MARTINI_enrich_BERTopic_greatreject

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_greatreject")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 121
  • Number of training documents: 16234
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 lockdown - unvaccinated - thefreedomshop - propaganda - ukraine 20 -1_lockdown_unvaccinated_thefreedomshop_propaganda
0 mariupol - severodonetsk - luhansk - russians - batallion 9825 0_mariupol_severodonetsk_luhansk_russians
1 brainwashing - chomsky - manipulated - influence - audience 219 1_brainwashing_chomsky_manipulated_influence
2 ivermectine - hydroxychloroquine - remdesivir - niclosamide - ritonavir 175 2_ivermectine_hydroxychloroquine_remdesivir_niclosamide
3 genoa - trento - protesters - blockade - greenpass 161 3_genoa_trento_protesters_blockade
4 vaccinations - eeoc - mandatory - exemptions - defendingtherepublic 158 4_vaccinations_eeoc_mandatory_exemptions
5 pfizer - vioxx - fentanyl - kickbacks - lawsuits 127 5_pfizer_vioxx_fentanyl_kickbacks
6 passport - covidtests - thecommonsproject - walmart - qr 126 6_passport_covidtests_thecommonsproject_walmart
7 ecb - monetary - bitcoin - euros - keepcashalive 115 7_ecb_monetary_bitcoin_euros
8 fires - explosion - flood - evacuated - reportedly 112 8_fires_explosion_flood_evacuated
9 ballots - biden - lindell - georgia - smartmatic 111 9_ballots_biden_lindell_georgia
10 nuremberg - buttons - magnet - bumpnu - 8x6cm 111 10_nuremberg_buttons_magnet_bumpnu
11 paedophiles - sexualitat - puberty - indoctrination - unesco 108 11_paedophiles_sexualitat_puberty_indoctrination
12 nanoparticles - magnetised - adjuvant - superparamagnetic - mri 106 12_nanoparticles_magnetised_adjuvant_superparamagnetic
13 energie - renewables - petrol - prijsplafond - germany 101 13_energie_renewables_petrol_prijsplafond
14 pilots - airliners - lufthansa - flying - airport 92 14_pilots_airliners_lufthansa_flying
15 passsanitaire - bastille - mandatory - hospitals - protesters 92 15_passsanitaire_bastille_mandatory_hospitals
16 vaxxers - unvaccinated - brainwashed - uninjected - ostracize 88 16_vaxxers_unvaccinated_brainwashed_uninjected
17 souls - oneness - consciousness - everything - frequencies 88 17_souls_oneness_consciousness_everything
18 dutch - rijksoverheid - rietbergen - bevoegdheden - frauduleuze 87 18_dutch_rijksoverheid_rietbergen_bevoegdheden
19 5g - electrosmog - radiofrequency - coronahoax - towers 83 19_5g_electrosmog_radiofrequency_coronahoax
20 unvaxed - deaths - 2021 - dose - hospitalize 80 20_unvaxed_deaths_2021_dose
21 worldwidedemonstration - protesters - marches - london - reopening 79 21_worldwidedemonstration_protesters_marches_london
22 davos - globalism - mckibben - sarkozy - serfs 78 22_davos_globalism_mckibben_sarkozy
23 vaccination - jab - consent - headteacher - teens 77 23_vaccination_jab_consent_headteacher
24 vaccinated - kontrollgruppenteilnemer - qr - consent - antworten 76 24_vaccinated_kontrollgruppenteilnemer_qr_consent
25 truckersforfreedom - truckgender - ottawa - honk - towed 75 25_truckersforfreedom_truckgender_ottawa_honk
26 vaers - pfizer - 2021 - strokes - miscarriages 74 26_vaers_pfizer_2021_strokes
27 pycnogenol - quercetin - glutathione - antioxidants - supplements 74 27_pycnogenol_quercetin_glutathione_antioxidants
