MARTINI_enrich_BERTopic_PrivateCanadianNews

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_PrivateCanadianNews")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 142
  • Number of training documents: 19024
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 putin - ukraine - trudeau - fbi - covid 20 -1_putin_ukraine_trudeau_fbi
0 bullshit - manipulated - everywhere - lies - doublespeak 10295 0_bullshit_manipulated_everywhere_lies
1 awakening - consciousness - realise - humanity - everything 471 1_awakening_consciousness_realise_humanity
2 acanadian - omfg - tyranny - bbc - wake 297 2_acanadian_omfg_tyranny_bbc
3 macron - riots - rennes - demonstrators - march 256 3_macron_riots_rennes_demonstrators
4 bolsonaro - dilma - brasilia - rondonopolis - paulo 206 4_bolsonaro_dilma_brasilia_rondonopolis
5 farms - saskatchewan - manure - nitrate - cull 197 5_farms_saskatchewan_manure_nitrate
6 gaza - hamas - israelis - airstrikes - islamist 196 6_gaza_hamas_israelis_airstrikes
7 cbdc - bitcoin - cashless - centralized - bankers 190 7_cbdc_bitcoin_cashless_centralized
8 mariupol - severodonetsk - mizintsev - evacuated - militants 185 8_mariupol_severodonetsk_mizintsev_evacuated
9 davos - wef - globalist - governments - technocratic 184 9_davos_wef_globalist_governments
10 musk - dorsey - cnn - wechat - executives 181 10_musk_dorsey_cnn_wechat
11 zelenskyy - yanukovych - volodymyr - serhiy - 40bn 165 11_zelenskyy_yanukovych_volodymyr_serhiy
12 tesla - electricity - vehicles - fuels - kwh 161 12_tesla_electricity_vehicles_fuels
13 bioweapons - biden - pentagon - zakharova - laboratories 154 13_bioweapons_biden_pentagon_zakharova
14 fauci - hiv - coronaviruses - sarsii - institutes 146 14_fauci_hiv_coronaviruses_sarsii
15 plandemic - sovereignty - ghebreyesus - amendments - h5n1 133 15_plandemic_sovereignty_ghebreyesus_amendments
16 trafficked - pedophiles - pornhub - darknet - liliana 130 16_trafficked_pedophiles_pornhub_darknet
17 tiananmen - protests - chongqing - shenzhen - lockdowns 129 17_tiananmen_protests_chongqing_shenzhen
18 biden - hooker - doj - whistleblowers - hawley 121 18_biden_hooker_doj_whistleblowers
19 trudeau - cbc - dicktator - hecklers - treasonous 118 19_trudeau_cbc_dicktator_hecklers
20 unvaxxed - vaxx - immunize - ukcitizen2021 - vindicated 107 20_unvaxxed_vaxx_immunize_ukcitizen2021
21 gates - vaccinate - bioterror - hpv - controligarchs 98 21_gates_vaccinate_bioterror_hpv
22 trudeau - canadianfrontlinenurses - cbc - blockades - truckers 95 22_trudeau_canadianfrontlinenurses_cbc_blockades
23 gazprom - rubles - crude - sanctions - eurozone 94 23_gazprom_rubles_crude_sanctions
24 pcr - ncov - influenza - tested - swab 93 24_pcr_ncov_influenza_tested
25 taiwan - pelosi - prc - unilateralism - xiamen 89 25_taiwan_pelosi_prc_unilateralism
26 vaccinated - deaths - covid - 2021 - dowd 88 26_vaccinated_deaths_covid_2021
27 pfizer - lawsuit - spikevax - glaxosmithkline - falsified 88 27_pfizer_lawsuit_spikevax_glaxosmithkline
28 putin - sergei - hegemony - demilitarising - libya 88 28_putin_sergei_hegemony_demilitarising
29 epstein - jpmorgan - billionaire - lawsuits - blackmail 88 29_epstein_jpmorgan_billionaire_lawsuits
30 biometric - identifiers - ktdi - verification - transunion 87 30_biometric_identifiers_ktdi_verification
31 ballots - sabotaged - lindell - newsmax - maricopa 85 31_ballots_sabotaged_lindell_newsmax
32 lockdowns - 15minute - hafencity - neighbourhoods - edmontonians 85 32_lockdowns_15minute_hafencity_neighbourhoods
33 starlink - satellites - canaveral - aliens - cosmonaut 79 33_starlink_satellites_canaveral_aliens
