Add BERTopic model

3bf43ff verified 21 days ago

8.35 kB


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

	# MARTINI_enrich_BERTopic_DrPaulAlexander

	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_DrPaulAlexander")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 64
	* Number of training documents: 5766

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

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| unvaccinated - pfizer - lockdowns - injections - 2021 \| 20 \| -1_unvaccinated_pfizer_lockdowns_injections \|
	\| 0 \| tranny - females - penises - vaginoplasty - dysphoria \| 2790 \| 0_tranny_females_penises_vaginoplasty \|
	\| 1 \| fauci - deepstate - lockdowns - colluded - mengele \| 162 \| 1_fauci_deepstate_lockdowns_colluded \|
	\| 2 \| mrna - biontech - injections - malone - inventors \| 143 \| 2_mrna_biontech_injections_malone \|
	\| 3 \| pandemic - hoax - false - asymptomatic - never \| 125 \| 3_pandemic_hoax_false_asymptomatic \|
	\| 4 \| monkeypox - hiv - gay - gonorrhoea - marburg \| 124 \| 4_monkeypox_hiv_gay_gonorrhoea \|
	\| 5 \| zelensky - russia - volodymyr - missiles - kissinger \| 103 \| 5_zelensky_russia_volodymyr_missiles \|
	\| 6 \| peters - drs - interviews - bellavia - maldonado \| 89 \| 6_peters_drs_interviews_bellavia \|
	\| 7 \| myopericarditis - endomyocardial - vaccination - tamponade - mri \| 84 \| 7_myopericarditis_endomyocardial_vaccination_tamponade \|
	\| 8 \| pilots - cockpit - plane - boeing - crashed \| 77 \| 8_pilots_cockpit_plane_boeing \|
	\| 9 \| illegals - biden - invaded - jihadists - border \| 76 \| 9_illegals_biden_invaded_jihadists \|
	\| 10 \| vaccination - thromboembolic - autoantibodies - vasculitis - c19 \| 74 \| 10_vaccination_thromboembolic_autoantibodies_vasculitis \|
	\| 11 \| trudeau - vaccinal - njoo - truckers - sharma \| 69 \| 11_trudeau_vaccinal_njoo_truckers \|
	\| 12 \| remdesivir - midazolam - euthanasia - iatrogenic - ventilator \| 66 \| 12_remdesivir_midazolam_euthanasia_iatrogenic \|
	\| 13 \| coronaviruses - wuhan - chimeric - 2020 - wiv \| 66 \| 13_coronaviruses_wuhan_chimeric_2020 \|
	\| 14 \| died - sudden - year - 44 - vandaelle \| 63 \| 14_died_sudden_year_44 \|
	\| 15 \| naomi - innoculations - bannon - dailyclout - genocidal \| 60 \| 15_naomi_innoculations_bannon_dailyclout \|
	\| 16 \| islamists - wolf - bataclan - migrant - europe \| 58 \| 16_islamists_wolf_bataclan_migrant \|
	\| 17 \| subvariants - omicron - clade - ba5 - dominant \| 57 \| 17_subvariants_omicron_clade_ba5 \|
