sdantonio's picture
Add BERTopic model
1edaab6 verified
metadata
tags:
  - bertopic
library_name: bertopic
pipeline_tag: text-classification

BERTopic_SicilianGorillian2

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("sdantonio/BERTopic_SicilianGorillian2")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 171
  • Number of training documents: 24193
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 siciliangorillian2 - police_frequency - migrants - ukraine - immigrants 10 -1_siciliangorillian2_police_frequency_migrants_ukraine
0 politics - tensions - blocks - migrants - reuters 12046 0_politics_tensions_blocks_migrants
1 shelter - police_frequency - shooter - hampshire - migrants 655 1_shelter_police_frequency_shooter_hampshire
2 dreams - tolerate - awkward - julian - carlson 606 2_dreams_tolerate_awkward_julian
3 greg_price11 - 9mm_smg - hypocrite - realjameswoods - frognscorpion 567 3_greg_price11_9mm_smg_hypocrite_realjameswoods
4 shelter - jumping - migrants - coins - announces 533 4_shelter_jumping_migrants_coins
5 strickland - comedians - shame - unmasked - nowhere 473 5_strickland_comedians_shame_unmasked
6 greg_price11 - alibradleytv - siciliangorillian2 - dc_draino - endwokeness 456 6_greg_price11_alibradleytv_siciliangorillian2_dc_draino
7 theferrymanstoll - thewesternchauvinist2 - siciliangorillian2 - thewesternchauvinist7 - crying 408 7_theferrymanstoll_thewesternchauvinist2_siciliangorillian2_thewesternchauvinist7
8 assaulted - sav_says_ - cbs_herridge - dc_draino - teens 399 8_assaulted_sav_says__cbs_herridge_dc_draino
9 unsolicited - scapegoat - cowards - stars - affairs 297 9_unsolicited_scapegoat_cowards_stars
10 purchased - elections - banks - whites - arrested 291 10_purchased_elections_banks_whites
11 donations - attacks - ukraine - minds - russian 279 11_donations_attacks_ukraine_minds
12 siciliangorillian2 - ian - whiteprivilege - defunded - prohibition 243 12_siciliangorillian2_ian_whiteprivilege_defunded
13 jake_neidert - uncensored - ramble_rants - rejectthegreat1 - dlivebearstream 212 13_jake_neidert_uncensored_ramble_rants_rejectthegreat1
14 silicon - punishment - believing - washington - worthy 181 14_silicon_punishment_believing_washington
15 wars - iwaswithyou - autographs - moabs - assumptions 177 15_wars_iwaswithyou_autographs_moabs
16 peacekeepers - pacifists - transmaxxing - thinks - galloway 161 16_peacekeepers_pacifists_transmaxxing_thinks
17 shelter - overcharged - collapsing - layoffs - citizens 152 17_shelter_overcharged_collapsing_layoffs
18 assaulting - police_frequency - shares - concealed - crossing 143 18_assaulting_police_frequency_shares_concealed
19 butthole - predictiveprogramming - docuseries - eyeballs - inbox 142 19_butthole_predictiveprogramming_docuseries_eyeballs
20 e1bm2oh - dkpd2ls - ftupjfc - fellowships - ezie3pb 142 20_e1bm2oh_dkpd2ls_ftupjfc_fellowships
21 thekevindalton - tuckercarlson - dc_draino - endwokeness - boats 134 21_thekevindalton_tuckercarlson_dc_draino_endwokeness
22 resistornewswire - confinement - bursting - lazers - foreshadowing 129 22_resistornewswire_confinement_bursting_lazers
23 thexreportcard - wlmcalifornia - ferryman4747 - awakenedoutlaw - michael 119 23_thexreportcard_wlmcalifornia_ferryman4747_awakenedoutlaw
