MARTINI_enrich_BERTopic_markacollett

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_markacollett")

topic_model.get_topic_info()

Topic overview

• Number of topics: 66
• Number of training documents: 7095

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	bitchute - nationalists - britain - whites - migrant	21	-1_bitchute_nationalists_britain_whites
0	dlive - patriotictalk - speakfreeradio - 7pm - brittania	3810	0_dlive_patriotictalk_speakfreeradio_7pm
1	shootings - murders - nonwhite - fbi - terrorist	219	1_shootings_murders_nonwhite_fbi
2	vaccinated - myocarditis - jabs - cdc - deaths	171	2_vaccinated_myocarditis_jabs_cdc
3	plandemic - lockdowns - omicron - governed - freedoms	166	3_plandemic_lockdowns_omicron_governed
4	trump - predictions - unfalsifiable - rigged - unelected	115	4_trump_predictions_unfalsifiable_rigged
5	tea - sam - grandmatowlers - nationalist - england	110	5_tea_sam_grandmatowlers_nationalist
6	whiteskins - racist - minority - rohirrim - disney	109	6_whiteskins_racist_minority_rohirrim
7	dlive - patriot - albion - thefallofwesternman - 3pm	103	7_dlive_patriot_albion_thefallofwesternman
8	dlive - albion - review - kubrick - horror	94	8_dlive_albion_review_kubrick
9	ukrainians - donetsk - zelensky - putin - invasion	91	9_ukrainians_donetsk_zelensky_putin
10	wlm_indigenous_peoples_day_2022 - international_day_pro - white_action_instructions - fightback - august	89	10_wlm_indigenous_peoples_day_2022_international_day_pro_white_action_instructions_fightback
11	transwoman - feminism - conservative - genitals - criminalises	80	11_transwoman_feminism_conservative_genitals
12	gaza - palestinians - israelis - naftali - atrocities	77	12_gaza_palestinians_israelis_naftali
13	llanelli - patrioticalternative - carmarthen - migrants - westminster	65	13_llanelli_patrioticalternative_carmarthen_migrants
14	policed - rioters - arrest - lockdowners - jailers	60	14_policed_rioters_arrest_lockdowners
15	livestream - thegreatresistancenortheastuk - albion - fightback - january	60	15_livestream_thegreatresistancenortheastuk_albion_fightback
16	patrioticalternative - protestors - wales - sexualised - queen	59	16_patrioticalternative_protestors_wales_sexualised
17	dlive - patriotic - weekly - 7pm - britannia	58	17_dlive_patriotic_weekly_7pm
18	twitter - censorship - musk - liberals - banned	57	18_twitter_censorship_musk_liberals
19	nationalist - odysee - 9pm - team - ukrainian	56	19_nationalist_odysee_9pm_team
20	manchester - patrioticalternative - homeless - donate - parcels	54	20_manchester_patrioticalternative_homeless_donate
21	paedophiles - lgbtpaedo - molesting - sexualise - indoctrinate	50	21_paedophiles_lgbtpaedo_molesting_sexualise
22	prison - james - longshanks - swansea - givesendgo	49	22_prison_james_longshanks_swansea
23	migrants - patrioticalternative - protest - yorkshire - novotel	48	23_migrants_patrioticalternative_protest_yorkshire
24	today - chief_moody - 5pm - airing - bigtime	47	24_today_chief_moody_5pm_airing
25	britons - majority - birmingham - demographics - muslims	46	25_britons_majority_birmingham_demographics
26	bitchute - archive - weekly - morgoth - gariepy	46	26_bitchute_archive_weekly_morgoth
27	7pm - britannia - podcast - invited - guys	45	27_7pm_britannia_podcast_invited
28	warzone - tournaments - streamed - markyc - toutube	42	28_warzone_tournaments_streamed_markyc
29	dlive - 7pm - weekly - britannia - guests	41	29_dlive_7pm_weekly_britannia
