MARTINI_enrich_BERTopic_CIG_telegram

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_CIG_telegram")

topic_model.get_topic_info()

Topic overview

• Number of topics: 182
• Number of training documents: 24109

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	russia - syria - afghanistan - hamas - migrants	20	-1_russia_syria_afghanistan_hamas
0	transnistria - moldavian - wallachia - mircea - craiova	14294	0_transnistria_moldavian_wallachia_mircea
1	burkina - niamey - mauritania - sahelian - abuja	237	1_burkina_niamey_mauritania_sahelian
2	spacex - cosmonauts - spacewalk - liftoff - satellites	232	2_spacex_cosmonauts_spacewalk_liftoff
3	trudeau - ottawa - alberta - multiculturalism - quebecois	215	3_trudeau_ottawa_alberta_multiculturalism
4	fed - recessions - inflation - deficit - depositors	198	4_fed_recessions_inflation_deficit
5	hezbollah - quneitra - baalbek - missiles - merkava	163	5_hezbollah_quneitra_baalbek_missiles
6	rioters - minnehaha - arrests - aurorailpolice - looted	155	6_rioters_minnehaha_arrests_aurorailpolice
7	bielorrusia - mogilev - лукашенко - mobilized - kalashnikov	136	7_bielorrusia_mogilev_лукашенко_mobilized
8	hamas - brigades - ashkelon - mujahideen - zaytoun	125	8_hamas_brigades_ashkelon_mujahideen
9	hungary - brussels - euros - veto - 50bn	116	9_hungary_brussels_euros_veto
10	guyana - venezuelan - essequibo - suriname - exxonmobil	110	10_guyana_venezuelan_essequibo_suriname
11	bolsonaro - rondonopolis - janeiro - moraes - alvorada	109	11_bolsonaro_rondonopolis_janeiro_moraes
12	taiwan - spratly - fujian - invade - warships	108	12_taiwan_spratly_fujian_invade
13	imran - peshawar - faisalabad - abottabad - shahbaz	107	13_imran_peshawar_faisalabad_abottabad
14	gaza - mossad - sinai - egyptians - jordanian	106	14_gaza_mossad_sinai_egyptians
15	iraqi - airstrikes - assad - nasiriyah - nineveh	105	15_iraqi_airstrikes_assad_nasiriyah
16	shipyards - warships - tankers - pacific - destroyer	104	16_shipyards_warships_tankers_pacific
17	donetsk - putin - khoroshilov - ratification - zyuganov	103	17_donetsk_putin_khoroshilov_ratification
18	qamishli - syria - dabiq - sharqiya - militias	103	18_qamishli_syria_dabiq_sharqiya
19	texas - border - governors - mcallen - militarize	101	19_texas_border_governors_mcallen
20	telegram - groupchats - banned - extremists - stopdittatura	100	20_telegram_groupchats_banned_extremists
21	afrikaners - johannesburg - mandela - kwazulu - rhodesia	99	21_afrikaners_johannesburg_mandela_kwazulu
22	fbi - bannon - indicted - subpoena - mugshots	95	22_fbi_bannon_indicted_subpoena
23	shoigu - lukashenka - mogilev - petersburg - rebellion	95	23_shoigu_lukashenka_mogilev_petersburg
24	demographic - births - ivf - slovakia - secularization	95	24_demographic_births_ivf_slovakia
25	hezbollah - israeli - yoav - ironclad - retaliate	94	25_hezbollah_israeli_yoav_ironclad
26	lithium - bolivia - eurometaux - mines - cobalt	89	26_lithium_bolivia_eurometaux_mines
27	netanyahu - בנימין - gideon - i24news - bennett	88	27_netanyahu_בנימין_gideon_i24news
28	pope - mothers - holy - fatima - rosary	83	28_pope_mothers_holy_fatima
29	khartoum - sudanesa - insurrectionists - junta - rrf	82	29_khartoum_sudanesa_insurrectionists_junta
30	serbia - kosovska - mitrovica - pristina - albanians	82	30_serbia_kosovska_mitrovica_pristina
31	howitzers - rheinmetall - ampv - m10 - hyundai	80	31_howitzers_rheinmetall_ampv_m10
32	tweets - musk - dorsey - qanon - shadowbanned	80	32_tweets_musk_dorsey_qanon
33	sinaloa - tamaulipas - mexicali - guanajuato - pemex	80	33_sinaloa_tamaulipas_mexicali_guanajuato
34	netanyahu - gaza - עמית - mahmoud - overthrow	79	34_netanyahu_gaza_עמית_mahmoud