24 resistornewswire - hunterhornyfox - revealed - texans - ethics 111 24_resistornewswire_hunterhornyfox_revealed_texans
25 cnnpolitics - minnesota - shelter - contempt - blocks 110 25_cnnpolitics_minnesota_shelter_contempt
26 greg_price11 - decades - whistleblower - coalition - muckraker 108 26_greg_price11_decades_whistleblower_coalition
27 elections - assault - officers - hunter - wristband 101 27_elections_assault_officers_hunter
28 michaelpsenger - eitc_official - narrative_hole - michael - supplies 99 28_michaelpsenger_eitc_official_narrative_hole_michael
29 homeschooling - enforces - trades - clerks - admiring 96 29_homeschooling_enforces_trades_clerks
30 transgender - siciliangorillian2 - tbdailynews - rejects - hormones 95 30_transgender_siciliangorillian2_tbdailynews_rejects
31 minnesota - thefts - washington - artifacts - discharges 92 31_minnesota_thefts_washington_artifacts
32 kanekoathegreat - guinean - migrants - ukraine - county 92 32_kanekoathegreat_guinean_migrants_ukraine
33 toss - swiss - beacon - mexinazi - tables 91 33_toss_swiss_beacon_mexinazi
34 detransitioning - payouts - rejects - reuters - finalizes 91 34_detransitioning_payouts_rejects_reuters
35 umbrellas - forgivable - disputed - liberation - inslee 89 35_umbrellas_forgivable_disputed_liberation
36 thewesternchauvinist2 - resistornewswire - canadafirstofficial - zoomerwaffen08 - robinthehood 87 36_thewesternchauvinist2_resistornewswire_canadafirstofficial_zoomerwaffen08
37 ltchrisolivarez - txdps - brownsville - troopers - crossing 87 37_ltchrisolivarez_txdps_brownsville_troopers
38 realdonaldtrump - wallstreetsilv - ferryman4747 - sgtnewsnetwork - danielturnerptf 82 38_realdonaldtrump_wallstreetsilv_ferryman4747_sgtnewsnetwork
39 thepoliticalpom - breathtaking - tuckercarlson - hypocrite - americafirst 78 39_thepoliticalpom_breathtaking_tuckercarlson_hypocrite
40 highlighted - feeding - offices - actors - shorts 77 40_highlighted_feeding_offices_actors
41 sarahhuckabee - ivermectin - invictachannel - extended - huckabee 76 41_sarahhuckabee_ivermectin_invictachannel_extended
42 firearms - shelter - convicted - announces - downplayed 74 42_firearms_shelter_convicted_announces
43 highlights - appropriation - detected - celebrations - smiling 72 43_highlights_appropriation_detected_celebrations
44 cig_telegram - censoredmen - travis_in_flint - dadspostwins - censored 72 44_cig_telegram_censoredmen_travis_in_flint_dadspostwins
45 resistornewswire - assaults - decades - antidepressants - loans 69 45_resistornewswire_assaults_decades_antidepressants
46 ghosts - suppressed - alzheimers - helen - venues 69 46_ghosts_suppressed_alzheimers_helen
47 crossroads_josh - philadelphians - police_frequency - siciliangorillian2 - rebranding 68 47_crossroads_josh_philadelphians_police_frequency_siciliangorillian2
48 siciliangorillian2 - govsisolak - campaigns - abercrombie - incels 67 48_siciliangorillian2_govsisolak_campaigns_abercrombie
49 swirl - counterparts - heater - migrants - planting 65 49_swirl_counterparts_heater_migrants
50 deployed - southafrica - whistleblowers - cbs_herridge - allegations 63 50_deployed_southafrica_whistleblowers_cbs_herridge
51 zhuravel - apprehensions - iran - aside - sectors 56 51_zhuravel_apprehensions_iran_aside
52 reclaimthenet - lizharrington76 - edwards - transgender - gatewaypunditofficial 56 52_reclaimthenet_lizharrington76_edwards_transgender
