MARTINI_enrich_BERTopic_BritainFirst

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_BritainFirst")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 112
  • Number of training documents: 13176
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 brexit - islamist - twitter - arrested - wakefield 20 -1_brexit_islamist_twitter_arrested
0 novotel - migrants - accommodation - leeds - gatwick 7332 0_novotel_migrants_accommodation_leeds
1 trump - ballots - clinton - impeachment - michigan 178 1_trump_ballots_clinton_impeachment
2 calais - refugees - dunkirk - tents - sudanese 168 2_calais_refugees_dunkirk_tents
3 marseille - macron - zemmour - jean - president 165 3_marseille_macron_zemmour_jean
4 lockdowns - omicron - vaccinated - nhs - morons 162 4_lockdowns_omicron_vaccinated_nhs
5 antifa - rioters - oregon - molotov - flames 141 5_antifa_rioters_oregon_molotov
6 poland - migrants - border - minsk - guards 120 6_poland_migrants_border_minsk
7 membership - british - fightback - nationalist - steadfast 117 7_membership_british_fightback_nationalist
8 taliban - afghans - kandahar - soldiers - suhail 108 8_taliban_afghans_kandahar_soldiers
9 salford - dartford - swanscombe - elections - cambridgeshire 107 9_salford_dartford_swanscombe_elections
10 meghan - harry - royal - oprah - hypocrites 106 10_meghan_harry_royal_oprah
11 migrants - crossing - yesterday - boat - 2021 93 11_migrants_crossing_yesterday_boat
12 barracks - migrant - bexhill - pembrokeshire - dambusters 93 12_barracks_migrant_bexhill_pembrokeshire
13 londonistan - stabbings - khan - mayor - lawless 86 13_londonistan_stabbings_khan_mayor
14 aegean - cyprus - erdogan - smugglers - nikos 86 14_aegean_cyprus_erdogan_smugglers
15 dover - harbour - immigrants - grimsby - disembarked 86 15_dover_harbour_immigrants_grimsby
16 biden - delaware - forgets - donnell - alzheimers 85 16_biden_delaware_forgets_donnell
17 dublin - mullingar - kilkenny - ulster - crimewaves 80 17_dublin_mullingar_kilkenny_ulster
18 traitors - extremist - hope - exposing - tommy 80 18_traitors_extremist_hope_exposing
19 rioters - blacks - minneapolis - victimhood - damond 80 19_rioters_blacks_minneapolis_victimhood
20 england - luton - multiculturalism - cockney - saxons 78 20_england_luton_multiculturalism_cockney
21 psalm - philippians - supplication - worry - angels 77 21_psalm_philippians_supplication_worry
22 reparations - colston - statues - enslaved - vandalised 76 22_reparations_colston_statues_enslaved
23 constables - politically - sacked - newham - robberies 74 23_constables_politically_sacked_newham
24 golding - speeches - paul - regional - pontefract 70 24_golding_speeches_paul_regional
25 border - texas - rio - smugglers - venezuela 68 25_border_texas_rio_smugglers
26 deportations - accommodation - holidaymakers - 8million - taxpayers 68 26_deportations_accommodation_holidaymakers_8million
27 corbyn - antisemitism - starmer - sympathisers - gaza 67 27_corbyn_antisemitism_starmer_sympathisers
28 transgender - women - menstruate - olympic - weightlifter 66 28_transgender_women_menstruate_olympic
29 lampedusa - migration - disembarked - malta - libya 65 29_lampedusa_migration_disembarked_malta
30 censorship - totalitarianism - brainwashed - demonise - moronic 63 30_censorship_totalitarianism_brainwashed_demonise
31 bletchley - battles - trafalgar - anzac - 1944 62 31_bletchley_battles_trafalgar_anzac
32 lifeboat - rnli - smuggling - beachgoers - bangladesh 61 32_lifeboat_rnli_smuggling_beachgoers
33 ballymena - golding - bail - terrorism - solicitor 61 33_ballymena_golding_bail_terrorism
34 borders - mexico - mcallen - democrats - doomed 60 34_borders_mexico_mcallen_democrats
35 gaza - israelis - ashkelon - airstrikes - islamists 60 35_gaza_israelis_ashkelon_airstrikes
