MARTINI_enrich_BERTopic_Not_On_The_Beeb

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_Not_On_The_Beeb")

topic_model.get_topic_info()

Topic overview

• Number of topics: 66
• Number of training documents: 7161

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	vaccinated - pandemic - 2021 - freedom - everyone	20	-1_vaccinated_pandemic_2021_freedom
0	jabberwockys - neighbour - bobby - charlton - tesco	3560	0_jabberwockys_neighbour_bobby_charlton
1	athletes - footballer - died - collapsed - cpr	321	1_athletes_footballer_died_collapsed
2	vaccination - unvaccinated - children - risks - fluenz	190	2_vaccination_unvaccinated_children_risks
3	beam - watching - articles - chappelle - maaaaaaaaaaaaaaaate	170	3_beam_watching_articles_chappelle
4	hamas - gaza - palestinians - israelis - antisemitism	154	4_hamas_gaza_palestinians_israelis
5	censorship - wikileaks - spying - disinformation - facebook	121	5_censorship_wikileaks_spying_disinformation
6	pfizer - fatalities - 2021 - anaphylaxis - card	106	6_pfizer_fatalities_2021_anaphylaxis
7	magnetised - mri - vaccinations - mercury - nanoparticles	99	7_magnetised_mri_vaccinations_mercury
8	ukraine - donetsk - zelenskiy - mariupol - russians	96	8_ukraine_donetsk_zelenskiy_mariupol
9	climeworks - temperatures - alarmist - ww3 - hotter	95	9_climeworks_temperatures_alarmist_ww3
10	menstruate - vaccination - miscarriages - contraceptives - gynaecologists	89	10_menstruate_vaccination_miscarriages_contraceptives
11	vaxxed - itv - safeandeffective - documentary - sharman	89	11_vaxxed_itv_safeandeffective_documentary
12	shirts - jointhewhiterose - freeeeeeee - sticker - protest	83	12_shirts_jointhewhiterose_freeeeeeee_sticker
13	globalist - rockefeller - plandemic - snowden - awakening	80	13_globalist_rockefeller_plandemic_snowden
14	worldcouncilforhealth - petition - sovereignty - parliamentarians - amendments	79	14_worldcouncilforhealth_petition_sovereignty_parliamentarians
15	myocarditis - vaers - palpitation - symptoms - mrna	79	15_myocarditis_vaers_palpitation_symptoms
16	not_on_the_beeb - highlights - webpage - propaganda - digitalwarriorproductions	68	16_not_on_the_beeb_highlights_webpage_propaganda
17	dna - plasmid - vaccines - gmos - contaminated	67	17_dna_plasmid_vaccines_gmos
18	dreamers - passions - regret - constantly - succumb	62	18_dreamers_passions_regret_constantly
19	hemp - cannabinoids - nigella - ivermectin - honey	55	19_hemp_cannabinoids_nigella_ivermectin
20	ncov - pcr - virologists - conspiracy - false	54	20_ncov_pcr_virologists_conspiracy
21	vaccination - nhs100k - mandatory - employers - gbnews	53	21_vaccination_nhs100k_mandatory_employers
22	jamforfreedom - chiswick - eventbrite - friday - stephen	52	22_jamforfreedom_chiswick_eventbrite_friday
23	doctors - nhs - hippocratic - ukmfa - naturopathic	52	23_doctors_nhs_hippocratic_ukmfa
24	londoners - mayor - ulez - khan - emissions	52	24_londoners_mayor_ulez_khan
25	cashless - britcoin - stablecoins - payments - coins	49	25_cashless_britcoin_stablecoins_payments
26	protests - arrests - london - policeman - footage	46	26_protests_arrests_london_policeman
27	lampedusa - melilla - protesters - garibaldi - francia	46	27_lampedusa_melilla_protesters_garibaldi
28	parliament - westminster - deaths - bridgend - andrew	45	28_parliament_westminster_deaths_bridgend
29	vaccinated - sweden - passport - holidaymakers - montenegro	44	29_vaccinated_sweden_passport_holidaymakers
30	markplayne - kindle - bogota - exupery - thrilling	42	30_markplayne_kindle_bogota_exupery