53 loneliness - alphas - johncornyn - briefs - jokes 55 53_loneliness_alphas_johncornyn_briefs
54 womens - lmao - checked - commissioner - detroit 53 54_womens_lmao_checked_commissioner
55 wellbeing - incriminate - carcass - dissolves - rhino 50 55_wellbeing_incriminate_carcass_dissolves
56 motorcycles - overdue - poisoned - dismayed - spearheading 49 56_motorcycles_overdue_poisoned_dismayed
57 investing - promoted - thinks - infowars - controls 49 57_investing_promoted_thinks_infowars
58 sprinterfactory - israeli - mediasets1 - flaming - prospects 47 58_sprinterfactory_israeli_mediasets1_flaming
59 converted - fisherman - shots - wins - oaklanders 47 59_converted_fisherman_shots_wins
60 crying - fathers - actors - practically - founding 46 60_crying_fathers_actors_practically
61 alibradleytv - bradley - roberts - pentagon - intercepted 44 61_alibradleytv_bradley_roberts_pentagon
62 buildings - 1960s - connecting - cars - 1940s 44 62_buildings_1960s_connecting_cars
63 shaykhsulaiman - abdullah - nsfw - hasnatpakistani - israeli 44 63_shaykhsulaiman_abdullah_nsfw_hasnatpakistani
64 theinsiderpaper - uberboyo - grown - parliament - balls 43 64_theinsiderpaper_uberboyo_grown_parliament
65 helicopters - thestormhasarrived - ca_insider - sav_says_ - wristbands 42 65_helicopters_thestormhasarrived_ca_insider_sav_says_
66 transactions - celebrations - incentives - thinks - statements 42 66_transactions_celebrations_incentives_thinks
67 balls - aids - woods - pushing - weekends 42 67_balls_aids_woods_pushing
68 realdonaldtrump - hampshire - kristina_wong - lfg - rapids 41 68_realdonaldtrump_hampshire_kristina_wong_lfg
69 mysteriously - unchanged - balloons - bpcostello - complaints 41 69_mysteriously_unchanged_balloons_bpcostello
70 converted - 2hrs - mexicans - antidepressant - puppets 40 70_converted_2hrs_mexicans_antidepressant
71 thewesternchauvinist5 - thewesternchauvinist7 - theferrymanstoll - dailyrealtimenews - crickets 40 71_thewesternchauvinist5_thewesternchauvinist7_theferrymanstoll_dailyrealtimenews
72 icscq4w - rf0y1m4 - 3fgm6cz - eec5zbi - jp6d3zb 39 72_icscq4w_rf0y1m4_3fgm6cz_eec5zbi
73 riding - examples - couples - 1960s - surpassing 37 73_riding_examples_couples_1960s
74 bears - siciliangorillian2 - 766k - ftx - likes 37 74_bears_siciliangorillian2_766k_ftx
75 unforgettable - heartbroken - worker - hills - nurses 36 75_unforgettable_heartbroken_worker_hills
76 uncensored - unfounded - carriage - altskull48 - occupy 35 76_uncensored_unfounded_carriage_altskull48
77 americanscantbreathe - dictatorships - whisperer - skyrocketed - defendfreespeech 33 77_americanscantbreathe_dictatorships_whisperer_skyrocketed
78 iiiegals - grabblers - wishing - reptilian - inclined 33 78_iiiegals_grabblers_wishing_reptilian
79 trolling - invading - risks - fears - responses 33 79_trolling_invading_risks_fears
80 pillows - wwii - facts - wojpawelczyk - rudygiuliani 32 80_pillows_wwii_facts_wojpawelczyk
81 safes - cohencidental - palestinians - elon - history 31 81_safes_cohencidental_palestinians_elon
82 brittney - grassley - buttplug - francisco - thieves 31 82_brittney_grassley_buttplug_francisco
83 cnnpolitics - roberts - thefts - awards - override 31 83_cnnpolitics_roberts_thefts_awards