	\| 18 \| immunization - pfizer - sids - shots - harmful \| 57 \| 18_immunization_pfizer_sids_shots \|
	\| 19 \| shootings - officer - texas - dewitt - robbers \| 56 \| 19_shootings_officer_texas_dewitt \|
	\| 20 \| maloney - breggins - lawsuit - oppenheimer - jane \| 56 \| 20_maloney_breggins_lawsuit_oppenheimer \|
	\| 21 \| povidone - mouthwash - hypochlorite - nasal - ivermectin \| 53 \| 21_povidone_mouthwash_hypochlorite_nasal \|
	\| 22 \| sarcoma - leukemias - glioblastoma - oncologist - rapid \| 50 \| 22_sarcoma_leukemias_glioblastoma_oncologist \|
	\| 23 \| biden - republicans - mcconnell - teleprompter - midterms \| 49 \| 23_biden_republicans_mcconnell_teleprompter \|
	\| 24 \| masks - toxic - cochrane - ineffectiveness - microplastic \| 47 \| 24_masks_toxic_cochrane_ineffectiveness \|
	\| 25 \| deaths - vaccinated - eurostat - 2021 - kuhbandner \| 45 \| 25_deaths_vaccinated_eurostat_2021 \|
	\| 26 \| vaccinations - miscarriage - decidual - dysmenorrhea - diethylstilbestrol \| 43 \| 26_vaccinations_miscarriage_decidual_dysmenorrhea \|
	\| 27 \| fluorofentanyl - carfentanil - xylazine - naloxone - overdose \| 39 \| 27_fluorofentanyl_carfentanil_xylazine_naloxone \|
	\| 28 \| lockdowns - tiananmen - shanghai - xi - lunatic \| 39 \| 28_lockdowns_tiananmen_shanghai_xi \|
	\| 29 \| omicron - vaccination - booster - hansen - subvariants \| 37 \| 29_omicron_vaccination_booster_hansen \|
	\| 30 \| fbi - trump - raided - defund - politicized \| 37 \| 30_fbi_trump_raided_defund \|
	\| 31 \| antibodies - naturally - reinfection - documented - sars \| 36 \| 31_antibodies_naturally_reinfection_documented \|
	\| 32 \| harvard - plagiarized - claudine - zakaria - antisemite \| 34 \| 32_harvard_plagiarized_claudine_zakaria \|
	\| 33 \| vaccinated - omicron - prophylaxis - nigeria - deaths \| 34 \| 33_vaccinated_omicron_prophylaxis_nigeria \|
	\| 34 \| kennedy - kwiatkowski - prasad - mkultra - partisan \| 34 \| 34_kennedy_kwiatkowski_prasad_mkultra \|
	\| 35 \| pfizer - deathvax - defrauded - ombudsman - bla \| 34 \| 35_pfizer_deathvax_defrauded_ombudsman \|
	\| 36 \| bengals - myocarditis - cornerback - xfl - demarcus \| 33 \| 36_bengals_myocarditis_cornerback_xfl \|
	\| 37 \| djokovic - champion - mcenroe - kelce - superbowl \| 33 \| 37_djokovic_champion_mcenroe_kelce \|
	\| 38 \| nattokinase - detoxifier - spike - acetylcysteine - anticoagulant \| 32 \| 38_nattokinase_detoxifier_spike_acetylcysteine \|
	\| 39 \| vaers - adenovirus - adverse - astrazeneca - pneumoniae \| 29 \| 39_vaers_adenovirus_adverse_astrazeneca \|
