MARTINI_enrich_BERTopic_davidickeofficial

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_davidickeofficial")

topic_model.get_topic_info()

Topic overview

• Number of topics: 50
• Number of training documents: 5006

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	vaccine - fake - lockdown - biden - england	20	-1_vaccine_fake_lockdown_biden
0	ukraine - zelensky - missiles - ww3 - sanctions	2556	0_ukraine_zelensky_missiles_ww3
1	hamas - israelis - airstrikes - militants - soleimani	197	1_hamas_israelis_airstrikes_militants
2	artificial - openai - mankind - warns - dystopia	165	2_artificial_openai_mankind_warns
3	london - ulez - motorists - mayor - sadiq	118	3_london_ulez_motorists_mayor
4	greenpeace - renewables - blackouts - power - boilers	107	4_greenpeace_renewables_blackouts_power
5	musk - tweets - takeover - richest - 44billion	87	5_musk_tweets_takeover_richest
6	pfizergate - vaccinated - mrna - fake - documents	80	6_pfizergate_vaccinated_mrna_fake
7	netherlands - livestream - banned - david - protest	78	7_netherlands_livestream_banned_david
8	tory - starmer - blair - eurocrats - shadowing	77	8_tory_starmer_blair_eurocrats
9	twindemic - britain - psychopaths - michie - ministers	73	9_twindemic_britain_psychopaths_michie
10	tonight - news - nickita - podcaster - dowding	71	10_tonight_news_nickita_podcaster
11	davidickelive - subscribe - albion - divine - january	71	11_davidickelive_subscribe_albion_divine
12	fauci - vaccination - deaths - ccvac - myocarditis	62	12_fauci_vaccination_deaths_ccvac
13	antarctica - alarmism - weatherman - colder - hottest	60	13_antarctica_alarmism_weatherman_colder
14	migrants - coastguard - arriving - skegness - smuggled	60	14_migrants_coastguard_arriving_skegness
15	midazolam - killing - drugging - hancock - nuremberg	59	15_midazolam_killing_drugging_hancock
16	tonight - ickonic - watch - episodes - www	55	16_tonight_ickonic_watch_episodes
17	tesla - charging - electrified - petrol - renewable	53	17_tesla_charging_electrified_petrol
18	unvaccinated - cdc - dose - fake - 291k	49	18_unvaccinated_cdc_dose_fake
19	epstein - ghislaine - paedophile - prince - mountbatten	48	19_epstein_ghislaine_paedophile_prince
20	trudeau - fascists - freeland - convoy - ceausescu	46	20_trudeau_fascists_freeland_convoy
21	teachers - genders - girls - transphobe - sex	46	21_teachers_genders_girls_transphobe
22	bbc - southgate - broadcaster - yaqub - bias	40	22_bbc_southgate_broadcaster_yaqub
23	australia - gareth - tjumpatjimpa - christiansen - podcasters	39	23_australia_gareth_tjumpatjimpa_christiansen
24	mayor - illegals - denver - yuma - floodgates	38	24_mayor_illegals_denver_yuma
25	ufos - spacecraft - debris - scientists - jupiter	36	25_ufos_spacecraft_debris_scientists
26	died - footballers - sergio - collapses - lartillot	36	26_died_footballers_sergio_collapses
27	transgender - swimmers - ladies - championships - lynne	33	27_transgender_swimmers_ladies_championships
28	biden - democrats - mcconnell - kamala - independent	32	28_biden_democrats_mcconnell_kamala
29	pandemic - diktats - sovereignty - eu - oliver	31	29_pandemic_diktats_sovereignty_eu
30	biden - fbi - whistleblower - bribery - emails	31	30_biden_fbi_whistleblower_bribery
31	censorship - fascistic - ofcom - goebbels - unconstitutional	30	31_censorship_fascistic_ofcom_goebbels
32	royals - monarchy - balmoral - buckingham - harry	29	32_royals_monarchy_balmoral_buckingham
33	insurrectionists - fbi - carlson - january - colluding	28	33_insurrectionists_fbi_carlson_january
34	globalist - bilderberger - kissinger - leaders - leonardo	28	34_globalist_bilderberger_kissinger_leaders
35	zealanders - dictatorship - nukunonu - vaccination - mandatory	27	35_zealanders_dictatorship_nukunonu_vaccination
36	stillbirths - vaers - pfizer - ivf - preterm	27	36_stillbirths_vaers_pfizer_ivf
37	liar - sycophants - idiots - definition - arrogant	27	37_liar_sycophants_idiots_definition
38	david - icke - videocast - hoax - connector	27	38_david_icke_videocast_hoax
39	protestors - eco - spray - silverstone - blockading	26	39_protestors_eco_spray_silverstone
40	5g - radiofrequency - towers - verizon - harmful	25	40_5g_radiofrequency_towers_verizon
41	belfast - luton - david - middlesbrough - tickets	24	41_belfast_luton_david_middlesbrough
42	universities - decolonisation - warwick - woke - wrongs	23	42_universities_decolonisation_warwick_woke
43	audiobook - dream - david - revelations - available	22	43_audiobook_dream_david_revelations
44	mortalities - britain - overestimate - april - heatwaves	22	44_mortalities_britain_overestimate_april
45	transsexual - detransitioned - hysterectomy - mutilated - testosterone	22	45_transsexual_detransitioned_hysterectomy_mutilated
46	china - falun - lockdowns - typhoon - genocide	22	46_china_falun_lockdowns_typhoon
47	offshore - turbines - whales - endangered - governors	22	47_offshore_turbines_whales_endangered
48	vaxxers - nurses - understaffed - mandatory - javid	21	48_vaxxers_nurses_understaffed_mandatory

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