Add BERTopic model

9fa0a8f verified about 1 year ago

7.96 kB


	---
	tags:
	- bertopic
	library_name: bertopic
	pipeline_tag: text-classification
	---

	# MARTINI_enrich_BERTopic_node_of_time_en

	This is a [BERTopic](https://github.com/MaartenGr/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:

	```python
	from bertopic import BERTopic
	topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_node_of_time_en")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 58
	* Number of training documents: 6346

	<details>
	<summary>Click here for an overview of all topics.</summary>

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| zelensky - russians - kherson - sanctions - missiles \| 20 \| -1_zelensky_russians_kherson_sanctions \|
	\| 0 \| taiwan - pyongyang - beijing - mao - geopolitical \| 3255 \| 0_taiwan_pyongyang_beijing_mao \|
	\| 1 \| tbilisi - homosexuality - uganda - pope - parade \| 168 \| 1_tbilisi_homosexuality_uganda_pope \|
	\| 2 \| hamas - gaza - israelis - hezbollah - airstrikes \| 167 \| 2_hamas_gaza_israelis_hezbollah \|
	\| 3 \| gabon - niamey - algeria - overthrow - gaddafi \| 165 \| 3_gabon_niamey_algeria_overthrow \|
	\| 4 \| hungary - juncker - slovak - european - sanctions \| 128 \| 4_hungary_juncker_slovak_european \|
	\| 5 \| nato - stoltenberg - baltics - kaliningrad - kosovars \| 116 \| 5_nato_stoltenberg_baltics_kaliningrad \|
	\| 6 \| nazis - zelenska - russians - suvorov - swastika \| 111 \| 6_nazis_zelenska_russians_suvorov \|
	\| 7 \| poland - kaczynski - ukrainianisation - zbigniew - zloty \| 107 \| 7_poland_kaczynski_ukrainianisation_zbigniew \|
	\| 8 \| bundeswehr - rheinmetall - panzer - merkava - veto \| 104 \| 8_bundeswehr_rheinmetall_panzer_merkava \|
	\| 9 \| zelensky - volodymyr - oligarchs - scandal - oscar \| 84 \| 9_zelensky_volodymyr_oligarchs_scandal \|
	\| 10 \| grain - bulgaria - wto - maersk - cavusoglu \| 82 \| 10_grain_bulgaria_wto_maersk \|
	\| 11 \| scholz - putin - russischen - zeitung - moldova \| 76 \| 11_scholz_putin_russischen_zeitung \|
	\| 12 \| mercenaries - severodonetsk - killed - kapuscinski - navy \| 69 \| 12_mercenaries_severodonetsk_killed_kapuscinski \|
	\| 13 \| putin - lugansk - россии - mobilization - motherland \| 57 \| 13_putin_lugansk_россии_mobilization \|
	\| 14 \| hamas - protests - pogroms - kristallnacht - denmark \| 56 \| 14_hamas_protests_pogroms_kristallnacht \|
	\| 15 \| bundestag - nsdap - saxony - scholz - wagenknecht \| 54 \| 15_bundestag_nsdap_saxony_scholz \|
	\| 16 \| riots - nantes - zemmour - macron - burgerkriegs \| 54 \| 16_riots_nantes_zemmour_macron \|