35	gendarmerie - algerians - riots - zemmour - montpellier	79	35_gendarmerie_algerians_riots_zemmour
36	karabakh - stepanakert - армении - азербаиджаном - pashinyan	78	36_karabakh_stepanakert_армении_азербаиджаном
37	hongkongers - sanctions - xinhua - hkfp - pompeo	76	37_hongkongers_sanctions_xinhua_hkfp
38	tankers - suez - maersk - mandeb - yemen	76	38_tankers_suez_maersk_mandeb
39	mitsotakis - cyprus - syriza - thessaloniki - aegean	75	39_mitsotakis_cyprus_syriza_thessaloniki
40	hezbollah - halevi - אדי - najib - truce	75	40_hezbollah_halevi_אדי_najib
41	capitol - insurrection - trumpist - mccarthy - boomhauer	75	41_capitol_insurrection_trumpist_mccarthy
42	ecuador - presidente - emergencias - narcoterrorist - embassy	73	42_ecuador_presidente_emergencias_narcoterrorist
43	sadrists - baghdad - maliki - badr - السيد	72	43_sadrists_baghdad_maliki_badr
44	ukraine - munitions - stockpiles - pentagon - supplied	70	44_ukraine_munitions_stockpiles_pentagon
45	beheading - bastille - terrorist - algerian - mohammed	70	45_beheading_bastille_terrorist_algerian
46	europride - romania - legalised - homosexual - mitsotakis	66	46_europride_romania_legalised_homosexual
47	gazprom - europe - renewable - 100kwh - subsidies	66	47_gazprom_europe_renewable_100kwh
48	aipac - appropriations - congressmen - bipartisan - veto	65	48_aipac_appropriations_congressmen_bipartisan
49	ramallah - palestinians - israelis - judea - paramilitaries	65	49_ramallah_palestinians_israelis_judea
50	argentines - malvinas - dollarization - macri - presidential	64	50_argentines_malvinas_dollarization_macri
51	nato - stoltenberg - kyiv - allies - milley	64	51_nato_stoltenberg_kyiv_allies
52	sudan - embassies - evacuated - convoys - jeddah	63	52_sudan_embassies_evacuated_convoys
53	newsfeed - africa - subscribers - russie - memritv	63	53_newsfeed_africa_subscribers_russie
54	abortionists - scotus - unfpa - repealling - unconstitutional	62	54_abortionists_scotus_unfpa_repealling
55	spratly - palawan - luzon - navies - kiribati	61	55_spratly_palawan_luzon_navies
56	fentanyl - mexico - cartel - lopez - desantis	60	56_fentanyl_mexico_cartel_lopez
57	gaza - battalions - katif - remobilized - yehuda	60	57_gaza_battalions_katif_remobilized
58	kandahar - talibanes - afgano - faizabad - provinces	59	58_kandahar_talibanes_afgano_faizabad
59	chipmakers - taiwan - huawei - hisilicon - sanctions	58	59_chipmakers_taiwan_huawei_hisilicon
60	houthi - missiles - yemen - maersk - frigate	57	60_houthi_missiles_yemen_maersk
61	sanctions - blinken - beijing - eurasia - patrushev	57	61_sanctions_blinken_beijing_eurasia
62	gaza - לישראל - yoav - fallujahs - attacking	57	62_gaza_לישראל_yoav_fallujahs
63	iraqi - mujahideen - najaf - taqwa - hamidawi	56	63_iraqi_mujahideen_najaf_taqwa
64	mariupol - severodonetsk - lugansk - kharkov - zaporozhye	55	64_mariupol_severodonetsk_lugansk_kharkov
65	haitians - hispaniola - caricom - guterres - gang	55	65_haitians_hispaniola_caricom_guterres
66	antisemitism - desantis - congressman - amendment - ihra	55	66_antisemitism_desantis_congressman_amendment
67	sturmgeschutz - tanks - bulgarianmilitary - uralvagonzavod - volgograd	54	67_sturmgeschutz_tanks_bulgarianmilitary_uralvagonzavod
68	kremlin - ryabkov - sergey - военныи - novosti	53	68_kremlin_ryabkov_sergey_военныи
69	peru - ayacucho - bolivian - protests - impeached	52	69_peru_ayacucho_bolivian_protests
70	gunman - indianapolis - officers - injured - bodycam	50	70_gunman_indianapolis_officers_injured
71	erdogan - stoltenberg - scandinavia - alliances - terrorism	50	71_erdogan_stoltenberg_scandinavia_alliances
72	kiev - embassy - evacuating - dulles - flights	49	72_kiev_embassy_evacuating_dulles
