AngelPanizo's picture
Add BERTopic model
68f3058 verified
metadata
tags:
  - bertopic
library_name: bertopic
pipeline_tag: text-classification

MARTINI_enrich_BERTopic_LauraAbolichannel

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_LauraAbolichannel")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 132
  • Number of training documents: 19843
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 humanity - hope - become - fear - never 20 -1_humanity_hope_become_fear
0 bolsonaro - favelas - janeiro - salvador - venezuela 11567 0_bolsonaro_favelas_janeiro_salvador
1 trudeau - alberta - convoy - freedoms - protesters 295 1_trudeau_alberta_convoy_freedoms
2 footballer - died - myopericarditis - collapsing - stroke 287 2_footballer_died_myopericarditis_collapsing
3 vaccinated - vaxxers - unquackccinated - jabbed - paxlovid 226 3_vaccinated_vaxxers_unquackccinated_jabbed
4 alarmists - co2 - thunberg - scientifically - greenland 223 4_alarmists_co2_thunberg_scientifically
5 ridiculous - insanity - idiots - soooooo - laugh 197 5_ridiculous_insanity_idiots_soooooo
6 biden - whistleblowers - impeachment - bribery - indicted 189 6_biden_whistleblowers_impeachment_bribery
7 fauci - hiv - coronaviruses - institutes - funded 169 7_fauci_hiv_coronaviruses_institutes
8 migrants - illegals - smuggling - panama - lampedusa 153 8_migrants_illegals_smuggling_panama
9 macron - toulouse - liberte - nouvelles - protests 152 9_macron_toulouse_liberte_nouvelles
10 zelensky - volodymyr - kiev - belarus - peskov 146 10_zelensky_volodymyr_kiev_belarus
11 musk - twitter - zuckerberg - takeover - ellison 145 11_musk_twitter_zuckerberg_takeover
12 pfizer - spikevax - fda - approved - waiver 139 12_pfizer_spikevax_fda_approved
13 nasa - ufo - satellites - spacecraft - moon 132 13_nasa_ufo_satellites_spacecraft
14 bannon - indicted - prosecutors - presidential - christie 127 14_bannon_indicted_prosecutors_presidential
15 floods - torrential - downpours - landfall - ravenna 127 15_floods_torrential_downpours_landfall
16 scotus - ballots - lindell - senators - maricopa 122 16_scotus_ballots_lindell_senators
17 russia - putin - vladimir - globalist - sergei 121 17_russia_putin_vladimir_globalist
18 tree - jellyfish - diameter - elephants - oaxaca 116 18_tree_jellyfish_diameter_elephants
19 bioweapons - ukraine - pentagon - laboratories - ebola 115 19_bioweapons_ukraine_pentagon_laboratories
20 goodnight - farewell - welcome - appreciated - together 107 20_goodnight_farewell_welcome_appreciated
21 epstein - billionaire - victims - convicted - prostitution 107 21_epstein_billionaire_victims_convicted
22 cbdc - cashless - worldcoin - monetary - technocrats 99 22_cbdc_cashless_worldcoin_monetary
23 mariupol - donetsk - militants - azovites - battalion 97 23_mariupol_donetsk_militants_azovites
24 transgenderism - sexes - lupron - wemen - alyssa 96 24_transgenderism_sexes_lupron_wemen
25 fires - exploded - refineries - pemex - ohio 95 25_fires_exploded_refineries_pemex
26 chemtrails - clouds - spraying - stratospheric - weaponised 93 26_chemtrails_clouds_spraying_stratospheric
27 derailments - ohio - hazardous - chemicals - spilled 90 27_derailments_ohio_hazardous_chemicals
28 biden - barack - jill - sotu - grandpop 90 28_biden_barack_jill_sotu
29 propaganda - msm - whistlesblower - reporters - rosanne 88 29_propaganda_msm_whistlesblower_reporters
30 clots - defibrillators - strokes - caused - ʜᴇᴀʟᴛʜʏ 77 30_clots_defibrillators_strokes_caused
