MARTINI_enrich_BERTopic_TommyRobinsonNews

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_TommyRobinsonNews")

topic_model.get_topic_info()

Topic overview

• Number of topics: 160
• Number of training documents: 24830

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	rape - britain - arrested - muslim - girl	20	-1_rape_britain_arrested_muslim
0	migrants - drogheda - finglas - ballymun - irishman	15476	0_migrants_drogheda_finglas_ballymun
1	wembley - footballers - kneeling - booed - racism	250	1_wembley_footballers_kneeling_booed
2	brexiteers - corbyn - blair - prorogue - undemocratic	228	2_brexiteers_corbyn_blair_prorogue
3	whiteness - supremacists - racially - stereotyping - marxist	198	3_whiteness_supremacists_racially_stereotyping
4	jamal - allegations - almondbury - headteacher - kirklees	182	4_jamal_allegations_almondbury_headteacher
5	hamas - gaza - palestinians - israelis - gazan	172	5_hamas_gaza_palestinians_israelis
6	farmers - diesel - protests - stuttgart - motorways	170	6_farmers_diesel_protests_stuttgart
7	pfizer - mrna - myocarditis - injection - causes	164	7_pfizer_mrna_myocarditis_injection
8	illegals - britain - invade - smugglers - arrivals	164	8_illegals_britain_invade_smugglers
9	telegram - banned - amnesty - followers - scammers	150	9_telegram_banned_amnesty_followers
10	capitol - insurrectionists - stormed - homicide - january	142	10_capitol_insurrectionists_stormed_homicide
11	salman - jihadi - abdalraouf - manchester - safiyya	136	11_salman_jihadi_abdalraouf_manchester
12	migrants - borders - cbp - brownsville - invaded	134	12_migrants_borders_cbp_brownsville
13	trump - giuliani - hogan - triumphant - motorcade	131	13_trump_giuliani_hogan_triumphant
14	genoa - carabinieri - calabria - protesters - unvaxed	129	14_genoa_carabinieri_calabria_protesters
15	activists - vegans - milk - vandalise - harrods	121	15_activists_vegans_milk_vandalise
16	silenced - episode - subbed - rasmus - tntradio	120	16_silenced_episode_subbed_rasmus
17	ronvdesantis - florida - governor - mandates - maskless	111	17_ronvdesantis_florida_governor_mandates
18	trudeau - protestors - impounded - convoys - winnipeg	110	18_trudeau_protestors_impounded_convoys
19	fauci - wuhan - coronaviruses - researchers - laboratory	104	19_fauci_wuhan_coronaviruses_researchers
20	masked - unvaxxed - harassing - shoppers - exemption	103	20_masked_unvaxxed_harassing_shoppers
21	biden - psaki - reporters - teleprompter - monsignor	103	21_biden_psaki_reporters_teleprompter
22	bolsonaro - janeiro - moraes - neymar - argentines	102	22_bolsonaro_janeiro_moraes_neymar
23	antifa - vandalize - bellingham - fires - sacramento	99	23_antifa_vandalize_bellingham_fires
24	islamists - mohammed - france - beheaded - schoolteacher	96	24_islamists_mohammed_france_beheaded
25	australians - protesting - feminazi - victoria - tyrannised	94	25_australians_protesting_feminazi_victoria
26	bbc - viewers - sacked - pensioners - licensing	93	26_bbc_viewers_sacked_pensioners
27	stabbing - kilburn - croydon - tasered - khan	91	27_stabbing_kilburn_croydon_tasered
28	greenpeace - co2 - alarmists - noaa - moore	90	28_greenpeace_co2_alarmists_noaa
29	lampedusa - migrants - libya - melilla - invaded	90	29_lampedusa_migrants_libya_melilla
30	died - cardiac - footballers - laliga - collapses	87	30_died_cardiac_footballers_laliga
31	journalists - propagandists - headlines - murdoch - fakebook	84	31_journalists_propagandists_headlines_murdoch
32	rupaul - sexualising - parading - stripper - teletubbies	84	32_rupaul_sexualising_parading_stripper
33	parisians - protests - unvaccinated - passport - martinique	82	33_parisians_protests_unvaccinated_passport
34	livestream - gettr - 7pm - tomorrow - timcast	80	34_livestream_gettr_7pm_tomorrow
35	facemasks - maskwankery - mandating - wearing - homeschool	78	35_facemasks_maskwankery_mandating_wearing
36	khamenei - iranians - isfahan - khuzestan - shia	78	36_khamenei_iranians_isfahan_khuzestan