	\| 17 \| volunteers - subscribe - putinists - subtitling - volkov \| 52 \| 17_volunteers_subscribe_putinists_subtitling \|
	\| 18 \| донбасс - петровскии - памятника - kuybyshevsky - ekaterina \| 52 \| 18_донбасс_петровскии_памятника_kuybyshevsky \|
	\| 19 \| ukrainians - casualties - artemovsk - brigade - servicemen \| 52 \| 19_ukrainians_casualties_artemovsk_brigade \|
	\| 20 \| donetsk - counterattacks - karmazynivka - highlights - july \| 52 \| 20_donetsk_counterattacks_karmazynivka_highlights \|
	\| 21 \| pfizer - unvaccinated - ivermectin - injected - lockdowns \| 50 \| 21_pfizer_unvaccinated_ivermectin_injected \|
	\| 22 \| ukrainehumanrightsabuses - conscripted - prisoners - azovstal - sergeevich \| 50 \| 22_ukrainehumanrightsabuses_conscripted_prisoners_azovstal \|
	\| 23 \| biden - impeachment - giuliani - bribes - mccarthy \| 49 \| 23_biden_impeachment_giuliani_bribes \|
	\| 24 \| munitions - missiles - pentagon - supplies - billion \| 48 \| 24_munitions_missiles_pentagon_supplies \|
	\| 25 \| crimea - peace - chomsky - negotiated - counteroffensive \| 46 \| 25_crimea_peace_chomsky_negotiated \|
	\| 26 \| kakhovka - dnieper - ukrenergo - hydropower - blackout \| 45 \| 26_kakhovka_dnieper_ukrenergo_hydropower \|
	\| 27 \| ukrainians - refugees - poland - slovak - eurostat \| 44 \| 27_ukrainians_refugees_poland_slovak \|
	\| 28 \| zaporizhzhia - chernobyl - radioactive - npp - novosti \| 43 \| 28_zaporizhzhia_chernobyl_radioactive_npp \|
	\| 29 \| kremlin - zelenskiy - volodymyr - kherson - updates \| 43 \| 29_kremlin_zelenskiy_volodymyr_kherson \|
	\| 30 \| nordstream - sweden - sabotage - explosions - terrorist \| 43 \| 30_nordstream_sweden_sabotage_explosions \|
	\| 31 \| pravoslavie - sviatohirsk - chernivtsi - persecution - hieromonk \| 42 \| 31_pravoslavie_sviatohirsk_chernivtsi_persecution \|
	\| 32 \| germany - protests - hannover - nagorno - bundeskanzleramt \| 41 \| 32_germany_protests_hannover_nagorno \|
	\| 33 \| brics - nigeria - bangladesh - arabia - mnangagwa \| 40 \| 33_brics_nigeria_bangladesh_arabia \|
	\| 34 \| globalists - interglacial - co2 - twitterigtruth - klaus \| 40 \| 34_globalists_interglacial_co2_twitterigtruth \|
	\| 35 \| germany - gdp - recession - eurozone - 2023 \| 37 \| 35_germany_gdp_recession_eurozone \|
	\| 36 \| prigozhin - lukashenko - yevkurov - propagandists - gunship \| 36 \| 36_prigozhin_lukashenko_yevkurov_propagandists \|
	\| 37 \| congressmen - 24bn - spending - pentagon - israel \| 36 \| 37_congressmen_24bn_spending_pentagon \|