34 abortions - scotus - kamala - overturning - planned 77 34_abortions_scotus_kamala_overturning
35 chancellor - westminster - sunak - partygate - sacked 76 35_chancellor_westminster_sunak_partygate
36 transgenderism - brainwashes - mutilation - omfuckingg - gynaecologist 72 36_transgenderism_brainwashes_mutilation_omfuckingg
37 myocarditis - coronary - defibrillators - died - clot 71 37_myocarditis_coronary_defibrillators_died
38 desantis - florida - repealing - felony - impanelment 69 38_desantis_florida_repealing_felony
39 handguns - alberta - sheriffs - assault - enforce 66 39_handguns_alberta_sheriffs_assault
40 brics - rubles - petrodollar - gold - sanctions 64 40_brics_rubles_petrodollar_gold
41 trudeau - ualberta - interprovincial - immigrants - mansion 63 41_trudeau_ualberta_interprovincial_immigrants
42 vaxcentres - tripledemic - bivalent - injected - infants 61 42_vaxcentres_tripledemic_bivalent_injected
43 yanukovych - crimea - luhansk - overthrow - invaded 60 43_yanukovych_crimea_luhansk_overthrow
44 facemasks - epidemiologist - scientifically - exhaled - ineffective 58 44_facemasks_epidemiologist_scientifically_exhaled
45 sdgs - agenda - 2030 - totalitarian - corporations 55 45_sdgs_agenda_2030_totalitarian
46 duckduckgo - zuckerberg - censorship - metager - truthcoin 53 46_duckduckgo_zuckerberg_censorship_metager
47 lanka - colombo - gunawardena - uprising - president 52 47_lanka_colombo_gunawardena_uprising
48 iranians - khuzestan - protesters - khomeini - mashhad 52 48_iranians_khuzestan_protesters_khomeini
49 nordstream - sabotaging - explosions - watergate - leaks 52 49_nordstream_sabotaging_explosions_watergate
50 scholz - leipzig - protesting - brandenburg - augustusplatz 49 50_scholz_leipzig_protesting_brandenburg
51 ottawapolice - arrests - protesters - convoy - terrorizing 49 51_ottawapolice_arrests_protesters_convoy
52 shootings - suspects - manhunt - stabbed - tulsa 49 52_shootings_suspects_manhunt_stabbed
53 illegals - texas - juarez - smuggler - border 48 53_illegals_texas_juarez_smuggler
54 nato - finland - sanctions - cavusoglu - herzegovina 47 54_nato_finland_sanctions_cavusoglu
55 antisemite - millionjews - pogroms - zionazis - ashkenazi 46 55_antisemite_millionjews_pogroms_zionazis
56 draghi - sicily - andrea - popolo - immigration 46 56_draghi_sicily_andrea_popolo
57 wikileaks - extradited - julian - belmarsh - torture 45 57_wikileaks_extradited_julian_belmarsh
58 bangladesh - protesters - ramaphosa - gouging - blockades 44 58_bangladesh_protesters_ramaphosa_gouging
59 toxins - bicarbonate - aspartame - healthy - sodas 43 59_toxins_bicarbonate_aspartame_healthy
60 netanyahu - israelis - mossad - protestors - reforms 43 60_netanyahu_israelis_mossad_protestors
61 kremlin - beijing - chunying - khrushchev - wars 43 61_kremlin_beijing_chunying_khrushchev
62 sapiens - yuval - gevolution - harrari - evil 42 62_sapiens_yuval_gevolution_harrari
63 schoolboard - hwdsb - sexualization - grindr - phuck 42 63_schoolboard_hwdsb_sexualization_grindr
64 euthanasia - canadan - legalising - assisted - stairlift 42 64_euthanasia_canadan_legalising_assisted
65 ivermectin - remdesivir - hydroxychloroquine - antiviral - acetylcysteine 41 65_ivermectin_remdesivir_hydroxychloroquine_antiviral
66 kauai - mauna - fires - lahaina - helpmauirise 40 66_kauai_mauna_fires_lahaina
67 westjet - unvaccinated - moldova - arrivecan - destinations 40 67_westjet_unvaccinated_moldova_arrivecan
68 mealworms - insectivorous - larva - scorpions - parasitic 39 68_mealworms_insectivorous_larva_scorpions
69 trump - indicted - giuliani - presiding - subpoenas 39 69_trump_indicted_giuliani_presiding