73	taiwan - pelosi - beijing - lijian - annexing	49	73_taiwan_pelosi_beijing_lijian
74	lukashenko - minsk - radio - belsat - protesters	49	74_lukashenko_minsk_radio_belsat
75	somaliland - eritrea - mogadishu - ethiopian - hargeisa	49	75_somaliland_eritrea_mogadishu_ethiopian
76	italexit - europeelects - ipsos - syriza - lega	48	76_italexit_europeelects_ipsos_syriza
77	petroleum - refiners - reserves - brent - surge	47	77_petroleum_refiners_reserves_brent
78	erdogan - gaziantep - hurriyet - syrian - karkemish	47	78_erdogan_gaziantep_hurriyet_syrian
79	mariupol - mykolaivka - zaporizhzhia - donskoye - novoapostolovka	47	79_mariupol_mykolaivka_zaporizhzhia_donskoye
80	coronavirus - epidemic - quarantining - panicking - masks	46	80_coronavirus_epidemic_quarantining_panicking
81	migrants - border - brownsville - illegally - marshals	46	81_migrants_border_brownsville_illegally
82	yemen - naval - jihad - almighty - sabeen	46	82_yemen_naval_jihad_almighty
83	pyongyang - yonhap - yeonpyeong - kumgangsan - yoon	46	83_pyongyang_yonhap_yeonpyeong_kumgangsan
84	grain - famine - harvests - chornomorsk - rosselkhozbank	45	84_grain_famine_harvests_chornomorsk
85	commonwealthians - monarch - britain - balmoral - zealand	44	85_commonwealthians_monarch_britain_balmoral
86	belgorod - kursk - cossacks - shchetinovka - militiamen	44	86_belgorod_kursk_cossacks_shchetinovka
87	hagia - istanbul - mosque - kemalism - mehmed	44	87_hagia_istanbul_mosque_kemalism
88	tripoli - misrata - gaddafi - jamahiriya - abdelhamid	43	88_tripoli_misrata_gaddafi_jamahiriya
89	japan - demographic - urbanization - declining - koreans	43	89_japan_demographic_urbanization_declining
90	bukele - salvadorans - escobar - crackdown - soyapango	42	90_bukele_salvadorans_escobar_crackdown
91	patriotfront - pennsylvania - massachusetts - active - wyoming	42	91_patriotfront_pennsylvania_massachusetts_active
92	wahlkreisprognose - thuringia - extremists - afd - unelected	41	92_wahlkreisprognose_thuringia_extremists_afd
93	flightradar24 - makhachkala - pogromists - runways - planes	40	93_flightradar24_makhachkala_pogromists_runways
94	anzus - canberra - pacific - zealand - submarines	39	94_anzus_canberra_pacific_zealand
95	zelenskyy - volodymyr - kyiv - serhiy - verkhovna	39	95_zelenskyy_volodymyr_kyiv_serhiy
96	nugmyanmar - kachin - buthidaung - irrawaddy - mandarin	38	96_nugmyanmar_kachin_buthidaung_irrawaddy
97	beijing - weibo - jerusalem - aiib - alibaba	38	97_beijing_weibo_jerusalem_aiib
98	shinzo - hideki - wakayama - manchukuo - nhkニュース	38	98_shinzo_hideki_wakayama_manchukuo
99	chicago - police - alderman - looters - superintendent	38	99_chicago_police_alderman_looters
100	nuclear - reactors - terrapower - thorium - breakthroughs	38	100_nuclear_reactors_terrapower_thorium
101	putin - sanctions - invades - nbc - joe	38	101_putin_sanctions_invades_nbc
102	norad - aviationtracker - yukon - debris - altitude	36	102_norad_aviationtracker_yukon_debris
103	kashmir - manipur - bjp - hindus - islamist	36	103_kashmir_manipur_bjp_hindus
104	patriotfront - jefferson - rosseau - manifesto - founder	36	104_patriotfront_jefferson_rosseau_manifesto
105	mercenaries - libya - afrika - novichok - wladimir	36	105_mercenaries_libya_afrika_novichok
106	yemen - airstrikes - targets - tankertrackers - hajjah	36	106_yemen_airstrikes_targets_tankertrackers
107	antisemitism - rabbis - sharansky - megyn - mengele	36	107_antisemitism_rabbis_sharansky_megyn
108	riots - almaty - kazakh - attackers - novosti	35	108_riots_almaty_kazakh_attackers
109	riots - insurrectionist - antiterrorism - capitol - supremacy	35	109_riots_insurrectionist_antiterrorism_capitol