28 electricity - edison - orgone - antigravity - alternator 74 28_electricity_edison_orgone_antigravity
29 chemtrail - spraying - raytheon - clouds - aircraft 73 29_chemtrail_spraying_raytheon_clouds
30 alarmists - noaa - pseudowissenschaft - lindzen - temperatures 69 30_alarmists_noaa_pseudowissenschaft_lindzen
31 nypd - protesters - antimandate - albany - firefighters 69 31_nypd_protesters_antimandate_albany
32 reignitedemocracyaustralia - victoriapolice - tasmania - protesters - sedition 67 32_reignitedemocracyaustralia_victoriapolice_tasmania_protesters
33 polizisten - antifaschisten - verfassungsschutz - gewalttatige - dusseldorf 65 33_polizisten_antifaschisten_verfassungsschutz_gewalttatige
34 corona - reinerfuellmichenglish - wolfgang - falsification - witnesses 63 34_corona_reinerfuellmichenglish_wolfgang_falsification
35 giletsjaunes - rioters - parisians - marseille - molotov 61 35_giletsjaunes_rioters_parisians_marseille
36 donaldjtrump - melania - msnbc - statements - 45th 61 36_donaldjtrump_melania_msnbc_statements
37 livestream - sitzung - reinerfuellmichenglish - odysee - impfschaden 57 37_livestream_sitzung_reinerfuellmichenglish_odysee
38 greta - thefreedomshop - normies - bannon - skinhead 55 38_greta_thefreedomshop_normies_bannon
39 bankingsystem - bankrupt - hyperinflation - goldman - crashed 54 39_bankingsystem_bankrupt_hyperinflation_goldman
40 eurosceptic - polexit - hungary - barnier - morawiecki 54 40_eurosceptic_polexit_hungary_barnier
41 diesels - tesla - 350kw - charging - gallons 53 41_diesels_tesla_350kw_charging
42 musk - dorsey - shareholders - trump - takeover 52 42_musk_dorsey_shareholders_trump
43 overthrow - thermite - pentagon - guatemala - 1959 52 43_overthrow_thermite_pentagon_guatemala
44 curvature - earthers - globe - heliocentric - altitude 51 44_curvature_earthers_globe_heliocentric
45 footballer - died - cardiac - collapses - cristiano 51 45_footballer_died_cardiac_collapses
46 spikeproteins - antigen - mrna - cjd - adenovirus 51 46_spikeproteins_antigen_mrna_cjd
47 pandemics - marburg - safetyism - soligenix - highjacked 50 47_pandemics_marburg_safetyism_soligenix
48 antivaxxers - deathvax - unvaccinated - thevigilantfox - unmasked 50 48_antivaxxers_deathvax_unvaccinated_thevigilantfox
49 bolsonaro - guaruja - janeiro - venezuelan - guyana 50 49_bolsonaro_guaruja_janeiro_venezuelan
50 verfassungsbeschwerde - grundfreiheiten - gesundheitsvorschriften - mitgliedstaaten - pandemievertrag 50 50_verfassungsbeschwerde_grundfreiheiten_gesundheitsvorschriften_mitgliedstaaten
51 wuhan - lockdown - shenzhen - foxconn - zhangjiajie 50 51_wuhan_lockdown_shenzhen_foxconn
52 telegram - windscribe - proxy - apk - blocked 49 52_telegram_windscribe_proxy_apk
53 trudeau - blockades - ceausescu - authoritarian - regan 49 53_trudeau_blockades_ceausescu_authoritarian
54 rfk - tucker - whitehouse - selassie - jumplinks 47 54_rfk_tucker_whitehouse_selassie
55 putin - vladimir - yelizarova - gulags - lvmh 47 55_putin_vladimir_yelizarova_gulags
56 virologists - debunked - wuhan - kontrollexperimente - postmortaal 46 56_virologists_debunked_wuhan_kontrollexperimente
57 pcr - ncov - tested - asymptomatic - serological 46 57_pcr_ncov_tested_asymptomatic
