")

topic_model.get_topic_info()

Topic overview

• Number of topics: 50
• Number of training documents: 7519

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	trump - murderthemedia - states - china - never	20	-1_trump_murderthemedia_states_china
0	vaccinated - pfizer - vaxx - monkeypox - shots	4322	0_vaccinated_pfizer_vaxx_monkeypox
1	mistrial - jurors - kenosha - testimony - firearm	238	1_mistrial_jurors_kenosha_testimony
2	billionaire - dorsey - spacex - tweeted - cryptocurrencies	183	2_billionaire_dorsey_spacex_tweeted
3	trannies - lgbtq - pedophilia - nonbinary - dysphoria	182	3_trannies_lgbtq_pedophilia_nonbinary
4	ukraine - donetsk - pentagon - nordstream - ww3	142	4_ukraine_donetsk_pentagon_nordstream
5	gunman - killed - arrested - suspects - officers	140	5_gunman_killed_arrested_suspects
6	fbi - informants - terrorist - whistleblower - nassar	136	6_fbi_informants_terrorist_whistleblower
7	murderthemedia - gab - instagram - hellmuzzle - carlmtm	120	7_murderthemedia_gab_instagram_hellmuzzle
8	nerds - cola - lmfao - noooooooooooo - mcrib	112	8_nerds_cola_lmfao_noooooooooooo
9	propagandized - totalitarian - news - tiananmen - rumsfeld	99	9_propagandized_totalitarian_news_tiananmen
10	israel - netanyahu - mossad - hamas - eliyahu	98	10_israel_netanyahu_mossad_hamas
11	prison - pushups - idk - update - keto	94	11_prison_pushups_idk_update
12	tonight - perry - weimerica - stream - episode	91	12_tonight_perry_weimerica_stream
13	theanthonyrogersshow - mike - murderthemedia - tonight - dougie	88	13_theanthonyrogersshow_mike_murderthemedia_tonight
14	capitol - officers - militia - rioters - howard	79	14_capitol_officers_militia_rioters
15	radioblackballed - murderthemedia - dlive - 11pm - episode	78	15_radioblackballed_murderthemedia_dlive_11pm
16	blacks - kkklansman - supremacists - superpowers - white	77	16_blacks_kkklansman_supremacists_superpowers
17	biden - kamala - democrats - delaware - hunter	73	17_biden_kamala_democrats_delaware
18	telegram - whatsapp - google - privacy - advertisers	70	18_telegram_whatsapp_google_privacy
19	homesteads - chickens - livestock - farmer - sow	64	19_homesteads_chickens_livestock_farmer
20	antifa - rioters - portland - militants - assaulted	61	20_antifa_rioters_portland_militants
21	thunderdometv - showtime - recaps - friday - blacks	61	21_thunderdometv_showtime_recaps_friday
22	ballots - electors - recount - michigan - megathread	56	22_ballots_electors_recount_michigan
23	live - episodes - molester - daughters - apostate	53	23_live_episodes_molester_daughters
24	illegals - deportations - honduras - border - mcallen	53	24_illegals_deportations_honduras_border
25	sheriffs - authoritarianism - defund - enforce - vandals	49	25_sheriffs_authoritarianism_defund_enforce
26	ghislaine - clinton - jeffrey - threesomes - convicted	49	26_ghislaine_clinton_jeffrey_threesomes
27	dicknecarlo - donate - freenick - nicholas - brothers	42	27_dicknecarlo_donate_freenick_nicholas
28	dlive - balrog - telegram - jamie - fedophiles	40	28_dlive_balrog_telegram_jamie
29	thunderdometv - live - youtube - shingtv - murder	38	29_thunderdometv_live_youtube_shingtv
30	explosion - corruptifornia - tornadoes - fatalities - firefighters	34	30_explosion_corruptifornia_tornadoes_fatalities
31	inspirational - dads - courage - mindful - valentine	31	31_inspirational_dads_courage_mindful
32	firearms - cicilline - legislation - prohibit - defund	31	32_firearms_cicilline_legislation_prohibit
33	starring - dafoe - johnny - gangsters - 1991	30	33_starring_dafoe_johnny_gangsters
34	islamists - charlemagne - edouard - macronland - mohamed	30	34_islamists_charlemagne_edouard_macronland
35	murder - marla - episodes - militia - whites	30	35_murder_marla_episodes_militia
36	taliban - kabul - kunduz - zabihullah - outpost	29	36_taliban_kabul_kunduz_zabihullah
37	apostles - catholic - heretics - podcast - unvaxxed	28	37_apostles_catholic_heretics_podcast
38	hotline - samaritan - enzo - catholicism - heaven	27	38_hotline_samaritan_enzo_catholicism
39	tbsp - ingredients - jalapenos - pickling - skillet	27	39_tbsp_ingredients_jalapenos_pickling
40	thunderdometv - chat - streaming - storm - 5pm	27	40_thunderdometv_chat_streaming_storm
41	republicans - impeachment - pelosi - congressman - mccarthy	26	41_republicans_impeachment_pelosi_congressman
42	mealworm - locusts - larvae - prawn - edible	25	42_mealworm_locusts_larvae_prawn
43	lockdowns - melbourne - adelaide - victoria - organisers	24	43_lockdowns_melbourne_adelaide_victoria
44	africa - 9pm - carl - nigga - dunk	24	44_africa_9pm_carl_nigga
45	stimulus - pelosi - bipartisan - fdr - trillion	23	45_stimulus_pelosi_bipartisan_fdr
46	confederates - chancellorsville - manassas - gettysburgmuseumofhistory - 1861	22	46_confederates_chancellorsville_manassas_gettysburgmuseumofhistory
47	tshirt - hoodies - fundraiser - nicks - sold	22	47_tshirt_hoodies_fundraiser_nicks
48	airlines - taxiing - stranded - goddamn - cabo	21	48_airlines_taxiing_stranded_goddamn

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