84 unmooring - funds - investments - subversive - gdp 31 84_unmooring_funds_investments_subversive
85 torpedo - operators - muckraker - trains - recordings 30 85_torpedo_operators_muckraker_trains
86 deployment - carriers - flows - metals - consumers 30 86_deployment_carriers_flows_metals
87 brainwashing - pushing - carlson - bankers - noticing 29 87_brainwashing_pushing_carlson_bankers
88 cig_telegram - firefighters - resistornewswireuk - plants - france 29 88_cig_telegram_firefighters_resistornewswireuk_plants
89 quadcopters - missiles - quadcopter - carrying - decommissioning 29 89_quadcopters_missiles_quadcopter_carrying
90 firefighters - france - spearheaded - sicilians - unalterable 28 90_firefighters_france_spearheaded_sicilians
91 minnesota - pills - multipolar - doctors - coins 27 91_minnesota_pills_multipolar_doctors
92 hotwifing - kj1tjcfbemc - vlpdvsj - kansas - undocumented 27 92_hotwifing_kj1tjcfbemc_vlpdvsj_kansas
93 signs - highlights - ads - cats - staggering 26 93_signs_highlights_ads_cats
94 weimar - fox - nc - life - weave 26 94_weimar_fox_nc_life
95 amer_icanbadass - fisherlady111 - theonlydsc - censoredmen - censored 26 95_amer_icanbadass_fisherlady111_theonlydsc_censoredmen
96 thewesternchauvinist5 - utahzoomer - siciliangorillian2 - mentally - talks 26 96_thewesternchauvinist5_utahzoomer_siciliangorillian2_mentally
97 institutions - embarrassed - promised - unknown - pushing 25 97_institutions_embarrassed_promised_unknown
98 massachusetts - shelter - deployed - troopers - concerns 25 98_massachusetts_shelter_deployed_troopers
99 tombstone - police_frequency - claiming - migrants - blanketed 25 99_tombstone_police_frequency_claiming_migrants
100 reporting - jakepaul - natediaz209 - equity - dallas 24 100_reporting_jakepaul_natediaz209_equity
101 secblinken - unfairly - puppets - toss - france 24 101_secblinken_unfairly_puppets_toss
102 screamed - disbelieving - incredulous - mattwalshblog - nathanjrobinson 24 102_screamed_disbelieving_incredulous_mattwalshblog
103 theonlydsc - ᗰisᑕᕼiᗴᖴ - rulerofhumanity - txdeplorable - gettrmvp 24 103_theonlydsc_ᗰisᑕᕼiᗴᖴ_rulerofhumanity_txdeplorable
104 greg_price11 - poisoned - censoredmen - victims - choices 23 104_greg_price11_poisoned_censoredmen_victims
105 unremarkable - kgr9yzd - footprints - snatched - phones 23 105_unremarkable_kgr9yzd_footprints_snatched
106 scottlobaido - michael_yon - robertkennedyjr - richard_harambe - jimmy_dore 23 106_scottlobaido_michael_yon_robertkennedyjr_richard_harambe
107 nypd6pct - hellenic - licensing - foremost - showers 22 107_nypd6pct_hellenic_licensing_foremost
108 hypocrite - lporiginalg - ancestor - memes - endwokeness 21 108_hypocrite_lporiginalg_ancestor_memes
109 stoptheinvasion - stoptheboats - encrypted - anthonyweiner - discredited 21 109_stoptheinvasion_stoptheboats_encrypted_anthonyweiner
110 altskull48 - frens - redpillpharmacist - carlson - spreading 21 110_altskull48_frens_redpillpharmacist_carlson
111 chirp - community - calorie - kek - vey 21 111_chirp_community_calorie_kek
112 justdudechannel - geopoliticsandempire - minds - soundcloud - an0maly 21 112_justdudechannel_geopoliticsandempire_minds_soundcloud
113 shamelessly - singlehandedly - subtly - weakened - beholden 20 113_shamelessly_singlehandedly_subtly_weakened