37	ballots - recount - counties - georgia - affidavits	77	37_ballots_recount_counties_georgia
38	davos - wefreports - globalists - crises - agenda	77	38_davos_wefreports_globalists_crises
39	biden - comey - delaware - declassified - pozharskyi	76	39_biden_comey_delaware_declassified
40	vaccine - injected - incentives - coercion - wtf	76	40_vaccine_injected_incentives_coercion
41	episodes - telford - rape - 27th - livestreamed	72	41_episodes_telford_rape_27th
42	transgenderism - dysphoria - castration - mutilating - hysterectomies	72	42_transgenderism_dysphoria_castration_mutilating
43	belmarsh - tommy - imprisonment - verdicts - reporters	72	43_belmarsh_tommy_imprisonment_verdicts
44	fdny - protesters - councilman - mandates - vaxxed	71	44_fdny_protesters_councilman_mandates
45	accused - rape - huddersfield - schoolgirl - zahid	71	45_accused_rape_huddersfield_schoolgirl
46	rhys - sonny - wishes - cancerous - rhabdomyo	69	46_rhys_sonny_wishes_cancerous
47	lgbtqwxyzs - tranny - indoctrination - sexualism - teacher	68	47_lgbtqwxyzs_tranny_indoctrination_sexualism
48	riots - morocco - algerian - toulon - belgium	68	48_riots_morocco_algerian_toulon
49	islamizing - allahu - teachers - blasphemous - batley	67	49_islamizing_allahu_teachers_blasphemous
50	migrants - housed - radisson - illegal - llanelli	64	50_migrants_housed_radisson_illegal
51	discredit - righteous - never - socials - biases	63	51_discredit_righteous_never_socials
52	djokovic - wimbledon - navratilova - australian - ballboy	63	52_djokovic_wimbledon_navratilova_australian
53	poland - lukashenka - błaszczak - border - invaders	62	53_poland_lukashenka_błaszczak_border
54	twitterfascism - musk - takeover - libsoftiktok - 44bn	62	54_twitterfascism_musk_takeover_libsoftiktok
55	kenosha - killed - tyler - supremacist - rifle	60	55_kenosha_killed_tyler_supremacist
56	transvestite - autogynephilia - trigender - lesbians - genders	59	56_transvestite_autogynephilia_trigender_lesbians
57	ghislaine - epstein - trafficking - billionaire - jpmorgan	59	57_ghislaine_epstein_trafficking_billionaire
58	paedophilia - perversions - fetishised - diapers - slutty	59	58_paedophilia_perversions_fetishised_diapers
59	bradford - stabbed - manslaughter - kamran - kershaw	58	59_bradford_stabbed_manslaughter_kamran
60	erdogan - migrants - bulgaria - islamistanis - koumoutsakos	58	60_erdogan_migrants_bulgaria_islamistanis
61	nurses - unvaccinated - sacked - hse - mandating	58	61_nurses_unvaccinated_sacked_hse
62	stabbed - gunman - islamist - nantes - moussa	57	62_stabbed_gunman_islamist_nantes
63	omicron - lockdowns - mutated - variants - immunising	56	63_omicron_lockdowns_mutated_variants
64	george - jury - fentanyl - bodycam - minneapolis	56	64_george_jury_fentanyl_bodycam
65	gaysagainstgroomers - homophobe - lgbtqia - padeophiles - indoctrination	55	65_gaysagainstgroomers_homophobe_lgbtqia_padeophiles
66	vaccinated - covid - deaths - 94 - nucleocapsid	53	66_vaccinated_covid_deaths_94
67	protesters - corbyn - lockdown - policeman - brixton	51	67_protesters_corbyn_lockdown_policeman
68	doxed - lizzie - allegations - tommy - sweeney	51	68_doxed_lizzie_allegations_tommy
69	fauci - vaccinated - fema - everybody - voluntarily	51	69_fauci_vaccinated_fema_everybody
70	protests - berlin - nuremberg - lockdown - merkel	50	70_protests_berlin_nuremberg_lockdown
71	hungary - soros - persecuted - brussels - vetoing	49	71_hungary_soros_persecuted_brussels
72	died - astrazeneca - clots - jessica - rhabdomyolysis	49	72_died_astrazeneca_clots_jessica
73	china - maoist - uyghurs - wengui - cangzhou	46	73_china_maoist_uyghurs_wengui
74	hatun - islamists - dawah - outspoken - threats	46	74_hatun_islamists_dawah_outspoken
75	tampons - feminazi - menstruate - men - menopausal	46	75_tampons_feminazi_menstruate_men
76	ivermectin - paxlovid - overdosed - olbermann - misinformation	45	76_ivermectin_paxlovid_overdosed_olbermann
77	macron - bastille - lyon - heckling - crowds	44	77_macron_bastille_lyon_heckling