30	rape - criminalising - victims - rotherham - brutalised	39	30_rape_criminalising_victims_rotherham
31	jewish_power - semitism - swastikas - sabbath - shunned	38	31_jewish_power_semitism_swastikas_sabbath
32	video - horror - reviews - sequel - blacula	36	32_video_horror_reviews_sequel
33	gbp - poverty - petrol - billion - thames	36	33_gbp_poverty_petrol_billion
34	patalkchannel - 9pm - libtards - peem - join	36	34_patalkchannel_9pm_libtards_peem
35	congratulations - morning - dads - november - strive	34	35_congratulations_morning_dads_november
36	britain - immigrants - albanians - 2022 - million	33	36_britain_immigrants_albanians_2022
37	nationalists - speeches - patv - lewthwaite - pembrokeshire	33	37_nationalists_speeches_patv_lewthwaite
38	wembley - footballers - patriotard - qatar - kneeling	32	38_wembley_footballers_patriotard_qatar
39	dlive - unvaxxed - 7pm - albion - invade	31	39_dlive_unvaxxed_7pm_albion
40	patrioticartscommunity - creative - drawings - contributing - entries	31	40_patrioticartscommunity_creative_drawings_contributing
41	britain - monarch - elizabeth - mourning - celebrating	29	41_britain_monarch_elizabeth_mourning
42	zionist - london - hooligan - tommy - clashed	29	42_zionist_london_hooligan_tommy
43	christmas - adverts - whitest - sainsbury - aliens	27	43_christmas_adverts_whitest_sainsbury
44	livestream - castlevania - play - battlegrounds - 9pm	26	44_livestream_castlevania_play_battlegrounds
45	migrants - conservative - australian - illegally - points	26	45_migrants_conservative_australian_illegally
46	kidnapped - rapists - lola - deportation - algerian	26	46_kidnapped_rapists_lola_deportation
47	populists - bundestag - extremists - netherlands - immigration	26	47_populists_bundestag_extremists_netherlands
48	bitchute - patriotic - weekly - podcast - britain	25	48_bitchute_patriotic_weekly_podcast
49	johannesburg - africans - genocide - slum - unsustainable	24	49_johannesburg_africans_genocide_slum
50	renfrewshire - erskine - counterprotesting - msps - river	24	50_renfrewshire_erskine_counterprotesting_msps
51	migrants - briton - hostel - rents - illegally	24	51_migrants_briton_hostel_rents
52	patrioticalternative - litter - merseyside - altrincham - parks	24	52_patrioticalternative_litter_merseyside_altrincham
53	putin - sanctions - nordstreams - dissidents - autocracy	24	53_putin_sanctions_nordstreams_dissidents
54	merseyside - patrioticalternative - northwest - events - barnoldswick	23	54_merseyside_patrioticalternative_northwest_events
55	tonight - live - moody - 12pm - spoooookey	23	55_tonight_live_moody_12pm
56	murdered - bradley - gledhill - defendants - smurphytv	23	56_murdered_bradley_gledhill_defendants
57	david - awakening - interviewed - tucker - radio	23	57_david_awakening_interviewed_tucker
58	bitchute - patriotic - weekly - videos - styxhexenhammer	22	58_bitchute_patriotic_weekly_videos
59	sam - sentenced - prosecuting - inciting - martyr	22	59_sam_sentenced_prosecuting_inciting
60	bbc - defund - paying - viewership - whites	22	60_bbc_defund_paying_viewership
61	zionists - netanyahu - gaza - deportation - demonised	22	61_zionists_netanyahu_gaza_deportation
62	live - mood - tomorrow - gmt - troops	22	62_live_mood_tomorrow_gmt
63	live - patriotic - 7pm - albion - paul	21	63_live_patriotic_7pm_albion
64	patriotic - weekly - 7pm - live - panel	21	64_patriotic_weekly_7pm_live

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