114 sombreriza_d_mz - losbloqueados2 - elblogdelosgua1 - thewarnextdoor - jalisciense1c3 20 114_sombreriza_d_mz_losbloqueados2_elblogdelosgua1_thewarnextdoor
115 onlyfans - russian - ballistic - alive - optic 20 115_onlyfans_russian_ballistic_alive
116 uncovered - unwavering - heartbroken - compiles - flooding 20 116_uncovered_unwavering_heartbroken_compiles
117 indoctrinated - publishing - elections - ungathegreat - brainwash 20 117_indoctrinated_publishing_elections_ungathegreat
118 aforementioned - strengthening - silicon - eritrean - vandals 20 118_aforementioned_strengthening_silicon_eritrean
119 resistornewswire - roadblocks - facts - overdose - collapses 20 119_resistornewswire_roadblocks_facts_overdose
120 mistakenly - lgbtqwxyz - rabbit - consumed - adams 19 120_mistakenly_lgbtqwxyz_rabbit_consumed
121 aside - infected - depleted - ffs - linkedin 19 121_aside_infected_depleted_ffs
122 oversight - deployment - answers - secured - marshals 19 122_oversight_deployment_answers_secured
123 unusual_whales - bennyjohnson - grabbers - kurtschlichter - azerbaijan 18 123_unusual_whales_bennyjohnson_grabbers_kurtschlichter
124 overrated - cernolisp - shorts - thinks - weinstein 18 124_overrated_cernolisp_shorts_thinks
125 aim4theheadx - slaughtered - based_poland - france - censoredmen 18 125_aim4theheadx_slaughtered_based_poland_france
126 shots - officers - cameras - zuckerberg - reportedly 18 126_shots_officers_cameras_zuckerberg
127 acquitted - repeatedly - awaiting - identifying - jackass 17 127_acquitted_repeatedly_awaiting_identifying
128 michoacana - mothers - libs - suspected - recorded 17 128_michoacana_mothers_libs_suspected
129 yaboi - lsraei - ayo - joe - banger 17 129_yaboi_lsraei_ayo_joe
130 rothschildcovid19patent - bitch - enjoythed - obscuro - latamobscuro 17 130_rothschildcovid19patent_bitch_enjoythed_obscuro
131 mick_o_keeffe - drclaytonforre1 - shamelessly - dragshows - profits 17 131_mick_o_keeffe_drclaytonforre1_shamelessly_dragshows
132 lauren3vememes - johnhackerla - ultra_majesty - mythinformedmke - lporiginalg 16 132_lauren3vememes_johnhackerla_ultra_majesty_mythinformedmke
133 ninja_stuntz - cryptoonlycoims - censoredmen - animalautisms - censored 16 133_ninja_stuntz_cryptoonlycoims_censoredmen_animalautisms
134 bombing - spain - scholarly - reminder - ford 15 134_bombing_spain_scholarly_reminder
135 siciliangorillian2 - siciliangorillian - commander - craziness - creep 15 135_siciliangorillian2_siciliangorillian_commander_craziness
136 mattgaetz - bidenbordercrisis - realjameswoods - brianroemmele - tomselliott 15 136_mattgaetz_bidenbordercrisis_realjameswoods_brianroemmele
137 intersectionality - repeatedly - apprehensions - kansas - screaming 15 137_intersectionality_repeatedly_apprehensions_kansas
138 parliamentary - livestreamer - johnny - connectivity - mentally 15 138_parliamentary_livestreamer_johnny_connectivity
139 unfettered - democrats - robinmg - retardsoftiktok - pretending 15 139_unfettered_democrats_robinmg_retardsoftiktok
140 israelfightsback - christopherhitchens - caitlyn_jenner - knappertsbusch - cwbchicago 15 140_israelfightsback_christopherhitchens_caitlyn_jenner_knappertsbusch
141 greg_price11 - lukewearechange - oilfield_rando - closet - goodness 15 141_greg_price11_lukewearechange_oilfield_rando_closet
142 extort - carlson - ukraine - hypocrisy - wire 15 142_extort_carlson_ukraine_hypocrisy