58 gates - melinda - billion - unicef - philanthropist 45 58_gates_melinda_billion_unicef
59 wirfurheinrich - weiter - staatsanwaltschaft - bochum - patienten 44 59_wirfurheinrich_weiter_staatsanwaltschaft_bochum
60 faggot - bateman - moulsecoomb - trumptard - demonised 44 60_faggot_bateman_moulsecoomb_trumptard
61 rothschild - khazarian - warmongers - satanists - genocide 43 61_rothschild_khazarian_warmongers_satanists
62 chinafication - blacklisted - wechat - paybyface - biometric 43 62_chinafication_blacklisted_wechat_paybyface
63 israelis - vaccinated - aviv - incitement - hospitalizations 42 63_israelis_vaccinated_aviv_incitement
64 nordstream - gazprombank - sanctions - pipelins - 2022 42 64_nordstream_gazprombank_sanctions_pipelins
65 livefree - awakened - lsd - demons - drumpf 42 65_livefree_awakened_lsd_demons
66 messages - subscribe - spammers - email - unsolicited 41 66_messages_subscribe_spammers_email
67 australians - nsw - turnbull - lockdown - unvaccinated 40 67_australians_nsw_turnbull_lockdown
68 shortages - shtf - perishables - supermarkets - stocked 39 68_shortages_shtf_perishables_supermarkets
69 maskless - homeschooling - maddie - superintendent - mpsd 39 69_maskless_homeschooling_maddie_superintendent
70 maskeineffektivitet - christmask - n95s - oxygen - microfibres 38 70_maskeineffektivitet_christmask_n95s_oxygen
71 biden - trumpjr - dotard - libtards - gitmo 38 71_biden_trumpjr_dotard_libtards
72 additives - glyphosate - aspartame - toxic - pepsico 36 72_additives_glyphosate_aspartame_toxic
73 derailment - michigan - crashed - tankwagons - spills 36 73_derailment_michigan_crashed_tankwagons
74 duckduckgo - gloogle - yandex - websites - censorship 36 74_duckduckgo_gloogle_yandex_websites
75 miscarriages - unborn - obstetrician - trimester - contraceptive 35 75_miscarriages_unborn_obstetrician_trimester
76 constitutions - mandamus - incorporated - crown - trustee 35 76_constitutions_mandamus_incorporated_crown
77 fauci - coronaviruses - ecohealthalliance - laboratory - cloned 35 77_fauci_coronaviruses_ecohealthalliance_laboratory
78 cyborgs - neuralink - intelligence - metaverse - chatbots 32 78_cyborgs_neuralink_intelligence_metaverse
79 zelenskyy - volodymyr - nawaz - mironyuk - clownworld 32 79_zelenskyy_volodymyr_nawaz_mironyuk
80 hamas - israelis - terrorists - zionists - antisemitism 30 80_hamas_israelis_terrorists_zionists
81 giantology - archaeologists - smithsonian - discovered - skeletons 30 81_giantology_archaeologists_smithsonian_discovered
82 soros - shevardnadze - antifa - whofundswho - spitzenpolitik 30 82_soros_shevardnadze_antifa_whofundswho
83 myocarditis - covax - pericardium - colleenhubernmd - biologic 30 83_myocarditis_covax_pericardium_colleenhubernmd
84 globalist - stopworldcontrol - mundo - unidas - desinformacao 30 84_globalist_stopworldcontrol_mundo_unidas
85 greenland - seaice - polar - alarmists - interglacial 29 85_greenland_seaice_polar_alarmists
86 biowaffenlabore - ukraine - usaid - anthrax - pentagon 29 86_biowaffenlabore_ukraine_usaid_anthrax
87 vaxxine - queensland - kerryn - waleeds - nurses 29 87_vaxxine_queensland_kerryn_waleeds
88 pandemic - publishes - orwellian - bombshell - impossibilities 29 88_pandemic_publishes_orwellian_bombshell
89 died - pfizer - coroners - thrombosis - injection 28 89_died_pfizer_coroners_thrombosis