36 lockdown - arrested - protest - peckham - policeman 56 36_lockdown_arrested_protest_peckham
37 lampedusa - borders - invading - disembarking - armada 54 37_lampedusa_borders_invading_disembarking
38 minibuses - campaigning - scotland - embarked - churchill 54 38_minibuses_campaigning_scotland_embarked
39 conference - tickets - nuneaton - 2021 - southampton 54 39_conference_tickets_nuneaton_2021
40 paul - persecution - golding - spearheaded - paperback 53 40_paul_persecution_golding_spearheaded
41 tommy - assaulting - paedophile - magistrates - trumped 52 41_tommy_assaulting_paedophile_magistrates
42 melilla - migrants - africa - gibraltar - guardsmen 51 42_melilla_migrants_africa_gibraltar
43 mosques - ramadan - praying - adhan - call 51 43_mosques_ramadan_praying_adhan
44 beheaded - aoussaoui - gunman - radicalized - mogadishu 50 44_beheaded_aoussaoui_gunman_radicalized
45 великобритания - россия - голдинг - партии - могиле 50 45_великобритания_россия_голдинг_партии
46 patriotmerchandise - hoodie - shirts - merchandise - products 50 46_patriotmerchandise_hoodie_shirts_merchandise
47 shamima - jihadist - returning - shariah - bride 49 47_shamima_jihadist_returning_shariah
48 ulster - ballymena - unionist - newtownards - bfni 48 48_ulster_ballymena_unionist_newtownards
49 popes - benedict - sacraments - archbishopric - persecuted 46 49_popes_benedict_sacraments_archbishopric
50 helmand - corporal - died - battalion - stephen 45 50_helmand_corporal_died_battalion
51 jesus - blessed - whosoever - persecuted - everlasting 45 51_jesus_blessed_whosoever_persecuted
52 racism - brainwash - curriculum - white - decolonise 45 52_racism_brainwash_curriculum_white
53 whitephobia - whiter - silence - systemically - consensual 42 53_whitephobia_whiter_silence_systemically
54 refugees - smugglers - genuine - freeloading - ukrainian 42 54_refugees_smugglers_genuine_freeloading
55 rotherham - rape - scandals - islamist - nawaz 41 55_rotherham_rape_scandals_islamist
56 mexicans - caravan - tapachula - cartels - marches 40 56_mexicans_caravan_tapachula_cartels
57 britbox - broadcaster - stormzy - gary - complain 39 57_britbox_broadcaster_stormzy_gary
58 referendum - deadline - approved - september - 24th 39 58_referendum_deadline_approved_september
59 lithuania - belarusian - rudninkai - trespassers - sanctions 39 59_lithuania_belarusian_rudninkai_trespassers
60 deported - offenders - jamaicans - degenerates - partygate 38 60_deported_offenders_jamaicans_degenerates
61 britannia - wigan - protests - deported - schoolgirls 38 61_britannia_wigan_protests_deported
62 share - telegram - videos - everywhere - retweet 38 62_share_telegram_videos_everywhere
63 raped - convicted - rashid - hussain - kirklees 37 63_raped_convicted_rashid_hussain
64 charlenedownes - blackpool - murdered - saddleworth - vicky 37 64_charlenedownes_blackpool_murdered_saddleworth
65 crimea - russophobia - nordstream - katyusha - vladimir 37 65_crimea_russophobia_nordstream_katyusha
66 buckinghamshire - middlesbrough - rochdale - telford - perpetrators 37 66_buckinghamshire_middlesbrough_rochdale_telford
67 libya - deporting - amnesty - eritrean - escaped 36 67_libya_deporting_amnesty_eritrean
68 leicestershire - birmingham - activists - harassed - gestapo 34 68_leicestershire_birmingham_activists_harassed
69 terrorist - qaeda - murdering - knifeman - sharif 34 69_terrorist_qaeda_murdering_knifeman
70 germany - rioting - rotterdam - baghdad - allensbach 34 70_germany_rioting_rotterdam_baghdad
71 sunday - blessings - christian - worship - supporters 33 71_sunday_blessings_christian_worship
72 canvassing - north - wigan - altrincham - winning 33 72_canvassing_north_wigan_altrincham
73 activist - meetings - welcomed - tonight - sussex 33 73_activist_meetings_welcomed_tonight
74 dlive - paul - golding - 7pm - bitchute 33 74_dlive_paul_golding_7pm