31	pfizer - falsified - kickbacks - celebrex - fy21	40	31_pfizer_falsified_kickbacks_celebrex
32	graphene - vaccines - contaminations - vial - agin	39	32_graphene_vaccines_contaminations_vial
33	horizon - pythagoras - geoengineeringwatch - gravity - circumference	39	33_horizon_pythagoras_geoengineeringwatch_gravity
34	pilots - aircrewdefence - aussiefreedomflyers - qantas - gatwick	39	34_pilots_aircrewdefence_aussiefreedomflyers_qantas
35	trudeau - truckers - insurrectionists - ottowa - cbc	35	35_trudeau_truckers_insurrectionists_ottowa
36	repost - davos - booing - sundaymirror - dream	33	36_repost_davos_booing_sundaymirror
37	bottled - waterlight - straws - microscope - fluoride	33	37_bottled_waterlight_straws_microscope
38	telegraph_the_bbc_did_what_the_government_wanted_june - mri - oregano - links - graphene	33	38_telegraph_the_bbc_did_what_the_government_wanted_june_mri_oregano_links
39	savebabywill - unvaccinated - counterspinmedia - auckland - transfusions	32	39_savebabywill_unvaccinated_counterspinmedia_auckland
40	masks - nhs - ukmfa - mandates - headteacher	32	40_masks_nhs_ukmfa_mandates
41	paypal - boycott - defund - gofundme - natwest	31	41_paypal_boycott_defund_gofundme
42	broadyorkshirelaw - immunisation - solicitor - complainants - issued	30	42_broadyorkshirelaw_immunisation_solicitor_complainants
43	cepi - mccullough - quackkines - mbbch - cardiologist	29	43_cepi_mccullough_quackkines_mbbch
44	banned - bot - whatsapp - cbdcs - whistleblower	29	44_banned_bot_whatsapp_cbdcs
45	deaths - vaers - children - jabbed - 15	28	45_deaths_vaers_children_jabbed
46	cameron - tory - leigh - dougie - tonight	28	46_cameron_tory_leigh_dougie
47	radiofrequency - antennas - 5g - airwavedefender - satellites	28	47_radiofrequency_antennas_5g_airwavedefender
48	transgender - indoctrination - puberty - minors - doping	28	48_transgender_indoctrination_puberty_minors
49	oncologists - metastatic - lymphoblastic - boosters - mammogram	27	49_oncologists_metastatic_lymphoblastic_boosters
50	ivermectin - worldivermectinday - molnupiravir - india - prophylactic	27	50_ivermectin_worldivermectinday_molnupiravir_india
51	mortalities - statista - 2020 - funeral - wales	26	51_mortalities_statista_2020_funeral
52	repost - nato - banned - disagree - mep	25	52_repost_nato_banned_disagree
53	mask - pathogens - corynebacterium - contaminated - microplastics	22	53_mask_pathogens_corynebacterium_contaminated
54	netherlands - farmers - vlaardingerbroek - coups - rutte	22	54_netherlands_farmers_vlaardingerbroek_coups
55	betterwayconference - attendee - wellmann - virtual - wchsubscriber	22	55_betterwayconference_attendee_wellmann_virtual
56	mikael - nordfors - memorial - magufuli - virologist	21	56_mikael_nordfors_memorial_magufuli
57	ukraine - bioweapons - biden - konashenkov - pentagon	21	57_ukraine_bioweapons_biden_konashenkov
58	thrombosis - clotting - dvt - heparin - astrazeneca	21	58_thrombosis_clotting_dvt_heparin
59	vaccinated - causalties - 94 - percentage - unfounded	21	59_vaccinated_causalties_94_percentage
60	digitalization - saveourrights - identities - stamp - stasi	21	60_digitalization_saveourrights_identities_stamp
61	oregano - forgotify - honey - bombs - herbalist	21	61_oregano_forgotify_honey_bombs
62	bots - banned - spammer - messages - lurking	20	62_bots_banned_spammer_messages
63	petrol - electricity - decarbonise - subsidies - bill	20	63_petrol_electricity_decarbonise_subsidies
64	djokovic - australia - novax - deported - visa	20	64_djokovic_australia_novax_deported

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