90 kybalion - healing - karmic - cannabis - shamanic 28 90_kybalion_healing_karmic_cannabis
91 modrna - lipofectin - transgene - dsdna - adenoviruses 27 91_modrna_lipofectin_transgene_dsdna
92 maui - jumpsmartmaui - lahaina - firebombing - mizuho 27 92_maui_jumpsmartmaui_lahaina_firebombing
93 pyramids - teotihuacan - ruines - atlantis - civilizations 27 93_pyramids_teotihuacan_ruines_atlantis
94 shitcoins - cryptocurrencies - bitmining - satoshi - holochain 26 94_shitcoins_cryptocurrencies_bitmining_satoshi
95 extraterrestrials - sightings - skinwalkers - roswell - scariest 25 95_extraterrestrials_sightings_skinwalkers_roswell
96 antibodies - superspreaders - naturally - presymptomatic - harvard 25 96_antibodies_superspreaders_naturally_presymptomatic
97 fatalities - epidemiological - c19 - euthanised - finland 25 97_fatalities_epidemiological_c19_euthanised
98 brics - yuan - putin - gold - sanctions 24 98_brics_yuan_putin_gold
99 djokovic - wimbledon - melbourne - unquaccinated - visa 24 99_djokovic_wimbledon_melbourne_unquaccinated
100 zuckerberg - facezuckeshiten - whatsapp - fbi - deleted 24 100_zuckerberg_facezuckeshiten_whatsapp_fbi
101 blackrock - nationalizing - shareholders - trillion - oligopoly 24 101_blackrock_nationalizing_shareholders_trillion
102 papacy - bishops - benedict - vigano - heretic 24 102_papacy_bishops_benedict_vigano
103 mrna - hydroxychloroquine - malone - misinformation - inventors 24 103_mrna_hydroxychloroquine_malone_misinformation
104 unvaccinated - safeblood - transfusions - antibodies - tainted 24 104_unvaccinated_safeblood_transfusions_antibodies
105 freemasonic - kommunismus - weltkrieg - documentaries - weisskopf 24 105_freemasonic_kommunismus_weltkrieg_documentaries
106 texas - veto - legislators - passports - overmedicalizing 23 106_texas_veto_legislators_passports
107 omicron - deltavariant - debunked - panicking - fuckin 22 107_omicron_deltavariant_debunked_panicking
108 nonvaccinated - viruses - immunodominant - mutate - epitopes 22 108_nonvaccinated_viruses_immunodominant_mutate
109 microchipping - biodigital - implantable - neuralink - iob 22 109_microchipping_biodigital_implantable_neuralink
110 amsterdam - willem - protestors - femke - democratie 22 110_amsterdam_willem_protestors_femke
111 inoculations - cv19 - compensation - victims - gsk 22 111_inoculations_cv19_compensation_victims
112 wikileaks - julian - podesta - extrajudicially - assassinate 21 112_wikileaks_julian_podesta_extrajudicially
113 jintao - dictator - commies - xi - uyghurs 21 113_jintao_dictator_commies_xi
114 moonlanding - craters - telescopes - footage - faked 21 114_moonlanding_craters_telescopes_footage
115 londoners - motorists - ultra - parking - camera 21 115_londoners_motorists_ultra_parking
116 mealworms - entomophagic - meatpacker - beetle - larval 20 116_mealworms_entomophagic_meatpacker_beetle
117 impeachment - insurrection - traitors - federalized - brigades 20 117_impeachment_insurrection_traitors_federalized
118 lanka - rajapakse - haiti - gotabaya - insurrection 20 118_lanka_rajapakse_haiti_gotabaya
119 digital - passport - fingerprint - eidas - wallets 20 119_digital_passport_fingerprint_eidas

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