Add BERTopic model

0348765 verified about 1 year ago

8.02 kB


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

	# MARTINI_enrich_BERTopic_DrJaneRuby

	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_DrJaneRuby")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 60
	* Number of training documents: 5890

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

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| doctors - pfizer - vaccinated - bioweapon - patriot \| 20 \| -1_doctors_pfizer_vaccinated_bioweapon \|
	\| 0 \| malone - protectdrjane - vaccines - mrna - lawsuits \| 2944 \| 0_malone_protectdrjane_vaccines_mrna \|
	\| 1 \| pfizer - fda - becerra - pdufa - redacted \| 175 \| 1_pfizer_fda_becerra_pdufa \|
	\| 2 \| pilots - airliner - cockpit - jets - flying \| 154 \| 2_pilots_airliner_cockpit_jets \|
	\| 3 \| clots - embalmer - fibrous - white - findings \| 131 \| 3_clots_embalmer_fibrous_white \|
	\| 4 \| covid - pcr - test - false - asymptomatic \| 112 \| 4_covid_pcr_test_false \|
	\| 5 \| military - rfra - mandates - dod - waivers \| 100 \| 5_military_rfra_mandates_dod \|
	\| 6 \| stewpeters - wednesday - jane - questions - tonight \| 95 \| 6_stewpeters_wednesday_jane_questions \|
	\| 7 \| towergarden - seedlings - aeroponic - tomatoes - celery \| 93 \| 7_towergarden_seedlings_aeroponic_tomatoes \|
	\| 8 \| spikevax - fda - toddlers - june - deaths \| 92 \| 8_spikevax_fda_toddlers_june \|
	\| 9 \| pfizer - vial - nanoparticles - findings - fibrinogen \| 87 \| 9_pfizer_vial_nanoparticles_findings \|
	\| 10 \| detoxing - mrna - quadrivalent - omicron - shots \| 85 \| 10_detoxing_mrna_quadrivalent_omicron \|
	\| 11 \| filterssuck - purifier - aerosol - allergens - forfree \| 81 \| 11_filterssuck_purifier_aerosol_allergens \|
	\| 12 \| channel - proselytizing - trolls - conflicts - conversations \| 80 \| 12_channel_proselytizing_trolls_conflicts \|
	\| 13 \| telegram - bots - spamming - banned - scammers \| 76 \| 13_telegram_bots_spamming_banned \|
	\| 14 \| zinc - antioxidant - supplements - apricot - b17 \| 66 \| 14_zinc_antioxidant_supplements_apricot \|
	\| 15 \| republicans - congressional - communism - mccarthy - takeover \| 61 \| 15_republicans_congressional_communism_mccarthy \|
	\| 16 \| desantis - quarantined - repeal - sb2006 - remdesivir \| 59 \| 16_desantis_quarantined_repeal_sb2006 \|
	\| 17 \| immunotherapies - injections - dna - c19 - deadlier \| 59 \| 17_immunotherapies_injections_dna_c19 \|
	\| 18 \| rubysuperfoods - mypowerheart - filterssuck - magnesium - symptoms \| 55 \| 18_rubysuperfoods_mypowerheart_filterssuck_magnesium \|
	\| 19 \| mypillows - lindell - towels - mike - discounts \| 53 \| 19_mypillows_lindell_towels_mike \|
	\| 20 \| jane - dtjaneruby - reruns - tunein - tonight \| 50 \| 20_jane_dtjaneruby_reruns_tunein \|
	\| 21 \| trump - denounce - reelected - weaponized - eugenicist \| 48 \| 21_trump_denounce_reelected_weaponized \|
	\| 22 \| monoglycerides - avocados - poisoning - coating - propiconazole \| 47 \| 22_monoglycerides_avocados_poisoning_coating \|
	\| 23 \| grounding - yoga - soreness - cushioned - advantages \| 46 \| 23_grounding_yoga_soreness_cushioned \|
	\| 24 \| orthopox - chickenpox - contagious - monkey - imvamune \| 43 \| 24_orthopox_chickenpox_contagious_monkey \|
	\| 25 \| mypillows - pillowcases - blankets - bathrobes - discounts \| 41 \| 25_mypillows_pillowcases_blankets_bathrobes \|
	\| 26 \| hospital - hermann - sarasota - unvaccinated - murdered \| 41 \| 26_hospital_hermann_sarasota_unvaccinated \|
	\| 27 \| nurses - endotracheal - phlebotomist - murderers - abused \| 39 \| 27_nurses_endotracheal_phlebotomist_murderers \|