	\| 40 \| mccullough - peter - investigator - cardiologist - tacit \| 28 \| 40_mccullough_peter_investigator_cardiologist \|
	\| 41 \| trump - reelected - maddow - politicized - ramaswamy \| 28 \| 41_trump_reelected_maddow_politicized \|
	\| 42 \| florida - surgeon - desantis - joe - walensky \| 27 \| 42_florida_surgeon_desantis_joe \|
	\| 43 \| horsemen - apocalpse - plague - 33 - horrendous \| 27 \| 43_horsemen_apocalpse_plague_33 \|
	\| 44 \| omicron - bivalent - ba5 - updated - 2023 \| 27 \| 44_omicron_bivalent_ba5_updated \|
	\| 45 \| hamas - israeli - yehuda - pogrom - invaders \| 27 \| 45_hamas_israeli_yehuda_pogrom \|
	\| 46 \| pedophiles - pope - scandalizing - corrupters - nuns \| 26 \| 46_pedophiles_pope_scandalizing_corrupters \|
	\| 47 \| remdesivir - hydroxychloroquine - tamiflu - zanamivir - pharmacovigilance \| 26 \| 47_remdesivir_hydroxychloroquine_tamiflu_zanamivir \|
	\| 48 \| inflation - biden - plummets - trillion - binance \| 25 \| 48_inflation_biden_plummets_trillion \|
	\| 49 \| nagase - coulson - everybody - malhotra - stacks \| 24 \| 49_nagase_coulson_everybody_malhotra \|
	\| 50 \| tribunals - hanged - jailed - punish - amnesty \| 24 \| 50_tribunals_hanged_jailed_punish \|
	\| 51 \| ottawa - james - tomb - marched - veteran \| 23 \| 51_ottawa_james_tomb_marched \|
	\| 52 \| fauci - virulent - evolve - injecting - chemoprophylaxis \| 23 \| 52_fauci_virulent_evolve_injecting \|
	\| 53 \| semaglutide - ozempic - insulin - hypoglycemia - pancreatitis \| 23 \| 53_semaglutide_ozempic_insulin_hypoglycemia \|
	\| 54 \| vaccinee - chemoprophylaxis - immunological - pediatricians - rennebohm \| 23 \| 54_vaccinee_chemoprophylaxis_immunological_pediatricians \|
	\| 55 \| sars - antigens - sequelae - persistent - exosomes \| 23 \| 55_sars_antigens_sequelae_persistent \|
	\| 56 \| twitter - musk - dorsey - zuckerberg - banned \| 23 \| 56_twitter_musk_dorsey_zuckerberg \|
	\| 57 \| liposome - exosomes - nanoparticles - lnp - lymphocytes \| 22 \| 57_liposome_exosomes_nanoparticles_lnp \|
	\| 58 \| amnesty - covidian - emma - wrongdoers - forgive \| 22 \| 58_amnesty_covidian_emma_wrongdoers \|
	\| 59 \| vaccinating - maternal - pfizer - pertussis - neonates \| 22 \| 59_vaccinating_maternal_pfizer_pertussis \|
	\| 60 \| endothelial - sars - sialylated - pathogenesis - hypercoagulation \| 20 \| 60_endothelial_sars_sialylated_pathogenesis \|
	\| 61 \| biden - indicted - bribery - impeach - ukraine \| 20 \| 61_biden_indicted_bribery_impeach \|
	\| 62 \| myopericarditis - pfizer - adolescent - ekg - thailand \| 20 \| 62_myopericarditis_pfizer_adolescent_ekg \|