	\| 38 \| crude - sanctions - bloomberg - tankers - ulyanov \| 36 \| 38_crude_sanctions_bloomberg_tankers \|
	\| 39 \| conscription - verkhovna - chmelnyzkyj - commissars - marching \| 35 \| 39_conscription_verkhovna_chmelnyzkyj_commissars \|
	\| 40 \| donetsk - battles - paratroopers - april - shebekinsky \| 35 \| 40_donetsk_battles_paratroopers_april \|
	\| 41 \| nusra - aleppo - airstrikes - afghanistan - milley \| 33 \| 41_nusra_aleppo_airstrikes_afghanistan \|
	\| 42 \| nato - finland - erdogan - ratification - join \| 32 \| 42_nato_finland_erdogan_ratification \|
	\| 43 \| wikileaks - espionage - agencies - langley - naryshkin \| 32 \| 43_wikileaks_espionage_agencies_langley \|
	\| 44 \| eurofighter - kampfflugzeuge - zelenski - gripen - slovakia \| 32 \| 44_eurofighter_kampfflugzeuge_zelenski_gripen \|
	\| 45 \| missiles - kremenchug - slaviansk - casualties - airbase \| 29 \| 45_missiles_kremenchug_slaviansk_casualties \|
	\| 46 \| submunitions - cambodia - thermobaric - clusters - explode \| 29 \| 46_submunitions_cambodia_thermobaric_clusters \|
	\| 47 \| dollarization - yuan - brics - sanctions - bashar \| 29 \| 47_dollarization_yuan_brics_sanctions \|
	\| 48 \| westphalia - renewable - siemens - heaters - 190bn \| 28 \| 48_westphalia_renewable_siemens_heaters \|
	\| 49 \| sanctions - eu - blacklist - prohibit - belarusian \| 25 \| 49_sanctions_eu_blacklist_prohibit \|
	\| 50 \| novorossiya - pereyaslav - podoljak - passportizing - criminalise \| 25 \| 50_novorossiya_pereyaslav_podoljak_passportizing \|
	\| 51 \| smuggled - howitzers - marchenko - terrorists - promoboronexport \| 24 \| 51_smuggled_howitzers_marchenko_terrorists \|
	\| 52 \| uranium - khmelnitsky - munitions - depleted - fallujah \| 22 \| 52_uranium_khmelnitsky_munitions_depleted \|
	\| 53 \| bundestag - schuldenbremse - wirtschaftswoche - spendings - 17bn \| 22 \| 53_bundestag_schuldenbremse_wirtschaftswoche_spendings \|
	\| 54 \| transnistria - moldovatransgaz - chisinau - moldovan - romanianization \| 22 \| 54_transnistria_moldovatransgaz_chisinau_moldovan \|
	\| 55 \| bryansk - novotroitsk - terrorists - golovanov - fsb \| 21 \| 55_bryansk_novotroitsk_terrorists_golovanov \|
	\| 56 \| gazprom - euros - diesel - exports - ammonia \| 21 \| 56_gazprom_euros_diesel_exports \|

	</details>

	## 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


	---
	tags:
	- bertopic
	library_name: bertopic
	pipeline_tag: text-classification
	---

	# MARTINI_enrich_BERTopic_node_of_time_en

	This is a [BERTopic](https://github.com/MaartenGr/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:

	```python
	from bertopic import BERTopic
	topic_model = BERTopic.load("AIDA-UPM/MARTINI_enrich_BERTopic_node_of_time_en")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 58
	* Number of training documents: 6346

	<details>
	<summary>Click here for an overview of all topics.</summary>

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| zelensky - russians - kherson - sanctions - missiles \| 20 \| -1_zelensky_russians_kherson_sanctions \|
	\| 0 \| taiwan - pyongyang - beijing - mao - geopolitical \| 3255 \| 0_taiwan_pyongyang_beijing_mao \|
	\| 1 \| tbilisi - homosexuality - uganda - pope - parade \| 168 \| 1_tbilisi_homosexuality_uganda_pope \|
	\| 2 \| hamas - gaza - israelis - hezbollah - airstrikes \| 167 \| 2_hamas_gaza_israelis_hezbollah \|
	\| 3 \| gabon - niamey - algeria - overthrow - gaddafi \| 165 \| 3_gabon_niamey_algeria_overthrow \|
	\| 4 \| hungary - juncker - slovak - european - sanctions \| 128 \| 4_hungary_juncker_slovak_european \|
	\| 5 \| nato - stoltenberg - baltics - kaliningrad - kosovars \| 116 \| 5_nato_stoltenberg_baltics_kaliningrad \|
	\| 6 \| nazis - zelenska - russians - suvorov - swastika \| 111 \| 6_nazis_zelenska_russians_suvorov \|
	\| 7 \| poland - kaczynski - ukrainianisation - zbigniew - zloty \| 107 \| 7_poland_kaczynski_ukrainianisation_zbigniew \|
	\| 8 \| bundeswehr - rheinmetall - panzer - merkava - veto \| 104 \| 8_bundeswehr_rheinmetall_panzer_merkava \|
	\| 9 \| zelensky - volodymyr - oligarchs - scandal - oscar \| 84 \| 9_zelensky_volodymyr_oligarchs_scandal \|
	\| 10 \| grain - bulgaria - wto - maersk - cavusoglu \| 82 \| 10_grain_bulgaria_wto_maersk \|
	\| 11 \| scholz - putin - russischen - zeitung - moldova \| 76 \| 11_scholz_putin_russischen_zeitung \|
	\| 12 \| mercenaries - severodonetsk - killed - kapuscinski - navy \| 69 \| 12_mercenaries_severodonetsk_killed_kapuscinski \|
	\| 13 \| putin - lugansk - россии - mobilization - motherland \| 57 \| 13_putin_lugansk_россии_mobilization \|
	\| 14 \| hamas - protests - pogroms - kristallnacht - denmark \| 56 \| 14_hamas_protests_pogroms_kristallnacht \|
	\| 15 \| bundestag - nsdap - saxony - scholz - wagenknecht \| 54 \| 15_bundestag_nsdap_saxony_scholz \|
	\| 16 \| riots - nantes - zemmour - macron - burgerkriegs \| 54 \| 16_riots_nantes_zemmour_macron \|
	\| 17 \| volunteers - subscribe - putinists - subtitling - volkov \| 52 \| 17_volunteers_subscribe_putinists_subtitling \|
	\| 18 \| донбасс - петровскии - памятника - kuybyshevsky - ekaterina \| 52 \| 18_донбасс_петровскии_памятника_kuybyshevsky \|
	\| 19 \| ukrainians - casualties - artemovsk - brigade - servicemen \| 52 \| 19_ukrainians_casualties_artemovsk_brigade \|
	\| 20 \| donetsk - counterattacks - karmazynivka - highlights - july \| 52 \| 20_donetsk_counterattacks_karmazynivka_highlights \|
	\| 21 \| pfizer - unvaccinated - ivermectin - injected - lockdowns \| 50 \| 21_pfizer_unvaccinated_ivermectin_injected \|
	\| 22 \| ukrainehumanrightsabuses - conscripted - prisoners - azovstal - sergeevich \| 50 \| 22_ukrainehumanrightsabuses_conscripted_prisoners_azovstal \|
	\| 23 \| biden - impeachment - giuliani - bribes - mccarthy \| 49 \| 23_biden_impeachment_giuliani_bribes \|
	\| 24 \| munitions - missiles - pentagon - supplies - billion \| 48 \| 24_munitions_missiles_pentagon_supplies \|
	\| 25 \| crimea - peace - chomsky - negotiated - counteroffensive \| 46 \| 25_crimea_peace_chomsky_negotiated \|
	\| 26 \| kakhovka - dnieper - ukrenergo - hydropower - blackout \| 45 \| 26_kakhovka_dnieper_ukrenergo_hydropower \|
