BERTopic_GeorgeWebb

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_GeorgeWebb")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 92
  • Number of training documents: 7194
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 thedukereport - realgeorgewebb1 - erasmus - downloaded - pottinger 12 -1_thedukereport_realgeorgewebb1_erasmus_downloaded
0 walker - ukraine - michael - virginia - paul 1889 0_walker_ukraine_michael_virginia
1 walker - ukraine - pfizer - journalism - anthrax 716 1_walker_ukraine_pfizer_journalism
2 investigative - begins - erasmus - quartet - gonzalo 373 2_investigative_begins_erasmus_quartet
3 bioagents - washington - michael - consulting - supported 353 3_bioagents_washington_michael_consulting
4 mcdufflivestwo - mcduff - railroads - wednesday - aids 270 4_mcdufflivestwo_mcduff_railroads_wednesday
5 stalkinghorse - slaughterpen - snippets - gathering - validation 229 5_stalkinghorse_slaughterpen_snippets_gathering
6 hemorrhagic - gasoline - spraying - moneypenny - ukraine 201 6_hemorrhagic_gasoline_spraying_moneypenny
7 cells - sides - ops - sars - breggins 143 7_cells_sides_ops_sars
8 realgeorgewebb1 - thedukereport - kineticcourtz - thejasonrink - livestreaming 138 8_realgeorgewebb1_thedukereport_kineticcourtz_thejasonrink
9 electrocardiograms - incomprable - jamescomer - erasmus - zealousness 127 9_electrocardiograms_incomprable_jamescomer_erasmus
10 fl_progressive - 2fimages - flying - cells - experiments 107 10_fl_progressive_2fimages_flying_cells
11 drying - livewithandy - charliekirk11 - rounds - scottpelly1 100 11_drying_livewithandy_charliekirk11_rounds
12 encrypted - rehearsals - racing - reporting - mentoring 92 12_encrypted_rehearsals_racing_reporting
13 encrypted - weapons - ukraine - virginia - hunter 90 13_encrypted_weapons_ukraine_virginia
14 accounts - dewine - virginia - ssn - curve 86 14_accounts_dewine_virginia_ssn
15 download_it_bot - whistleblower - biosensors - synthetic - midgets 79 15_download_it_bot_whistleblower_biosensors_synthetic
16 slaughter - natethelawyer - televised - bethesda - sunbathing 74 16_slaughter_natethelawyer_televised_bethesda
17 hairdresser - minnesota - interviews - prayers - frankfurt 66 17_hairdresser_minnesota_interviews_prayers
18 bioengineered - hemorrhagic - pfizerorg - footprints - synthetic 61 18_bioengineered_hemorrhagic_pfizerorg_footprints
19 mysteriously - measures - cells - advisory - farming 56 19_mysteriously_measures_cells_advisory
20 hemorrhagic - biolabs - swine - ghislanemaxwelltrial - erasmus 54 20_hemorrhagic_biolabs_swine_ghislanemaxwelltrial
21 v3txg6j - v3pxrmj - v3cdn5f - v3gvdea - v3y8kcm 53 21_v3txg6j_v3pxrmj_v3cdn5f_v3gvdea
22 realgeorgewebb1 - slaughter - livewithandy - lady__duchess - infowars 50 22_realgeorgewebb1_slaughter_livewithandy_lady__duchess
23 remastered - motorcycles - infoblocks - reinhardt - sideffect 50 23_remastered_motorcycles_infoblocks_reinhardt
24 1eajbgb - 1eajbgm - 1dxgyjg - 1odkrjr - 1djxxng 50 24_1eajbgb_1eajbgm_1dxgyjg_1odkrjr
25 rebels - bye - simulation - underscore - 10s 48 25_rebels_bye_simulation_underscore
26 uci8bkz7l3lc0 - housatonic - synthetic - shots - finals 47 26_uci8bkz7l3lc0_housatonic_synthetic_shots
27 workarounds - slaughter - thesteeltruth - canadian - biocontainment 46 27_workarounds_slaughter_thesteeltruth_canadian
28 coronavirusmcnutt - shamelessly - economics - adrenochrome - demolition 45 28_coronavirusmcnutt_shamelessly_economics_adrenochrome