	</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_DrPaulAlexander

	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_DrPaulAlexander")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 64
	* Number of training documents: 5766

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

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| unvaccinated - pfizer - lockdowns - injections - 2021 \| 20 \| -1_unvaccinated_pfizer_lockdowns_injections \|
	\| 0 \| tranny - females - penises - vaginoplasty - dysphoria \| 2790 \| 0_tranny_females_penises_vaginoplasty \|
	\| 1 \| fauci - deepstate - lockdowns - colluded - mengele \| 162 \| 1_fauci_deepstate_lockdowns_colluded \|
	\| 2 \| mrna - biontech - injections - malone - inventors \| 143 \| 2_mrna_biontech_injections_malone \|
	\| 3 \| pandemic - hoax - false - asymptomatic - never \| 125 \| 3_pandemic_hoax_false_asymptomatic \|
	\| 4 \| monkeypox - hiv - gay - gonorrhoea - marburg \| 124 \| 4_monkeypox_hiv_gay_gonorrhoea \|
	\| 5 \| zelensky - russia - volodymyr - missiles - kissinger \| 103 \| 5_zelensky_russia_volodymyr_missiles \|
	\| 6 \| peters - drs - interviews - bellavia - maldonado \| 89 \| 6_peters_drs_interviews_bellavia \|
	\| 7 \| myopericarditis - endomyocardial - vaccination - tamponade - mri \| 84 \| 7_myopericarditis_endomyocardial_vaccination_tamponade \|
	\| 8 \| pilots - cockpit - plane - boeing - crashed \| 77 \| 8_pilots_cockpit_plane_boeing \|
	\| 9 \| illegals - biden - invaded - jihadists - border \| 76 \| 9_illegals_biden_invaded_jihadists \|
	\| 10 \| vaccination - thromboembolic - autoantibodies - vasculitis - c19 \| 74 \| 10_vaccination_thromboembolic_autoantibodies_vasculitis \|
	\| 11 \| trudeau - vaccinal - njoo - truckers - sharma \| 69 \| 11_trudeau_vaccinal_njoo_truckers \|
	\| 12 \| remdesivir - midazolam - euthanasia - iatrogenic - ventilator \| 66 \| 12_remdesivir_midazolam_euthanasia_iatrogenic \|
	\| 13 \| coronaviruses - wuhan - chimeric - 2020 - wiv \| 66 \| 13_coronaviruses_wuhan_chimeric_2020 \|
	\| 14 \| died - sudden - year - 44 - vandaelle \| 63 \| 14_died_sudden_year_44 \|
	\| 15 \| naomi - innoculations - bannon - dailyclout - genocidal \| 60 \| 15_naomi_innoculations_bannon_dailyclout \|
	\| 16 \| islamists - wolf - bataclan - migrant - europe \| 58 \| 16_islamists_wolf_bataclan_migrant \|
	\| 17 \| subvariants - omicron - clade - ba5 - dominant \| 57 \| 17_subvariants_omicron_clade_ba5 \|
	\| 18 \| immunization - pfizer - sids - shots - harmful \| 57 \| 18_immunization_pfizer_sids_shots \|
	\| 19 \| shootings - officer - texas - dewitt - robbers \| 56 \| 19_shootings_officer_texas_dewitt \|
	\| 20 \| maloney - breggins - lawsuit - oppenheimer - jane \| 56 \| 20_maloney_breggins_lawsuit_oppenheimer \|
	\| 21 \| povidone - mouthwash - hypochlorite - nasal - ivermectin \| 53 \| 21_povidone_mouthwash_hypochlorite_nasal \|
	\| 22 \| sarcoma - leukemias - glioblastoma - oncologist - rapid \| 50 \| 22_sarcoma_leukemias_glioblastoma_oncologist \|
	\| 23 \| biden - republicans - mcconnell - teleprompter - midterms \| 49 \| 23_biden_republicans_mcconnell_teleprompter \|
	\| 24 \| masks - toxic - cochrane - ineffectiveness - microplastic \| 47 \| 24_masks_toxic_cochrane_ineffectiveness \|
	\| 25 \| deaths - vaccinated - eurostat - 2021 - kuhbandner \| 45 \| 25_deaths_vaccinated_eurostat_2021 \|
	\| 26 \| vaccinations - miscarriage - decidual - dysmenorrhea - diethylstilbestrol \| 43 \| 26_vaccinations_miscarriage_decidual_dysmenorrhea \|
	\| 27 \| fluorofentanyl - carfentanil - xylazine - naloxone - overdose \| 39 \| 27_fluorofentanyl_carfentanil_xylazine_naloxone \|
	\| 28 \| lockdowns - tiananmen - shanghai - xi - lunatic \| 39 \| 28_lockdowns_tiananmen_shanghai_xi \|
	\| 29 \| omicron - vaccination - booster - hansen - subvariants \| 37 \| 29_omicron_vaccination_booster_hansen \|