	\| 28 \| whistleblowers - colonel - dod - soldiers - theresa \| 39 \| 28_whistleblowers_colonel_dod_soldiers \|
	\| 29 \| myocarditis - endocardium - strokes - attacks - young \| 37 \| 29_myocarditis_endocardium_strokes_attacks \|
	\| 30 \| gold - 401ks - augusta - savings - trillions \| 37 \| 30_gold_401ks_augusta_savings \|
	\| 31 \| voters - ballots - recounts - arizona - november \| 35 \| 31_voters_ballots_recounts_arizona \|
	\| 32 \| fauci - darpa - treason - genocide - subpoena \| 33 \| 32_fauci_darpa_treason_genocide \|
	\| 33 \| purifiers - airwaterhealing - promo - shield - v3 \| 33 \| 33_purifiers_airwaterhealing_promo_shield \|
	\| 34 \| ivermectin - drstellamd - hydroxychloroquine - concerneddoctors - prescription \| 33 \| 34_ivermectin_drstellamd_hydroxychloroquine_concerneddoctors \|
	\| 35 \| blessings - pray - heaven - christmas - isaiah \| 32 \| 35_blessings_pray_heaven_christmas \|
	\| 36 \| sleepbreakthrough - melatonin - magbreakthrough - magnesium - supplement \| 32 \| 36_sleepbreakthrough_melatonin_magbreakthrough_magnesium \|
	\| 37 \| homeschool - masked - indoctrinating - vaxxpassport - walkout \| 31 \| 37_homeschool_masked_indoctrinating_vaxxpassport \|
	\| 38 \| airwaterhealing - purifiers - promo - protective - shungite \| 31 \| 38_airwaterhealing_purifiers_promo_protective \|
	\| 39 \| molnupiravir - vilobelimab - immunomodulators - prescriptions - dangerous \| 30 \| 39_molnupiravir_vilobelimab_immunomodulators_prescriptions \|
	\| 40 \| vaccine - poisons - shots - injectable - walgreens \| 29 \| 40_vaccine_poisons_shots_injectable \|
	\| 41 \| preppers - stockpile - survive - shortage - perishables \| 29 \| 41_preppers_stockpile_survive_shortage \|
	\| 42 \| stew - grassroots - patriots - megan - weaponizing \| 28 \| 42_stew_grassroots_patriots_megan \|
	\| 43 \| uploading - delayed - morning - discussions - struggling \| 27 \| 43_uploading_delayed_morning_discussions \|
	\| 44 \| protests - trudeau - tyrannical - nope - truckers \| 26 \| 44_protests_trudeau_tyrannical_nope \|
	\| 45 \| illegals - militia - weaponized - border - panama \| 25 \| 45_illegals_militia_weaponized_border \|
	\| 46 \| livestream - jane - morning - laurenwitzke - thrive \| 25 \| 46_livestream_jane_morning_laurenwitzke \|
	\| 47 \| drjaneruby - rumble - livestream - jane - january \| 24 \| 47_drjaneruby_rumble_livestream_jane \|
	\| 48 \| goldco - investments - riskiest - precious - protect \| 24 \| 48_goldco_investments_riskiest_precious \|
	\| 49 \| truly - heaven - gods - blessed - compassion \| 23 \| 49_truly_heaven_gods_blessed \|
	\| 50 \| hochul - nys - judicial - nonvaxxed - overturned \| 22 \| 50_hochul_nys_judicial_nonvaxxed \|
	\| 51 \| vaccinated - mandates - employer - exemption - masks \| 22 \| 51_vaccinated_mandates_employer_exemption \|
	\| 52 \| meredith - hugs - joshua - paramedics - bravery \| 22 \| 52_meredith_hugs_joshua_paramedics \|
	\| 53 \| reawaken - determinedpatriotismconference - speaker - clark - orlando \| 22 \| 53_reawaken_determinedpatriotismconference_speaker_clark \|
	\| 54 \| katherine - bioterrorism - brighteontv - bombshell - wednesday \| 22 \| 54_katherine_bioterrorism_brighteontv_bombshell \|
	\| 55 \| novavax - adjuvant - injected - baculovirus - nanoparticulate \| 22 \| 55_novavax_adjuvant_injected_baculovirus \|
	\| 56 \| drjaneruby - bioweapons - suppress - titan - fallout \| 22 \| 56_drjaneruby_bioweapons_suppress_titan \|
	\| 57 \| infowars - live - invited - hosts - shawn \| 20 \| 57_infowars_live_invited_hosts \|
	\| 58 \| vaccinepolicebook - christopher - banners4freedom - lawmakers - louisiana \| 20 \| 58_vaccinepolicebook_christopher_banners4freedom_lawmakers \|