78	austria - nazi - vaxxers - tyranny - schnedlitz	44	78_austria_nazi_vaxxers_tyranny
79	sadiq - londoners - mayor - statue - heckled	44	79_sadiq_londoners_mayor_statue
80	afghanistan - amrullah - guantanamo - blackhawk - screwed	44	80_afghanistan_amrullah_guantanamo_blackhawk
81	islamists - leicester - sikhs - rioted - rajasthan	44	81_islamists_leicester_sikhs_rioted
82	transgender - wimmins - swimmer - championships - weightlifter	44	82_transgender_wimmins_swimmer_championships
83	antisemitic - globalists - rabbis - jooooos - bolsheviks	43	83_antisemitic_globalists_rabbis_jooooos
84	invaded - migrant - brits - chaperoned - border	42	84_invaded_migrant_brits_chaperoned
85	wikileaks - extradited - whistleblower - julian - remand	42	85_wikileaks_extradited_whistleblower_julian
86	gunman - massacre - firepower - classroom - uvalde	41	86_gunman_massacre_firepower_classroom
87	queensland - quarantining - unvaccinated - novavax - mcgowan	41	87_queensland_quarantining_unvaccinated_novavax
88	nhs - ambulance - strike - underfunded - tiktok	41	88_nhs_ambulance_strike_underfunded
89	holland - rotterdam - lockdown - protesters - roermond	41	89_holland_rotterdam_lockdown_protesters
90	vaccinate - parental - jcvi - voluntary - overrule	41	90_vaccinate_parental_jcvi_voluntary
91	islamification - blasphemy - riots - korans - rasmus	40	91_islamification_blasphemy_riots_korans
92	blacks - racists - obama - anarchistic - marvin	40	92_blacks_racists_obama_anarchistic
93	vaxx - passport - compulsory - ministers - gareth	40	93_vaxx_passport_compulsory_ministers
94	islamophobes - islamistanis - tablighi - proselytise - ideology	40	94_islamophobes_islamistanis_tablighi_proselytise
95	urbanscoop - emails - spam - subscribed - important	40	95_urbanscoop_emails_spam_subscribed
96	zelensky - nuked - usa - missiles - billion	38	96_zelensky_nuked_usa_missiles
97	trudeau - ontarians - truckers - kamloops - freedoms	37	97_trudeau_ontarians_truckers_kamloops
98	livestream - horowitzfreedomcenter - 3pm - likesubscribeshare - brandnewtube	37	98_livestream_horowitzfreedomcenter_3pm_likesubscribeshare
99	carlson - spying - kremlin - gabbard - responds	36	99_carlson_spying_kremlin_gabbard
100	shamima - islamophobes - bride - assad - rapefugee	36	100_shamima_islamophobes_bride_assad
101	twitter - dorsey - censor - misinfo - violations	34	101_twitter_dorsey_censor_misinfo
102	charity - harrasment - extremists - hnh - bexleyheath	34	102_charity_harrasment_extremists_hnh
103	neil - monologue - always - saturday - tyranny	34	103_neil_monologue_always_saturday
104	donetsk - russians - grozny - gennadiy - wounded	33	104_donetsk_russians_grozny_gennadiy
105	rioters - bristol - vandalism - anarchy - destroyed	32	105_rioters_bristol_vandalism_anarchy
106	parliament - andrew - jabs - antisemitic - mordaunt	32	106_parliament_andrew_jabs_antisemitic
107	pfizer - spikevax - youngest - fda - injected	31	107_pfizer_spikevax_youngest_fda
108	gurkhas - casualties - veteran - whitehall - cenotaph	31	108_gurkhas_casualties_veteran_whitehall
109	monkeypox - outbreak - rash - warned - promiscuous	31	109_monkeypox_outbreak_rash_warned
110	pandemics - gates - global - oxfam - congo	30	110_pandemics_gates_global_oxfam
111	maricopa - ballots - recount - supervisors - uncounted	30	111_maricopa_ballots_recount_supervisors
112	supremacist - garvey - brixton - black - marxism	29	112_supremacist_garvey_brixton_black
113	silenced - christiansborg - parliament - invited - presenter	29	113_silenced_christiansborg_parliament_invited
114	immigrants - patrols - britain - smuggler - dover	29	114_immigrants_patrols_britain_smuggler
115	disney - pansexual - latoya - allen - woke	29	115_disney_pansexual_latoya_allen
116	assaulted - kidnapper - maidenhead - bromley - bearded	28	116_assaulted_kidnapper_maidenhead_bromley
117	zealanders - jacinda - faced - stalinist - minister	28	117_zealanders_jacinda_faced_stalinist
118	tucker - fox - antisemitism - timeline - glenn	28	118_tucker_fox_antisemitism_timeline