29 interleukins - peacekeepers - insurrection - outbreaks - erasmus 45 29_interleukins_peacekeepers_insurrection_outbreaks
30 thelaroucheorganization - avenues - interviews - screamingospreys - fathers 42 30_thelaroucheorganization_avenues_interviews_screamingospreys
31 downloaded - booster - housatonic - lee - nguyen 41 31_downloaded_booster_housatonic_lee
32 stratospheric - ethnically - v3cds4y - wesley - bioagents 40 32_stratospheric_ethnically_v3cds4y_wesley
33 1mrgmyx - 1rmgpmz - 1plkqdb - spaces - 1owxwwe 39 33_1mrgmyx_1rmgpmz_1plkqdb_spaces
34 grandkids - foretelling - aventis - consulting - protocols 39 34_grandkids_foretelling_aventis_consulting
35 download_it_bot - avenues - shares - screamingospreys - downloaded 39 35_download_it_bot_avenues_shares_screamingospreys
36 restarting - overdose - lights - downloaded - housatonic 38 36_restarting_overdose_lights_downloaded
37 dr_steph_gayet - realgeorgewebb1 - singersongwriter - sarahhrakm1 - downloaded 38 37_dr_steph_gayet_realgeorgewebb1_singersongwriter_sarahhrakm1
38 unloaded - strangely - shortcuts - falling - stevens 38 38_unloaded_strangely_shortcuts_falling
39 ivins - begins - investigative - fitzgibbon - jewels 36 39_ivins_begins_investigative_fitzgibbon
40 realgeorgewebb1 - fireworks - leytedriver - mcdufflives - realconniebevan 36 40_realgeorgewebb1_fireworks_leytedriver_mcdufflives
41 analytics - interviews - balls - housatonic - brassballs 34 41_analytics_interviews_balls_housatonic
42 slaughter - facts - cells - launching - ivins 34 42_slaughter_facts_cells_launching
43 hemorrhagic - politics - myocarditis - ukraine - bombs 32 43_hemorrhagic_politics_myocarditis_ukraine
44 trumparraignment - prussian - drjudyamikovits - investigative - rehearse 32 44_trumparraignment_prussian_drjudyamikovits_investigative
45 1dxxyjg - 1rmxp - 1djgxlw - 1rmxpma - 1mrgmyo 30 45_1dxxyjg_1rmxp_1djgxlw_1rmxpma
46 canariesblue - overcrowded - graciously - believed - swinging 28 46_canariesblue_overcrowded_graciously_believed
47 kate_hampstead - thedukereport - america1stlegal - realgeorgewebb1 - squads 28 47_kate_hampstead_thedukereport_america1stlegal_realgeorgewebb1
48 faster - myocarditis - tweets - commonwealth - begins 27 48_faster_myocarditis_tweets_commonwealth
49 avenues - upcoming - doctors - fathers - screamingospreys 27 49_avenues_upcoming_doctors_fathers
50 whistleblowers - fireworks - realgeorgewebb1 - secrets - mcdufflivestwo 27 50_whistleblowers_fireworks_realgeorgewebb1_secrets
51 unconditional - housatonic - psychopathic - studios - aids 26 51_unconditional_housatonic_psychopathic_studios
52 stopthesteal - avenues - doctors - screamingospreys - biodefense 26 52_stopthesteal_avenues_doctors_screamingospreys
53 unsealed - governments - commonwealth - profits - unlocked 25 53_unsealed_governments_commonwealth_profits
54 fl_progressive - triggering - supported - raises - subscriber 25 54_fl_progressive_triggering_supported_raises
55 mcdufflives - mcduff - mcdufflivestwo - topics - weekly 24 55_mcdufflives_mcduff_mcdufflivestwo_topics
56 crusader - biosolutions - presumably - recovering - awards 24 56_crusader_biosolutions_presumably_recovering
57 cowboys - rockefellers - knights - johnny - mcduff 24 57_cowboys_rockefellers_knights_johnny
58 launched - studying - doctors - loans - superspreaders 23 58_launched_studying_doctors_loans
59 videographer - johnson - blackberries - hunt - georgia 23 59_videographer_johnson_blackberries_hunt
60 bradley - cutouts - counterattack - inquiry - wesley 23 60_bradley_cutouts_counterattack_inquiry