110	destroyers - squadrons - expeditionary - homeport - usninews	34	110_destroyers_squadrons_expeditionary_homeport
111	unsc - palestine - embargo - vetoed - unconditional	34	111_unsc_palestine_embargo_vetoed
112	venezuela - colombian - telemundo - cristobal - cocaine	34	112_venezuela_colombian_telemundo_cristobal
113	republicans - whites - racism - demographics - hispanic	34	113_republicans_whites_racism_demographics
114	israel - munitions - pentagon - supplied - m4a1	34	114_israel_munitions_pentagon_supplied
115	merkava - gaza - bulldozers - m109a5 - turrets	34	115_merkava_gaza_bulldozers_m109a5
116	missiles - isfahan - uavs - osintdefender - launched	34	116_missiles_isfahan_uavs_osintdefender
117	enlistments - regiments - rifleman - freikorps - sandhurst	34	117_enlistments_regiments_rifleman_freikorps
118	protesting - glaad - neofascist - satancon - perverted	33	118_protesting_glaad_neofascist_satancon
119	taliban - kabul - zabihullah - mujahid - burka	33	119_taliban_kabul_zabihullah_mujahid
120	transgenderists - california - minors - assemblywoman - teacher	32	120_transgenderists_california_minors_assemblywoman
121	antifa - rioters - portland - squatters - fargo	32	121_antifa_rioters_portland_squatters
122	bombers - squadron - lakenheath - stratotanker - airworthy	32	122_bombers_squadron_lakenheath_stratotanker
123	instincts - strives - man - hedonism - zarathustra	32	123_instincts_strives_man_hedonism
124	white - rallies - europeenne - нашеи - genocided	32	124_white_rallies_europeenne_нашеи
125	racist - whitey - conservatives - hypercivilization - shitposting	31	125_racist_whitey_conservatives_hypercivilization
126	gaza - airstrikes - awadallah - killed - younes	31	126_gaza_airstrikes_awadallah_killed
127	finland - nato - helsingin - raikkonen - gripen	31	127_finland_nato_helsingin_raikkonen
128	immigrants - population - netherlands - norwegians - overstayers	30	128_immigrants_population_netherlands_norwegians
129	georgia - antifa - атланта - arrested - противостояние	30	129_georgia_antifa_атланта_arrested
130	cavusoglu - israelis - istanbul - ambassadors - abdollahian	29	130_cavusoglu_israelis_istanbul_ambassadors
131	tanks - poland - leopard - marder - dk	29	131_tanks_poland_leopard_marder
132	balloonists - norad - airship - stratospheric - hovering	29	132_balloonists_norad_airship_stratospheric
133	doklam - thimphu - rajnath - индииских - пограничниках	29	133_doklam_thimphu_rajnath_индииских
134	gaza - hezbollah - airstrikes - ashkelon - update	28	134_gaza_hezbollah_airstrikes_ashkelon
135	kharkiv - zaporizhia - bohodukhiv - shevchenkove - sumy	28	135_kharkiv_zaporizhia_bohodukhiv_shevchenkove
136	styria - islamist - linz - attackers - antonskirche	28	136_styria_islamist_linz_attackers
137	marches - independence - proceeded - massachusetts - participation	28	137_marches_independence_proceeded_massachusetts
138	nordstream - explosions - pipes - sabotage - zakharova	28	138_nordstream_explosions_pipes_sabotage
139	erdogan - kemalists - albayrak - cyprus - islamophobia	28	139_erdogan_kemalists_albayrak_cyprus
140	kyrgyzstan - peacekeepers - kalashnikov - serdyukov - novosti	28	140_kyrgyzstan_peacekeepers_kalashnikov_serdyukov
141	hamas - rafah - aljazeera - truce - hostage	28	141_hamas_rafah_aljazeera_truce
142	schengen - migrants - eurodac - reform - deutschlandtrend	28	142_schengen_migrants_eurodac_reform
143	derailment - dioxins - hazardous - combusting - ohio	27	143_derailment_dioxins_hazardous_combusting
144	chileans - mapuche - pinochetists - guerrillas - lanalhue	27	144_chileans_mapuche_pinochetists_guerrillas
145	ghislaine - epstein - trafficked - lewinsky - conspirator	27	145_ghislaine_epstein_trafficked_lewinsky