	\| 27 \| ukrainians - refugees - poland - slovak - eurostat \| 44 \| 27_ukrainians_refugees_poland_slovak \|
	\| 28 \| zaporizhzhia - chernobyl - radioactive - npp - novosti \| 43 \| 28_zaporizhzhia_chernobyl_radioactive_npp \|
	\| 29 \| kremlin - zelenskiy - volodymyr - kherson - updates \| 43 \| 29_kremlin_zelenskiy_volodymyr_kherson \|
	\| 30 \| nordstream - sweden - sabotage - explosions - terrorist \| 43 \| 30_nordstream_sweden_sabotage_explosions \|
	\| 31 \| pravoslavie - sviatohirsk - chernivtsi - persecution - hieromonk \| 42 \| 31_pravoslavie_sviatohirsk_chernivtsi_persecution \|
	\| 32 \| germany - protests - hannover - nagorno - bundeskanzleramt \| 41 \| 32_germany_protests_hannover_nagorno \|
	\| 33 \| brics - nigeria - bangladesh - arabia - mnangagwa \| 40 \| 33_brics_nigeria_bangladesh_arabia \|
	\| 34 \| globalists - interglacial - co2 - twitterigtruth - klaus \| 40 \| 34_globalists_interglacial_co2_twitterigtruth \|
	\| 35 \| germany - gdp - recession - eurozone - 2023 \| 37 \| 35_germany_gdp_recession_eurozone \|
	\| 36 \| prigozhin - lukashenko - yevkurov - propagandists - gunship \| 36 \| 36_prigozhin_lukashenko_yevkurov_propagandists \|
	\| 37 \| congressmen - 24bn - spending - pentagon - israel \| 36 \| 37_congressmen_24bn_spending_pentagon \|
	\| 38 \| crude - sanctions - bloomberg - tankers - ulyanov \| 36 \| 38_crude_sanctions_bloomberg_tankers \|
	\| 39 \| conscription - verkhovna - chmelnyzkyj - commissars - marching \| 35 \| 39_conscription_verkhovna_chmelnyzkyj_commissars \|
	\| 40 \| donetsk - battles - paratroopers - april - shebekinsky \| 35 \| 40_donetsk_battles_paratroopers_april \|
	\| 41 \| nusra - aleppo - airstrikes - afghanistan - milley \| 33 \| 41_nusra_aleppo_airstrikes_afghanistan \|
	\| 42 \| nato - finland - erdogan - ratification - join \| 32 \| 42_nato_finland_erdogan_ratification \|
	\| 43 \| wikileaks - espionage - agencies - langley - naryshkin \| 32 \| 43_wikileaks_espionage_agencies_langley \|
	\| 44 \| eurofighter - kampfflugzeuge - zelenski - gripen - slovakia \| 32 \| 44_eurofighter_kampfflugzeuge_zelenski_gripen \|
	\| 45 \| missiles - kremenchug - slaviansk - casualties - airbase \| 29 \| 45_missiles_kremenchug_slaviansk_casualties \|
	\| 46 \| submunitions - cambodia - thermobaric - clusters - explode \| 29 \| 46_submunitions_cambodia_thermobaric_clusters \|
	\| 47 \| dollarization - yuan - brics - sanctions - bashar \| 29 \| 47_dollarization_yuan_brics_sanctions \|
	\| 48 \| westphalia - renewable - siemens - heaters - 190bn \| 28 \| 48_westphalia_renewable_siemens_heaters \|
	\| 49 \| sanctions - eu - blacklist - prohibit - belarusian \| 25 \| 49_sanctions_eu_blacklist_prohibit \|
	\| 50 \| novorossiya - pereyaslav - podoljak - passportizing - criminalise \| 25 \| 50_novorossiya_pereyaslav_podoljak_passportizing \|
	\| 51 \| smuggled - howitzers - marchenko - terrorists - promoboronexport \| 24 \| 51_smuggled_howitzers_marchenko_terrorists \|
	\| 52 \| uranium - khmelnitsky - munitions - depleted - fallujah \| 22 \| 52_uranium_khmelnitsky_munitions_depleted \|
	\| 53 \| bundestag - schuldenbremse - wirtschaftswoche - spendings - 17bn \| 22 \| 53_bundestag_schuldenbremse_wirtschaftswoche_spendings \|
	\| 54 \| transnistria - moldovatransgaz - chisinau - moldovan - romanianization \| 22 \| 54_transnistria_moldovatransgaz_chisinau_moldovan \|
	\| 55 \| bryansk - novotroitsk - terrorists - golovanov - fsb \| 21 \| 55_bryansk_novotroitsk_terrorists_golovanov \|
	\| 56 \| gazprom - euros - diesel - exports - ammonia \| 21 \| 56_gazprom_euros_diesel_exports \|

	</details>

	## 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