31 boris - downing - partygate - modi - scotland 75 31_boris_downing_partygate_modi
32 china - lockdowns - shenzhen - foxconn - heilongjiang 72 32_china_lockdowns_shenzhen_foxconn
33 bailout - bancorp - suisse - svb - plummeted 72 33_bailout_bancorp_suisse_svb
34 tesla - electricity - gasoline - westinghouse - rechargeable 70 34_tesla_electricity_gasoline_westinghouse
35 unvaccinated - omicron - austria - lockdown - mandatory 69 35_unvaccinated_omicron_austria_lockdown
36 ftx - kraken - cryptocurrency - ponzi - extradited 68 36_ftx_kraken_cryptocurrency_ponzi
37 ivermectine - hydroxicloroquine - remdesivir - chemotherapy - multidrug 68 37_ivermectine_hydroxicloroquine_remdesivir_chemotherapy
38 donetsk - kharkov - missiles - crimean - tochka 67 38_donetsk_kharkov_missiles_crimean
39 reignitedemocracyaustralia - canberra - protesters - tyranny - legalised 66 39_reignitedemocracyaustralia_canberra_protesters_tyranny
40 desantis - newsflorida - governor - repealing - mandates 66 40_desantis_newsflorida_governor_repealing
41 glutathione - detoxifier - shilajit - sulforaphane - chlorella 63 41_glutathione_detoxifier_shilajit_sulforaphane
42 boerburgerbeweging - netherlands - monsanto - expropriations - staghouwer 62 42_boerburgerbeweging_netherlands_monsanto_expropriations
43 spratly - taipei - pelosi - fujian - junli 61 43_spratly_taipei_pelosi_fujian
44 mealworms - insectivorous - parasites - grasshoppers - eat 59 44_mealworms_insectivorous_parasites_grasshoppers
45 metaverse - transhumanists - satan - eternity - truthunedited 59 45_metaverse_transhumanists_satan_eternity
46 nordstream - sabotaged - terrorist - blasts - pipe 58 46_nordstream_sabotaged_terrorist_blasts
47 abortionists - scotus - demoncrats - overturning - legalizing 57 47_abortionists_scotus_demoncrats_overturning
48 kennedy - sirhan - snowden - assassinated - democrats 57 48_kennedy_sirhan_snowden_assassinated
49 zuckerberg - suing - metaverse - snapchat - defamatory 57 49_zuckerberg_suing_metaverse_snapchat
50 life - souls - purpose - meaningful - knowing 56 50_life_souls_purpose_meaningful
51 pedophilia - atrocities - satanic - qanon - tebow 55 51_pedophilia_atrocities_satanic_qanon
52 vaers - pfizer - deaths - 49 - shots 54 52_vaers_pfizer_deaths_49
53 40bn - zelensky - munitions - aid - amount 52 53_40bn_zelensky_munitions_aid
54 mandates - injunction - unvaccinated - judges - texas 52 54_mandates_injunction_unvaccinated_judges
55 15minute - clampdown - footprint - neighbourhoods - 20mph 51 55_15minute_clampdown_footprint_neighbourhoods
56 robot - holograms - samsung - smartwatch - innovations 50 56_robot_holograms_samsung_smartwatch
57 ncov - pcr - parainfluenza - cytomegalovirus - swabs 50 57_ncov_pcr_parainfluenza_cytomegalovirus
58 agenda - unsustainable - plandemic - totalitarian - 2030 49 58_agenda_unsustainable_plandemic_totalitarian
59 awakening - humanity - transcending - ignorance - metamosphosis 49 59_awakening_humanity_transcending_ignorance
60 queen - coronations - buckingham - bbc - meghan 49 60_queen_coronations_buckingham_bbc
61 gaza - ashkelon - airstrikes - falouja - projectile 49 61_gaza_ashkelon_airstrikes_falouja
62 gazprom - sanctions - crude - euros - exporters 48 62_gazprom_sanctions_crude_euros
63 pilots - flightaware - airbus - qantas - gatwick 47 63_pilots_flightaware_airbus_qantas
64 vaccines - dna - injected - interferon - stillbirths 47 64_vaccines_dna_injected_interferon