146	suicides - marijuana - overdoses - alzheimers - decline	26	146_suicides_marijuana_overdoses_alzheimers
147	ukmto - mandeb - 0330utc - unauthorised - munitions	26	147_ukmto_mandeb_0330utc_unauthorised
148	bosniaks - herzegovina - sarajevo - srpska - separatism	26	148_bosniaks_herzegovina_sarajevo_srpska
149	whites - homicide - offenders - statistically - hispanics	26	149_whites_homicide_offenders_statistically
150	ranatunga - lanka - kurunegala - maldives - maheepala	25	150_ranatunga_lanka_kurunegala_maldives
151	imperialism - isolationism - geopoliticians - neoliberals - supranational	25	151_imperialism_isolationism_geopoliticians_neoliberals
152	tory - britain - reaganomics - sunak - eliminated	25	152_tory_britain_reaganomics_sunak
153	carlson - murdoch - tucker - bartiromo - viewership	25	153_carlson_murdoch_tucker_bartiromo
154	reindustrialization - deindustrailisation - globalisation - sweatshops - chipmakers	25	154_reindustrialization_deindustrailisation_globalisation_sweatshops
155	firearms - unconstitutional - albuquerque - governor - plaintiffs	25	155_firearms_unconstitutional_albuquerque_governor
156	donald - republicans - newsmax - sotu - nominee	24	156_donald_republicans_newsmax_sotu
157	itamar - yehuda - minister - גביר - natsecmin	24	157_itamar_yehuda_minister_גביר
158	draghi - gentiloni - eurosceptics - calabria - montecitorio	24	158_draghi_gentiloni_eurosceptics_calabria
159	saudi - jeddah - wahhabism - haaretz - abdulaziz	23	159_saudi_jeddah_wahhabism_haaretz
160	karabakh - nakhchivan - yerevan - tavush - transcaucasus	23	160_karabakh_nakhchivan_yerevan_tavush
161	warships - mandeb - map - operationing - 26dec2023	23	161_warships_mandeb_map_operationing
162	beirut - explosives - ammonium - shipment - shamass	23	162_beirut_explosives_ammonium_shipment
163	rosaviatsia - vnukovo - evgeny - crashed - plane	23	163_rosaviatsia_vnukovo_evgeny_crashed
164	fbi - counterintelligence - pompeo - mi5 - wenheng	23	164_fbi_counterintelligence_pompeo_mi5
165	saudi - jeddah - khashoggi - khaled - qatar	23	165_saudi_jeddah_khashoggi_khaled
166	openai - golem - kabbalists - intelligent - blenderbot	23	166_openai_golem_kabbalists_intelligent
167	libya - misrata - tobruk - abdelhamid - combatants	22	167_libya_misrata_tobruk_abdelhamid
168	ukraine - putin - invades - nbc - intelligence	22	168_ukraine_putin_invades_nbc
169	irishmen - fermanagh - nationalparty - clann - emigration	22	169_irishmen_fermanagh_nationalparty_clann
170	squatters - california - francisco - decriminalized - shoplifting	22	170_squatters_california_francisco_decriminalized
171	kenosha - rioters - militia - sheriff - august	21	171_kenosha_rioters_militia_sheriff
172	ruanda - kivu - congolese - tanganyika - peacekeepers	21	172_ruanda_kivu_congolese_tanganyika
173	migrants - smuggling - ngos - lesvos - firefighters	21	173_migrants_smuggling_ngos_lesvos
174	seaflooding - mangrove - ecosystems - co2 - phytoplankton	21	174_seaflooding_mangrove_ecosystems_co2
175	kanye - chappelle - tweeting - jews - obama	21	175_kanye_chappelle_tweeting_jews
176	impeachment - cicilline - congresswoman - invoke - 25th	21	176_impeachment_cicilline_congresswoman_invoke
177	makarov - carbines - militants - m16a4 - x39mm	21	177_makarov_carbines_militants_m16a4
178	luganskaya - severodonetsk - militia - villages - outflanked	21	178_luganskaya_severodonetsk_militia_villages
179	tiktokers - bytedance - banned - legislation - app	20	179_tiktokers_bytedance_banned_legislation
180	hurricane - landfall - thunderstorms - louisiana - subtropical	20	180_hurricane_landfall_thunderstorms_louisiana

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