119	tommy - lawfare - judge - witnesses - todays	28	119_tommy_lawfare_judge_witnesses
120	migrants - lesvos - kathimerini - illegal - mainland	28	120_migrants_lesvos_kathimerini_illegal
121	nazis - ukrainians - pogroms - zhytomyr - yaakov	28	121_nazis_ukrainians_pogroms_zhytomyr
122	boers - johannesburg - bloemfontein - genocidal - white	27	122_boers_johannesburg_bloemfontein_genocidal
123	dictator - andrews - melbourne - parliament - enforced	26	123_dictator_andrews_melbourne_parliament
124	karabakh - armenians - turkish - islamist - genocides	26	124_karabakh_armenians_turkish_islamist
125	salford - burnley - tommorow - 5pm - postcode	26	125_salford_burnley_tommorow_5pm
126	swedens - malmo - somalia - migration - shootings	26	126_swedens_malmo_somalia_migration
127	neighbourhoods - southend - councillors - minute - wherever	26	127_neighbourhoods_southend_councillors_minute
128	telford - victims - constabulary - paedophillia - donate	25	128_telford_victims_constabulary_paedophillia
129	rape - convicted - mohamed - deported - falkenberg	25	129_rape_convicted_mohamed_deported
130	votetommy - ukip - polling - registered - everyone	25	130_votetommy_ukip_polling_registered
131	amazon - banned - trsilenced - biographies - ordered	24	131_amazon_banned_trsilenced_biographies
132	protesters - lockdown - london - underground - paulbrown_uk	24	132_protesters_lockdown_london_underground
133	abortions - contraception - unborn - gestation - inseminate	24	133_abortions_contraception_unborn_gestation
134	eu - mislav - croatia - billions - legislative	23	134_eu_mislav_croatia_billions
135	stickers - tommy - everywhere - stooges - imprisoning	23	135_stickers_tommy_everywhere_stooges
136	darrel - waukesha - massacre - farrakhan - suspect	23	136_darrel_waukesha_massacre_farrakhan
137	beetles - meelworm - edible - allergens - butter	23	137_beetles_meelworm_edible_allergens
138	proudboysusa - fascists - capitol - march - shouts	23	138_proudboysusa_fascists_capitol_march
139	vaccinated - fdny - sotomayor - mandate - denied	23	139_vaccinated_fdny_sotomayor_mandate
140	netherlands - geert - bjorn - moroccans - semitism	22	140_netherlands_geert_bjorn_moroccans
141	farmers - protests - brieuc - rubbish - toulouse	22	141_farmers_protests_brieuc_rubbish
142	ballyfermot - assaulting - migrant - kidnappings - dundalk	22	142_ballyfermot_assaulting_migrant_kidnappings
143	rochdale - kirklees - arrests - dewsbury - abuse	22	143_rochdale_kirklees_arrests_dewsbury
144	convoy - patriotic - welcome - whitehouse - hagerstown	22	144_convoy_patriotic_welcome_whitehouse
145	abused - rochdale - witnesses - scandals - iicsa	22	145_abused_rochdale_witnesses_scandals
146	asylum - guantanamo - yorkshire - linton - populated	22	146_asylum_guantanamo_yorkshire_linton
147	telford - samantha - rape - trafficked - perpetrators	22	147_telford_samantha_rape_trafficked
148	illegals - deported - shithole - come - trafficker	22	148_illegals_deported_shithole_come
149	cathedrals - nantes - steeple - destroyed - flames	21	149_cathedrals_nantes_steeple_destroyed
150	lindell - mike - pillow - suing - newsmax	21	150_lindell_mike_pillow_suing
151	vaccine - army - mandatory - refusing - discharged	21	151_vaccine_army_mandatory_refusing
152	libtards - wokeness - sociopathic - wankers - deluded	21	152_libtards_wokeness_sociopathic_wankers
153	assaulted - abducting - convict - abdulrahman - maidenhead	21	153_assaulted_abducting_convict_abdulrahman
154	zealand - protesters - haka - masked - tyranny	21	154_zealand_protesters_haka_masked
155	mullingar - barracks - migrants - belfast - unvetted	20	155_mullingar_barracks_migrants_belfast
156	lawfare - solicitors - donate - leaked - charges	20	156_lawfare_solicitors_donate_leaked
157	colonel - commie - servicemembers - armed - wankers	20	157_colonel_commie_servicemembers_armed
158	boxers - luton - jordan - middleweight - promoters	20	158_boxers_luton_jordan_middleweight

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