65 facemasks - skeptics - exhaled - asbestos - meningitidis 45 65_facemasks_skeptics_exhaled_asbestos
66 burkina - nigerien - cameroon - gabonese - coups 44 66_burkina_nigerien_cameroon_gabonese
67 freedom - patriot - resisting - righteousness - evildoers 43 67_freedom_patriot_resisting_righteousness
68 earthquake - aftershocks - magnitude - seismologist - malatya 41 68_earthquake_aftershocks_magnitude_seismologist
69 taliban - afghans - kandahar - amrullah - carbines 41 69_taliban_afghans_kandahar_amrullah
70 soros - funded - megalomaniacs - antisemitic - prosecutors 41 70_soros_funded_megalomaniacs_antisemitic
71 petrodollar - rubles - dollarization - sanctions - currencies 41 71_petrodollar_rubles_dollarization_sanctions
72 forgive - hindsight - unworthiness - revengeful - traumatic 40 72_forgive_hindsight_unworthiness_revengeful
73 doctors - pharmaceutical - underreported - hippocratic - fraudulent 39 73_doctors_pharmaceutical_underreported_hippocratic
74 suez - tankers - maersk - blockage - crane 39 74_suez_tankers_maersk_blockage
75 vaccinated - israel - omicron - hospitalizations - ourworldindata 38 75_vaccinated_israel_omicron_hospitalizations
76 wisdom - awakening - selfhood - ignorance - falsehoods 38 76_wisdom_awakening_selfhood_ignorance
77 comey - danchenko - dossier - counterintelligence - brennan 38 77_comey_danchenko_dossier_counterintelligence
78 hawaiʻi - lahaina - wildfires - governor - hurricane 37 78_hawaiʻi_lahaina_wildfires_governor
79 impeach - mccarthy - representatives - removed - knesset 37 79_impeach_mccarthy_representatives_removed
80 wildfires - blazes - chile - kindling - yellowknife 37 80_wildfires_blazes_chile_kindling
81 plandemic - flurona - cholera - brainwash - hypochondriacs 37 81_plandemic_flurona_cholera_brainwash
82 chatgpt - superintelligence - xai - democratize - pichai 36 82_chatgpt_superintelligence_xai_democratize
83 vaccinologist - dr - malhotra - mrna - robert 36 83_vaccinologist_dr_malhotra_mrna
84 handguns - shootings - australians - felons - violence 36 84_handguns_shootings_australians_felons
85 satanists - demonic - hellspawned - lucifer - samhain 36 85_satanists_demonic_hellspawned_lucifer
86 deaths - 2023 - prepandemic - england - 40 35 86_deaths_2023_prepandemic_england
87 kosovo - pristina - mitrovica - serb - aleksandar 34 87_kosovo_pristina_mitrovica_serb
88 prigozhin - petersburg - insurgency - warprisoners - yevkurov 34 88_prigozhin_petersburg_insurgency_warprisoners
89 volcanos - popocatepetl - erupting - eyjafjallajokull - sheveluch 34 89_volcanos_popocatepetl_erupting_eyjafjallajokull
90 fbi - declassified - melania - bush - hannity 33 90_fbi_declassified_melania_bush
91 resilience - madness - forever - remember - overwhelm 33 91_resilience_madness_forever_remember
92 pontiff - vigano - benedict - denounced - inoculated 33 92_pontiff_vigano_benedict_denounced
93 bulgaria - zelenskiy - bundestag - protesters - slava 33 93_bulgaria_zelenskiy_bundestag_protesters
94 vaccination - referendum - tyranny - passports - mep 32 94_vaccination_referendum_tyranny_passports
95 awakening - evil - miracles - existentially - survive 32 95_awakening_evil_miracles_existentially
96 imran - pakistan - khomeini - islamists - overthrown 32 96_imran_pakistan_khomeini_islamists
97 zealand - vaccinated - compulsory - fluoridation - whistleblower 32 97_zealand_vaccinated_compulsory_fluoridation
98 vaccines - nanotubes - graphe - implantable - 5g 31 98_vaccines_nanotubes_graphe_implantable