70 catalonia - spaniards - partido - sanchez - extremists 39 70_catalonia_spaniards_partido_sanchez
71 chemtrails - rainmaker - clouds - artificially - spray 39 71_chemtrails_rainmaker_clouds_artificially
72 convoys - cananda - weaponized - idiots - segregationists 38 72_convoys_cananda_weaponized_idiots
73 mutations - injected - gardasil - gmos - plasmid 38 73_mutations_injected_gardasil_gmos
74 alarmists - climatologist - cnn - baloney - temperature 38 74_alarmists_climatologist_cnn_baloney
75 halfblackconservative - afrocentrism - multiracial - whiteness - wakanda 37 75_halfblackconservative_afrocentrism_multiracial_whiteness
76 homophobes - drag - queens - dallas - naked 37 76_homophobes_drag_queens_dallas
77 rescuers - sanlıurfa - afghanistan - aftershocks - malatya 36 77_rescuers_sanlıurfa_afghanistan_aftershocks
78 wildfires - kamloops - yellowknife - northwest - arsonists 36 78_wildfires_kamloops_yellowknife_northwest
79 doctors - c19vax - died - virologist - saskatoon 35 79_doctors_c19vax_died_virologist
80 soros - clinton - funders - donated - haitians 34 80_soros_clinton_funders_donated
81 niamey - gabon - macron - peacekeepers - overthrown 34 81_niamey_gabon_macron_peacekeepers
82 5g - gigahertz - antennasearch - radiation - m2 33 82_5g_gigahertz_antennasearch_radiation
83 londoners - ulez - emissions - vandalised - starmer 32 83_londoners_ulez_emissions_vandalised
84 neil - oliver - fools - raynergate - unaccountable 32 84_neil_oliver_fools_raynergate
85 unvaccinated - mandated - rehired - exemptions - pentagon 32 85_unvaccinated_mandated_rehired_exemptions
86 globalists - reignitefreedom - parliament - dictatorship - democratically 32 86_globalists_reignitefreedom_parliament_dictatorship
87 ottawa - trucker - convoys - protesting - interstate 32 87_ottawa_trucker_convoys_protesting
88 transgender - idaho - minors - lawmakers - prohibit 32 88_transgender_idaho_minors_lawmakers
89 trudeau - chinas - ctvnews - espionage - interfered 31 89_trudeau_chinas_ctvnews_espionage
90 censorship - senatorwhite - streaming - mccallum - carignan 31 90_censorship_senatorwhite_streaming_mccallum
91 migrants - assaulting - racists - dublin - algerian 31 91_migrants_assaulting_racists_dublin
92 queen - britain - reign - buckingham - mourning 30 92_queen_britain_reign_buckingham
93 kennedy - snowden - candidacy - hitler - assassinated 30 93_kennedy_snowden_candidacy_hitler
94 pride - lgbtqxyz - parades - flag - muslims 29 94_pride_lgbtqxyz_parades_flag
95 alberta - blockade - truckers - protesters - roundabout 29 95_alberta_blockade_truckers_protesters
96 blackrock - vanguard - firms - shareholders - omnivision 29 96_blackrock_vanguard_firms_shareholders
97 homeschooled - indoctrinating - curriculum - radicalized - superintendent 29 97_homeschooled_indoctrinating_curriculum_radicalized
98 freeland - alberta - fascists - stoltenberg - chrystia 29 98_freeland_alberta_fascists_stoltenberg
99 flouridation - brainwashes - iodine - pineal - neurotoxicity 29 99_flouridation_brainwashes_iodine_pineal
100 aids - poxvax - virologist - immunogens - undetectable 28 100_aids_poxvax_virologist_immunogens
101 disneywe - mickey - wokeness - cartoons - mommy 28 101_disneywe_mickey_wokeness_cartoons
102 satanists - persecuted - abomination - ms13 - slaughtered 28 102_satanists_persecuted_abomination_ms13
103 donetsk - missiles - howitzers - surovtsevka - uav 27 103_donetsk_missiles_howitzers_surovtsevka
104 argentinians - maduro - fernandez - alberto - libertarian 27 104_argentinians_maduro_fernandez_alberto
105 maskless - walkout - superintendent - mandates - illinois 27 105_maskless_walkout_superintendent_mandates
