MARTINI_enrich_BERTopic_zeeemedia

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_zeeemedia")

topic_model.get_topic_info()

Topic overview

• Number of topics: 77
• Number of training documents: 8285

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	vaccinated - australia - covid - everyone - pfizer	20	-1_vaccinated_australia_covid_everyone
0	warmongering - communism - trending - amnesty - oliver	4593	0_warmongering_communism_trending_amnesty
1	amendments - pandemic - ghebreyesus - intergovernmental - delegates	303	1_amendments_pandemic_ghebreyesus_intergovernmental
2	censorship - zuckerberg - tweet - google - suspended	141	2_censorship_zuckerberg_tweet_google
3	hamas - netanyahu - terrorists - atrocities - jerusalem	135	3_hamas_netanyahu_terrorists_atrocities
4	nanobots - hydrogel - mihalcea - injected - dna	128	4_nanobots_hydrogel_mihalcea_injected
5	nuremberg - mercola - livestream - viviane - lobotomies	116	5_nuremberg_mercola_livestream_viviane
6	vaccine - myocarditis - deaths - adverse - 2021	94	6_vaccine_myocarditis_deaths_adverse
7	wuhan - lockdown - zhengzhou - shandong - hainan	93	7_wuhan_lockdown_zhengzhou_shandong
8	lindell - ballots - ausvstheagenda - aboriginals - fraudulent	86	8_lindell_ballots_ausvstheagenda_aboriginals
9	vaxxers - brainwashed - uninjected - traumatised - freakin	83	9_vaxxers_brainwashed_uninjected_traumatised
10	senators - australian - skerritt - malcolm - crossbench	81	10_senators_australian_skerritt_malcolm
11	illuminati - un100 - sdg - technocratic - seraphim	76	11_illuminati_un100_sdg_technocratic
12	trudeau - protesters - manitoba - blockade - politicized	73	12_trudeau_protesters_manitoba_blockade
13	indicted - trump - fbi - clinton - conspirators	71	13_indicted_trump_fbi_clinton
14	metropolis - wollongong - smart - neighbourhoods - decentralisation	70	14_metropolis_wollongong_smart_neighbourhoods
15	weather - chemtrails - droughts - sandstorm - atmospheric	70	15_weather_chemtrails_droughts_sandstorm
16	live - tonight - believers - answering - chris	69	16_live_tonight_believers_answering
17	vaccine - booster - australians - fully - fortnight	68	17_vaccine_booster_australians_fully
18	fauci - bioweapons - declassified - cheney - origins	65	18_fauci_bioweapons_declassified_cheney
19	tomorrow - 7am - herehttps - alexander - invited	58	19_tomorrow_7am_herehttps_alexander
20	pornography - sexualising - pedophiles - perverted - tiktok	57	20_pornography_sexualising_pedophiles_perverted
21	monkeypox - superspreader - immunocompromised - imvanex - blistering	54	21_monkeypox_superspreader_immunocompromised_imvanex
22	omicron - subvariants - nsw - masks - mandating	52	22_omicron_subvariants_nsw_masks
23	ukraine - donetsk - shoigu - zelensky - kremlin	51	23_ukraine_donetsk_shoigu_zelensky
24	mygov - digitalise - australians - registers - revenue	51	24_mygov_digitalise_australians_registers
25	australia - militarising - taiwan - allies - pengyu	49	25_australia_militarising_taiwan_allies
26	seeds - prepping - uncensored - dehydrator - supplements	46	26_seeds_prepping_uncensored_dehydrator
27	died - causes - sudden - strokes - defibrillators	46	27_died_causes_sudden_strokes
28	zelenskyy - putin - vladimir - grozny - oscar	46	28_zelenskyy_putin_vladimir_grozny
29	zelenskyy - trillions - fund - taxpayers - pentagon	46	29_zelenskyy_trillions_fund_taxpayers
30	censorship - misinformation - australian - influencers - legislators	46	30_censorship_misinformation_australian_influencers
31	cyberattacks - russia - killnet - outages - nsa	44	31_cyberattacks_russia_killnet_outages
32	goldco - mariazeeeofficial_s - discount - melbourne - 1kg	43	32_goldco_mariazeeeofficial_s_discount_melbourne
33	maria - subcribe - livestreams - zerotime - bidenflation	38	33_maria_subcribe_livestreams_zerotime
34	chatgpt - ceo - xai - robots - mika	38	34_chatgpt_ceo_xai_robots
35	riots - macron - paris - algerian - olivier	36	35_riots_macron_paris_algerian