99 wikileaks - extradition - jailed - julian - belmarsh 31 99_wikileaks_extradition_jailed_julian
100 melanoma - oncologists - oncogenic - vaccineshttp - mirna 30 100_melanoma_oncologists_oncogenic_vaccineshttp
101 catalonia - spaniards - partido - sanchez - extremists 29 101_catalonia_spaniards_partido_sanchez
102 pandemics - volksgezondheid - sovereignty - monopoliemacht - mondiale 29 102_pandemics_volksgezondheid_sovereignty_monopoliemacht
103 missiles - launched - yonhap - kim - hokkaido 29 103_missiles_launched_yonhap_kim
104 djokovic - wimbledon - champion - vaccinated - quarterfinals 28 104_djokovic_wimbledon_champion_vaccinated
105 vaccinated - hospitalisations - 2021 - quadruple - ukhsa 28 105_vaccinated_hospitalisations_2021_quadruple
106 gaza - casualties - airstrikes - besieged - rafah 28 106_gaza_casualties_airstrikes_besieged
107 morning - hi - hopefully - sorry - messages 28 107_morning_hi_hopefully_sorry
108 worldcouncilforhealth - wch - tedxwhitechapel - panelists - pranic 28 108_worldcouncilforhealth_wch_tedxwhitechapel_panelists
109 euromaidan - yanukovich - luhansk - overthrew - massacres 27 109_euromaidan_yanukovich_luhansk_overthrew
110 nazis - euromaidan - kubijovych - nevzlin - battalions 27 110_nazis_euromaidan_kubijovych_nevzlin
111 pedophilia - homeschooling - schoolchildren - indoctrinate - classroom 26 111_pedophilia_homeschooling_schoolchildren_indoctrinate
112 ramjet - volocopter - airship - jetpacks - horsepower 26 112_ramjet_volocopter_airship_jetpacks
113 frequencies - vibration - cymatics - harmonize - spiritual 25 113_frequencies_vibration_cymatics_harmonize
114 debt - trillion - bidenomics - mortgage - defaulted 25 114_debt_trillion_bidenomics_mortgage
115 happiness - blessings - appreciating - banalities - simplest 25 115_happiness_blessings_appreciating_banalities
116 germany - renewable - nuclear - shortages - heaters 24 116_germany_renewable_nuclear_shortages
117 egyptians - pyramids - geoglyphs - nazca - circumnavigators 24 117_egyptians_pyramids_geoglyphs_nazca
118 zelensky - chernivtsi - monastery - persecuted - kirill 24 118_zelensky_chernivtsi_monastery_persecuted
119 friendships - communicating - understood - empathic - heartbreaking 24 119_friendships_communicating_understood_empathic
120 gates - rockefellers - 200billion - philanthropic - bioweapon 24 120_gates_rockefellers_200billion_philanthropic
121 welcome - channel - morning - awareness - inspiring 23 121_welcome_channel_morning_awareness
122 scammers - impersonator - instagram - contacted - unfollow 23 122_scammers_impersonator_instagram_contacted
123 monkeypox - jabbed - homosexuals - jynneos - fearporn 22 123_monkeypox_jabbed_homosexuals_jynneos
124 gaza - hamas - israelis - judeism - massacre 21 124_gaza_hamas_israelis_judeism
125 plandemic - martin - conspirators - dossier - vladimir 21 125_plandemic_martin_conspirators_dossier
126 hydrogenated - diglycerides - aspartame - apeel - preservative 21 126_hydrogenated_diglycerides_aspartame_apeel
127 jury - indictes - nuremberg - accomplices - livestream 21 127_jury_indictes_nuremberg_accomplices
128 warships - yemeni - israel - admiral - tanker 21 128_warships_yemeni_israel_admiral
129 coerce - refusal - mandatory - liability - employers 21 129_coerce_refusal_mandatory_liability
130 omicron - variants - contagious - morons - alphabet 21 130_omicron_variants_contagious_morons

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