143 deceiving - canadafirst2 - misrepresentation - honestly - contemptible 14 143_deceiving_canadafirst2_misrepresentation_honestly
144 trannys - silicon - signs - officers - staying 14 144_trannys_silicon_signs_officers
145 riley_gaines_ - disrespecting - bastards - reluctantlyjoe - barstoolsports 13 145_riley_gaines__disrespecting_bastards_reluctantlyjoe
146 strengthened - misperceptions - distillate - holocausting - islamic 13 146_strengthened_misperceptions_distillate_holocausting
147 roosevelt - siciliangorillian2 - weapons - parade - ufc299 13 147_roosevelt_siciliangorillian2_weapons_parade
148 clinics - impacts - circle - falling - pushing 13 148_clinics_impacts_circle_falling
149 balls - funds - giggles - shocking - mentally 13 149_balls_funds_giggles_shocking
150 repjamescomer - muhsociofactors - assaults - laralogan - larry_kudlow 13 150_repjamescomer_muhsociofactors_assaults_laralogan
151 shelter - oligarchs - sxnvfio - retreat - approvals 13 151_shelter_oligarchs_sxnvfio_retreat
152 unreliable - ethnically - reprogramming - russians - governments 13 152_unreliable_ethnically_reprogramming_russians
153 fundraiser - injuring - newyork - collapsed - collapses 13 153_fundraiser_injuring_newyork_collapsed
154 censoredmen - censored - fightwithmemes - falling - harmlessyarddog 13 154_censoredmen_censored_fightwithmemes_falling
155 bidenborderinvasion - bbbbased - philadelphia - tm - sanfrancisco 13 155_bidenborderinvasion_bbbbased_philadelphia_tm
156 washington - unknown - licensing - curtissliwa - migrants 13 156_washington_unknown_licensing_curtissliwa
157 stanleyroberts - repjamescomer - untimely - roberts - unsolved 12 157_stanleyroberts_repjamescomer_untimely_roberts
158 oversight - transgender - hampshire - victims - announces 12 158_oversight_transgender_hampshire_victims
159 launched - simpsons - topics - smiling - dobbs 12 159_launched_simpsons_topics_smiling
160 revolutionaries - bloodied - collapsing - carlson - slides 12 160_revolutionaries_bloodied_collapsing_carlson
161 foreseeable - tortured - brainwashing - interfering - faster 11 161_foreseeable_tortured_brainwashing_interfering
162 boringly - wildfires - theblaze - charliekirk11 - carlson 11 162_boringly_wildfires_theblaze_charliekirk11
163 evacuating - biden - history - chris - service 11 163_evacuating_biden_history_chris
164 joao_chumbinho - margaretriverpro - johnny - ackerman - secured 11 164_joao_chumbinho_margaretriverpro_johnny_ackerman
165 bankrupt - cowards - elon - iq - cretin 10 165_bankrupt_cowards_elon_iq
166 acts - carlson - apwikxy - john - dignified 10 166_acts_carlson_apwikxy_john
167 deportation - adams - sanctuary - supports - hundreds 10 167_deportation_adams_sanctuary_supports
168 scootercasterny - scootercaster - ny_actions - xr_nyc - letstalkdgu 10 168_scootercasterny_scootercaster_ny_actions_xr_nyc
169 lockdowns - livjohnsontv - crickets - hormones - wrecked 10 169_lockdowns_livjohnsontv_crickets_hormones

Training hyperparameters

  • calculate_probabilities: False
  • 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: 1.23.5
  • HDBSCAN: 0.8.38.post1
  • UMAP: 0.5.6
  • Pandas: 2.2.2
  • Scikit-Learn: 1.5.1
  • Sentence-transformers: 3.0.1
  • Transformers: 4.44.2
  • Numba: 0.60.0
  • Plotly: 5.24.0
  • Python: 3.10.12