	\| 30 \| fbi - trump - raided - defund - politicized \| 37 \| 30_fbi_trump_raided_defund \|
	\| 31 \| antibodies - naturally - reinfection - documented - sars \| 36 \| 31_antibodies_naturally_reinfection_documented \|
	\| 32 \| harvard - plagiarized - claudine - zakaria - antisemite \| 34 \| 32_harvard_plagiarized_claudine_zakaria \|
	\| 33 \| vaccinated - omicron - prophylaxis - nigeria - deaths \| 34 \| 33_vaccinated_omicron_prophylaxis_nigeria \|
	\| 34 \| kennedy - kwiatkowski - prasad - mkultra - partisan \| 34 \| 34_kennedy_kwiatkowski_prasad_mkultra \|
	\| 35 \| pfizer - deathvax - defrauded - ombudsman - bla \| 34 \| 35_pfizer_deathvax_defrauded_ombudsman \|
	\| 36 \| bengals - myocarditis - cornerback - xfl - demarcus \| 33 \| 36_bengals_myocarditis_cornerback_xfl \|
	\| 37 \| djokovic - champion - mcenroe - kelce - superbowl \| 33 \| 37_djokovic_champion_mcenroe_kelce \|
	\| 38 \| nattokinase - detoxifier - spike - acetylcysteine - anticoagulant \| 32 \| 38_nattokinase_detoxifier_spike_acetylcysteine \|
	\| 39 \| vaers - adenovirus - adverse - astrazeneca - pneumoniae \| 29 \| 39_vaers_adenovirus_adverse_astrazeneca \|
	\| 40 \| mccullough - peter - investigator - cardiologist - tacit \| 28 \| 40_mccullough_peter_investigator_cardiologist \|
	\| 41 \| trump - reelected - maddow - politicized - ramaswamy \| 28 \| 41_trump_reelected_maddow_politicized \|
	\| 42 \| florida - surgeon - desantis - joe - walensky \| 27 \| 42_florida_surgeon_desantis_joe \|
	\| 43 \| horsemen - apocalpse - plague - 33 - horrendous \| 27 \| 43_horsemen_apocalpse_plague_33 \|
	\| 44 \| omicron - bivalent - ba5 - updated - 2023 \| 27 \| 44_omicron_bivalent_ba5_updated \|
	\| 45 \| hamas - israeli - yehuda - pogrom - invaders \| 27 \| 45_hamas_israeli_yehuda_pogrom \|
	\| 46 \| pedophiles - pope - scandalizing - corrupters - nuns \| 26 \| 46_pedophiles_pope_scandalizing_corrupters \|
	\| 47 \| remdesivir - hydroxychloroquine - tamiflu - zanamivir - pharmacovigilance \| 26 \| 47_remdesivir_hydroxychloroquine_tamiflu_zanamivir \|
	\| 48 \| inflation - biden - plummets - trillion - binance \| 25 \| 48_inflation_biden_plummets_trillion \|
	\| 49 \| nagase - coulson - everybody - malhotra - stacks \| 24 \| 49_nagase_coulson_everybody_malhotra \|
	\| 50 \| tribunals - hanged - jailed - punish - amnesty \| 24 \| 50_tribunals_hanged_jailed_punish \|
	\| 51 \| ottawa - james - tomb - marched - veteran \| 23 \| 51_ottawa_james_tomb_marched \|
	\| 52 \| fauci - virulent - evolve - injecting - chemoprophylaxis \| 23 \| 52_fauci_virulent_evolve_injecting \|
	\| 53 \| semaglutide - ozempic - insulin - hypoglycemia - pancreatitis \| 23 \| 53_semaglutide_ozempic_insulin_hypoglycemia \|
	\| 54 \| vaccinee - chemoprophylaxis - immunological - pediatricians - rennebohm \| 23 \| 54_vaccinee_chemoprophylaxis_immunological_pediatricians \|
	\| 55 \| sars - antigens - sequelae - persistent - exosomes \| 23 \| 55_sars_antigens_sequelae_persistent \|
	\| 56 \| twitter - musk - dorsey - zuckerberg - banned \| 23 \| 56_twitter_musk_dorsey_zuckerberg \|
	\| 57 \| liposome - exosomes - nanoparticles - lnp - lymphocytes \| 22 \| 57_liposome_exosomes_nanoparticles_lnp \|
	\| 58 \| amnesty - covidian - emma - wrongdoers - forgive \| 22 \| 58_amnesty_covidian_emma_wrongdoers \|
	\| 59 \| vaccinating - maternal - pfizer - pertussis - neonates \| 22 \| 59_vaccinating_maternal_pfizer_pertussis \|
	\| 60 \| endothelial - sars - sialylated - pathogenesis - hypercoagulation \| 20 \| 60_endothelial_sars_sialylated_pathogenesis \|
	\| 61 \| biden - indicted - bribery - impeach - ukraine \| 20 \| 61_biden_indicted_bribery_impeach \|
	\| 62 \| myopericarditis - pfizer - adolescent - ekg - thailand \| 20 \| 62_myopericarditis_pfizer_adolescent_ekg \|

	</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