61 powerpoints - biographer - embraceable - graphics - citizens 23 61_powerpoints_biographer_embraceable_graphics
62 neighborhoodnewsstudios - realgeorgewebb1 - wednesday - leytedriver - realconniebevan 21 62_neighborhoodnewsstudios_realgeorgewebb1_wednesday_leytedriver
63 unspeakable - backing - georgia - reminder - incomparable 21 63_unspeakable_backing_georgia_reminder
64 housatonic - bradford - deaths - approvals - leads 19 64_housatonic_bradford_deaths_approvals
65 housatonic - untitled - auchincloss - connections - booster 19 65_housatonic_untitled_auchincloss_connections
66 backstage - forthcoming - lhatesyoualot - screaming - download_it_bot 18 66_backstage_forthcoming_lhatesyoualot_screaming
67 downloaded - telegram - alternate - new - channel 18 67_downloaded_telegram_alternate_new
68 downloaded - telegram - watch - - 17 68_downloaded_telegram_watch_
69 retrocomputing - tolerated - housatonicits - housatoniclive - computinghistory 17 69_retrocomputing_tolerated_housatonicits_housatoniclive
70 encrypted - tuckercarlson - bodyguards - profits - publishing 17 70_encrypted_tuckercarlson_bodyguards_profits
71 spaces - 1kvkpvn - 1ypkddz - 1lyxbqw - 1yqgodp 17 71_spaces_1kvkpvn_1ypkddz_1lyxbqw
72 guessing - secrets - erasmus - julian - burner 16 72_guessing_secrets_erasmus_julian
73 deadly - cameras - embraceable - erasmus - reenactment 16 73_deadly_cameras_embraceable_erasmus
74 myocarditis - booklets - delayed - battlefields - missouri 16 74_myocarditis_booklets_delayed_battlefields
75 memorialday2021 - mcm88gksw7a - realgeorgewebb1 - screamingospreys - weapons 15 75_memorialday2021_mcm88gksw7a_realgeorgewebb1_screamingospreys
76 realgeorgewebb1 - leytedriver - mistakes - investigative - jackrobertcat 15 76_realgeorgewebb1_leytedriver_mistakes_investigative
77 dsj2khtczx0 - thedukereport - vkfphzisa - leytedriver - jsuj0zaywq4 15 77_dsj2khtczx0_thedukereport_vkfphzisa_leytedriver
78 whistleblower - transgender - johnson - doctors - blackberries 15 78_whistleblower_transgender_johnson_doctors
79 gbj3g - unblocked - housatoniclive - slides - shadowbanning 14 79_gbj3g_unblocked_housatoniclive_slides
80 subpoenathebidenblackberrys - subpoenatheblackberrys - trumparraignment - thebravermanprophecy - thedukereport 14 80_subpoenathebidenblackberrys_subpoenatheblackberrys_trumparraignment_thebravermanprophecy
81 jaybeemediadlbot - video - - - 14 81_jaybeemediadlbot_video__
82 1owgwya - 1owxwyz - 1lyxbnp - spaces - 1owxwya 14 82_1owgwya_1owxwyz_1lyxbnp_spaces
83 deployed - summers - erasmus - uses - hanging 14 83_deployed_summers_erasmus_uses
84 realgeorgewebb1 - livewithandy - sniffing - housatoniclive - nanoparticle 14 84_realgeorgewebb1_livewithandy_sniffing_housatoniclive
85 realgeorgewebb1 - awaited - housatonic - ukraine - wins 13 85_realgeorgewebb1_awaited_housatonic_ukraine
86 introduced - france - writers - biscayne - nawctsd 13 86_introduced_france_writers_biscayne
87 avenues - doctors - shares - screamingospreys - mcdaniel 13 87_avenues_doctors_shares_screamingospreys
88 wesley - servers - bombs - megabucks - pentagon 13 88_wesley_servers_bombs_megabucks
89 bioagents - profits - snipers - julian - reporting 13 89_bioagents_profits_snipers_julian
90 v3fsg9g - embraceable - odysseus - rising - mrs 12 90_v3fsg9g_embraceable_odysseus_rising

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
Downloads last month
2
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.