75 apartheid - johannesburg - zimbabwe - boers - looters 33 75_apartheid_johannesburg_zimbabwe_boers
76 twitter - musk - shadowban - msnbc - shareholders 32 76_twitter_musk_shadowban_msnbc
77 canaryislands - spaniards - morocco - asylum - arguineguin 32 77_canaryislands_spaniards_morocco_asylum
78 hungary - referendum - prohibits - lgbtq - viktor 32 78_hungary_referendum_prohibits_lgbtq
79 twitter - trumpbook - lindell - censorship - influencers 31 79_twitter_trumpbook_lindell_censorship
80 islamist - jihadists - radicalisation - mi5 - fear 31 80_islamist_jihadists_radicalisation_mi5
81 britannia - glorious - silbury - stonehenge - fought 31 81_britannia_glorious_silbury_stonehenge
82 universities - whiteness - decolonise - walkout - lipscomb 31 82_universities_whiteness_decolonise_walkout
83 sweden - gangs - somalis - gottsunda - mikael 30 83_sweden_gangs_somalis_gottsunda
84 paedophiles - lgbtqoajsrgoauib - sexualisation - brainwashing - pansexual 30 84_paedophiles_lgbtqoajsrgoauib_sexualisation_brainwashing
85 eurosceptics - juncker - undemocratic - voted - remain 30 85_eurosceptics_juncker_undemocratic_voted
86 europeans - globalist - migration - islamophobe - invaded 29 86_europeans_globalist_migration_islamophobe
87 capitol - rioters - pelosi - msnbc - deputies 29 87_capitol_rioters_pelosi_msnbc
88 armagh - killed - bombings - fusiliers - 1974 29 88_armagh_killed_bombings_fusiliers
89 bfd - bodyguards - training - aikido - krav 28 89_bfd_bodyguards_training_aikido
90 newspapers - subscribed - patriot - worldwide - mainstream 28 90_newspapers_subscribed_patriot_worldwide
91 queen - funeral - westminster - dignitaries - carriage 27 91_queen_funeral_westminster_dignitaries
92 transwomen - lesbian - stonewall - matchmaker - elliot 26 92_transwomen_lesbian_stonewall_matchmaker
93 christianity - crusade - englishman - blesses - rediscovering 26 93_christianity_crusade_englishman_blesses
94 pray - almighty - victory - nationalists - strengthen 25 94_pray_almighty_victory_nationalists
95 dartford - campaigning - essex - canvassers - east 25 95_dartford_campaigning_essex_canvassers
96 livestream - thelionsradio - liamwalsall - tomorrow - 6pm 24 96_livestream_thelionsradio_liamwalsall_tomorrow
97 cathedrals - firebombed - flames - saint - france 23 97_cathedrals_firebombed_flames_saint
98 4climate - antarctica - coldest - thunberg - alarmists 23 98_4climate_antarctica_coldest_thunberg
99 parler - followers - alternatives - ashleasimonnews - censored 23 99_parler_followers_alternatives_ashleasimonnews
100 schoolteacher - mohammed - blasphemy - batley - cartoon 22 100_schoolteacher_mohammed_blasphemy_batley
101 postal - stamp - wellingborough - votes - urgently 22 101_postal_stamp_wellingborough_votes
102 britannia - camp - august - activist - 2022 22 102_britannia_camp_august_activist
103 muslims - birmingham - temple - riots - smethwick 22 103_muslims_birmingham_temple_riots
104 islamophobia - taqiyya - hijab - holiest - shitholes 21 104_islamophobia_taqiyya_hijab_holiest
105 asylum - hostel - residents - hull - flintshire 21 105_asylum_hostel_residents_hull
106 asylum - murdered - rapist - assaulting - grandmother 21 106_asylum_murdered_rapist_assaulting
107 parliament - remainers - prorogue - amendments - undemocratic 21 107_parliament_remainers_prorogue_amendments
108 ukprotests - trending - leftists - blmlondon - followers 20 108_ukprotests_trending_leftists_blmlondon
109 belfastlive - defrauding - jolene - verdict - commissioner 20 109_belfastlive_defrauding_jolene_verdict
110 wakefield - campaigning - palestinians - councillors - thursday 20 110_wakefield_campaigning_palestinians_councillors

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
Downloads last month
5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support