MARTINI_enrich_BERTopic_KanekoaTheGreat

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_KanekoaTheGreat")

topic_model.get_topic_info()

Topic overview

• Number of topics: 44
• Number of training documents: 4753

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	vaccine - fbi - ukraine - 2021 - deaths	20	-1_vaccine_fbi_ukraine_2021
0	fauci - coronaviruses - bioweapons - darpa - conspiracy	2607	0_fauci_coronaviruses_bioweapons_darpa
1	maricopa - ballots - auditors - senator - verify	180	1_maricopa_ballots_auditors_senator
2	hackable - voting - cybersecurity - tabulators - malware	176	2_hackable_voting_cybersecurity_tabulators
3	twitter - musk - taibbi - disinformation - censor	134	3_twitter_musk_taibbi_disinformation
4	ballots - georgia - traffickers - nationwide - raffensperger	122	4_ballots_georgia_traffickers_nationwide
5	hongzhengtech - guojun - jinhua - huawei - unicom	109	5_hongzhengtech_guojun_jinhua_huawei
6	trump - doj - clinton - indictments - declassified	97	6_trump_doj_clinton_indictments
7	ivermectin - paxlovid - hydroxychloroquine - myfreedoctor - doxycycline	78	7_ivermectin_paxlovid_hydroxychloroquine_myfreedoctor
8	covidvaccinevictims - adverse - miscarriages - doses - pericarditis	65	8_covidvaccinevictims_adverse_miscarriages_doses
9	fbi - conspirators - kidnapping - tucker - whitmer	64	9_fbi_conspirators_kidnapping_tucker
10	ballots - georgia - falsified - scanned - raffensperger	64	10_ballots_georgia_falsified_scanned
11	biden - impeachment - laundering - bribe - whistleblowers	59	11_biden_impeachment_laundering_bribe
12	bidenlaptopemails - marcopolousa - investigator - allegedly - subpoena	56	12_bidenlaptopemails_marcopolousa_investigator_allegedly
13	toxicologist - phosgene - spill - norfolk - cheremisinoff	53	13_toxicologist_phosgene_spill_norfolk
14	pfizer - vaccinators - physicians - reformulated - dtox	45	14_pfizer_vaccinators_physicians_reformulated
15	bidens - china - bribing - jianming - rosneft	45	15_bidens_china_bribing_jianming
16	subscribing - truthsocial - empower - newsbecker - tracybeanz	42	16_subscribing_truthsocial_empower_newsbecker
17	epstein - ghislaine - billionaire - clinton - conspirators	40	17_epstein_ghislaine_billionaire_clinton
18	deportations - billion - sinaloa - taxpayers - adams	40	18_deportations_billion_sinaloa_taxpayers
19	dlive - lindell - shoutout - patriots - jarrin	39	19_dlive_lindell_shoutout_patriots
20	vaccinated - hospitalizations - delta - gallup - 2021	38	20_vaccinated_hospitalizations_delta_gallup
21	trudeau - ottawalks - nazi - protesters - convoy	32	21_trudeau_ottawalks_nazi_protesters
22	blinken - wikileaks - benghazi - disinformation - spycraft	31	22_blinken_wikileaks_benghazi_disinformation
23	halemaumau - hawaii - kilauea - firefighters - hurricane	30	23_halemaumau_hawaii_kilauea_firefighters
24	brics - saudia - sanctions - dollarization - rubles	29	24_brics_saudia_sanctions_dollarization
25	vaccine - mrna - nucleocapsid - adenovirus - encephalitis	29	25_vaccine_mrna_nucleocapsid_adenovirus
26	crimea - mearsheimer - nukes - russians - allies	29	26_crimea_mearsheimer_nukes_russians
27	lockdowns - epidemiology - stanford - ioannidis - scientists	29	27_lockdowns_epidemiology_stanford_ioannidis
28	australians - lockdown - protests - vaccinpass - palaszczuk	28	28_australians_lockdown_protests_vaccinpass
29	nordstream - blinken - sabotaged - snowden - blow	28	29_nordstream_blinken_sabotaged_snowden
30	inflation - yellen - trillions - 2022 - eurozone	27	30_inflation_yellen_trillions_2022
31	vaccinations - worldcouncilforhealth - mrna - june - inject	27	31_vaccinations_worldcouncilforhealth_mrna_june
32	drones - ufo - landings - chandrayaan - pentagon	27	32_drones_ufo_landings_chandrayaan
33	yanukovych - usaid - overthrow - mccain - cyberwarfare	26	33_yanukovych_usaid_overthrow_mccain
34	superintelligence - chatgpt - microsoft - optimus - profit	26	34_superintelligence_chatgpt_microsoft_optimus
35	pichai - duckduckgo - youtube - censorship - newsfeed	25	35_pichai_duckduckgo_youtube_censorship
36	vaccinated - iceland - lockdowns - malta - passports	25	36_vaccinated_iceland_lockdowns_malta
37	afghanistan - benghazi - sniper - senators - withdrew	23	37_afghanistan_benghazi_sniper_senators
38	pandemics - gates - biontech - countermeasures - governance	23	38_pandemics_gates_biontech_countermeasures
39	mandates - vaccine - unconstitutional - ny - uncoverdc	23	39_mandates_vaccine_unconstitutional_ny
40	mccullough - doctor - baylor - mrna - cardiorenal	22	40_mccullough_doctor_baylor_mrna
41	cbdc - decentralized - cryptocurrencies - cashless - lagarde	21	41_cbdc_decentralized_cryptocurrencies_cashless
42	pcr - false - tested - threshold - contagiousness	20	42_pcr_false_tested_threshold

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