36	qld - hippocratic - parliament - unconstitutionally - signatories	36	36_qld_hippocratic_parliament_unconstitutionally
37	pfizer - injectable - mhra - eliquis - fatalities	36	37_pfizer_injectable_mhra_eliquis
38	biofield - injected - emitting - rf - scanners	35	38_biofield_injected_emitting_rf
39	channel - maria - bots - tolerables - befreewithdee	34	39_channel_maria_bots_tolerables
40	qld - vaccinated - skynews - premier - amanda	33	40_qld_vaccinated_skynews_premier
41	bankwest - debanking - cashless - withdrawals - closed	33	41_bankwest_debanking_cashless_withdrawals
42	hyperinflation - skyrocketing - rba - prices - argentina	33	42_hyperinflation_skyrocketing_rba_prices
43	bioterrorism - ukraine - pentagon - laboratories - kirillov	32	43_bioterrorism_ukraine_pentagon_laboratories
44	zeee - scammers - messages - maria - unsubscribe	30	44_zeee_scammers_messages_maria
45	australia - lockdowns - legalise - detainees - surveillance	30	45_australia_lockdowns_legalise_detainees
46	vaxxers - aflsolicitors - paralysed - victim - kerryn	30	46_vaxxers_aflsolicitors_paralysed_victim
47	pandemics - h5n1 - nipah - deadlier - redfield	29	47_pandemics_h5n1_nipah_deadlier
48	kerry - clinton - deniers - trillions - anthropogenic	28	48_kerry_clinton_deniers_trillions
49	ecb - euro - stablecoins - dollarisation - rbi	28	49_ecb_euro_stablecoins_dollarisation
50	transgender - rachael - woman - navy - councilman	27	50_transgender_rachael_woman_navy
51	norad - pentagon - airships - drone - detected	27	51_norad_pentagon_airships_drone
52	illegals - smuggling - cbp - impeachment - texas	27	52_illegals_smuggling_cbp_impeachment
53	teslas - motorists - emissions - diesel - volkswagen	27	53_teslas_motorists_emissions_diesel
54	unvaxxed - vaccinate - consent - schooling - covidshield	26	54_unvaxxed_vaccinate_consent_schooling
55	martin - recession - wwiii - terrorist - inevitable	26	55_martin_recession_wwiii_terrorist
56	outages - energiewende - generators - shutoff - germans	26	56_outages_energiewende_generators_shutoff
57	chancellor - rajapaksa - resigns - wickremesinghe - nittambuwa	26	57_chancellor_rajapaksa_resigns_wickremesinghe
58	ufos - mothership - pentagon - whistleblowers - unveiled	24	58_ufos_mothership_pentagon_whistleblowers
59	netherlands - gmo - branicevo - protesting - villages	24	59_netherlands_gmo_branicevo_protesting
60	biden - bidencrimes - investigations - breaching - laptop	24	60_biden_bidencrimes_investigations_breaching
61	bioweapon - karen - injections - poisoned - remotely	23	61_bioweapon_karen_injections_poisoned
62	tyson - mealworms - gmo - burgers - substitutes	23	62_tyson_mealworms_gmo_burgers
63	appealed - fedcourt - nswreg - livestream - awaiting	23	63_appealed_fedcourt_nswreg_livestream
64	survival - aussie - zeee - supplies - giveaway	22	64_survival_aussie_zeee_supplies
65	steaks - lamb - boneless - promo - december	22	65_steaks_lamb_boneless_promo
66	fdic - bailouts - depositors - snb - silvergate	21	66_fdic_bailouts_depositors_snb
67	australian - militarisation - barracks - correspondent - floods	21	67_australian_militarisation_barracks_correspondent
68	torture - canberra - protests - policemen - harrison	21	68_torture_canberra_protests_policemen
69	whistleblower - zealand - bail - barry - winston	21	69_whistleblower_zealand_bail_barry
70	bolsonaro - favelas - guilherme - janeiro - protesters	21	70_bolsonaro_favelas_guilherme_janeiro
71	fuels - emissions - coalition - worldwide - eliminate	20	71_fuels_emissions_coalition_worldwide
72	cyberattack - ransomware - optus - exposed - woolworths	20	72_cyberattack_ransomware_optus_exposed
73	uploading - sorry - maria - blocked - uncensored	20	73_uploading_sorry_maria_blocked
74	unemployed - ubi - transhumanism - slaves - factories	20	74_unemployed_ubi_transhumanism_slaves
75	biden - tucker - lol - remember - pentagon	20	75_biden_tucker_lol_remember

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