106 telegram - messages - privately - scammers - protonmail 27 106_telegram_messages_privately_scammers
107 djokovic - wimbledon - unvaccinated - novax - quarterfinals 26 107_djokovic_wimbledon_unvaccinated_novax
108 monkeypox - adenovirus - spreading - nsw - panicking 26 108_monkeypox_adenovirus_spreading_nsw
109 pharmaceutical - cure - paxil - lomotil - zyrtec 26 109_pharmaceutical_cure_paxil_lomotil
110 chemtrail - sprayed - arsenic - spain - ppm 25 110_chemtrail_sprayed_arsenic_spain
111 derailments - michigan - hazmat - watervliet - huron 25 111_derailments_michigan_hazmat_watervliet
112 belgrade - europride - albanians - parade - peacekeepers 25 112_belgrade_europride_albanians_parade
113 rothschild - richest - dynasty - trillion - kingpins 24 113_rothschild_richest_dynasty_trillion
114 greenspan - monetary - oligarchy - warburgs - legalized 24 114_greenspan_monetary_oligarchy_warburgs
115 co2 - greenpeace - pollutants - photosynthesis - 350ppm 24 115_co2_greenpeace_pollutants_photosynthesis
116 peru - callao - protesters - riobamba - machu 23 116_peru_callao_protesters_riobamba
117 doctors - epidemiologist - mccullough - whistleblowing - embalmer 23 117_doctors_epidemiologist_mccullough_whistleblowing
118 meat - cannibalism - soylent - hamburger - cells 23 118_meat_cannibalism_soylent_hamburger
119 mosquitoes - gates - genetically - millions - oxitec 23 119_mosquitoes_gates_genetically_millions
120 remdesivir - midazolam - pseudomedicine - deadly - hospitalised 23 120_remdesivir_midazolam_pseudomedicine_deadly
121 kanye - deplatformed - jew - shapiro - podcast 23 121_kanye_deplatformed_jew_shapiro
122 zealand - jacinda - vaxxers - haka - tyrannical 22 122_zealand_jacinda_vaxxers_haka
123 hungary - brussels - viktor - governors - corruption 22 123_hungary_brussels_viktor_governors
124 adrenochrome - pedophilia - deepstate - heroin - 100k 22 124_adrenochrome_pedophilia_deepstate_heroin
125 missiles - kremlin - zelenskyy - attacks - lviv 22 125_missiles_kremlin_zelenskyy_attacks
126 globalwalkout - steps - reignitefreedom - rwf - unsubscribe 22 126_globalwalkout_steps_reignitefreedom_rwf
127 jury - proceedings - livestream - accomplices - nuremberg 21 127_jury_proceedings_livestream_accomplices
128 chernobyl - zaporizhzhia - reactors - bombings - nagasaki 21 128_chernobyl_zaporizhzhia_reactors_bombings
129 co2 - climate - pseudoscientists - geologist - csiro 21 129_co2_climate_pseudoscientists_geologist
130 vaccinations - sids - died - meningitis - cyberbullied 21 130_vaccinations_sids_died_meningitis
131 imran - nawaz - rawalpindi - overthrown - imprisonment 21 131_imran_nawaz_rawalpindi_overthrown
132 severodonetsk - prigozhin - paramilitary - warnews - petersburg 21 132_severodonetsk_prigozhin_paramilitary_warnews
133 chatgpt - pichai - faked - biased - websites 21 133_chatgpt_pichai_faked_biased
134 athens - protesters - campuses - enforcement - clashes 21 134_athens_protesters_campuses_enforcement
135 baalenciaga - kardashian - blames - adidas - pedophilic 21 135_baalenciaga_kardashian_blames_adidas
136 haiti - riots - overthrow - inflation - vetoes 20 136_haiti_riots_overthrow_inflation
137 erdogan - kremlin - volodymyr - blinken - antalya 20 137_erdogan_kremlin_volodymyr_blinken
138 monkeypox - vaccinated - imvamune - poxface - jab 20 138_monkeypox_vaccinated_imvamune_poxface
139 pfizer - effects - pharmacist - pages - suppressed 20 139_pfizer_effects_pharmacist_pages
140 gofundme - donated - givesendgo - chargeback - trucker 20 140_gofundme_donated_givesendgo_chargeback

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
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support