	</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_DrJaneRuby

	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_DrJaneRuby")

	topic_model.get_topic_info()
	```

	## Topic overview

	* Number of topics: 60
	* Number of training documents: 5890

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

	\| Topic ID \| Topic Keywords \| Topic Frequency \| Label \|
	\|----------\|----------------\|-----------------\|-------\|
	\| -1 \| doctors - pfizer - vaccinated - bioweapon - patriot \| 20 \| -1_doctors_pfizer_vaccinated_bioweapon \|
	\| 0 \| malone - protectdrjane - vaccines - mrna - lawsuits \| 2944 \| 0_malone_protectdrjane_vaccines_mrna \|
	\| 1 \| pfizer - fda - becerra - pdufa - redacted \| 175 \| 1_pfizer_fda_becerra_pdufa \|
	\| 2 \| pilots - airliner - cockpit - jets - flying \| 154 \| 2_pilots_airliner_cockpit_jets \|
	\| 3 \| clots - embalmer - fibrous - white - findings \| 131 \| 3_clots_embalmer_fibrous_white \|
	\| 4 \| covid - pcr - test - false - asymptomatic \| 112 \| 4_covid_pcr_test_false \|
	\| 5 \| military - rfra - mandates - dod - waivers \| 100 \| 5_military_rfra_mandates_dod \|
	\| 6 \| stewpeters - wednesday - jane - questions - tonight \| 95 \| 6_stewpeters_wednesday_jane_questions \|
	\| 7 \| towergarden - seedlings - aeroponic - tomatoes - celery \| 93 \| 7_towergarden_seedlings_aeroponic_tomatoes \|
	\| 8 \| spikevax - fda - toddlers - june - deaths \| 92 \| 8_spikevax_fda_toddlers_june \|
	\| 9 \| pfizer - vial - nanoparticles - findings - fibrinogen \| 87 \| 9_pfizer_vial_nanoparticles_findings \|
	\| 10 \| detoxing - mrna - quadrivalent - omicron - shots \| 85 \| 10_detoxing_mrna_quadrivalent_omicron \|
	\| 11 \| filterssuck - purifier - aerosol - allergens - forfree \| 81 \| 11_filterssuck_purifier_aerosol_allergens \|
	\| 12 \| channel - proselytizing - trolls - conflicts - conversations \| 80 \| 12_channel_proselytizing_trolls_conflicts \|
	\| 13 \| telegram - bots - spamming - banned - scammers \| 76 \| 13_telegram_bots_spamming_banned \|
	\| 14 \| zinc - antioxidant - supplements - apricot - b17 \| 66 \| 14_zinc_antioxidant_supplements_apricot \|
	\| 15 \| republicans - congressional - communism - mccarthy - takeover \| 61 \| 15_republicans_congressional_communism_mccarthy \|
	\| 16 \| desantis - quarantined - repeal - sb2006 - remdesivir \| 59 \| 16_desantis_quarantined_repeal_sb2006 \|
	\| 17 \| immunotherapies - injections - dna - c19 - deadlier \| 59 \| 17_immunotherapies_injections_dna_c19 \|
	\| 18 \| rubysuperfoods - mypowerheart - filterssuck - magnesium - symptoms \| 55 \| 18_rubysuperfoods_mypowerheart_filterssuck_magnesium \|
	\| 19 \| mypillows - lindell - towels - mike - discounts \| 53 \| 19_mypillows_lindell_towels_mike \|
	\| 20 \| jane - dtjaneruby - reruns - tunein - tonight \| 50 \| 20_jane_dtjaneruby_reruns_tunein \|
	\| 21 \| trump - denounce - reelected - weaponized - eugenicist \| 48 \| 21_trump_denounce_reelected_weaponized \|
	\| 22 \| monoglycerides - avocados - poisoning - coating - propiconazole \| 47 \| 22_monoglycerides_avocados_poisoning_coating \|
	\| 23 \| grounding - yoga - soreness - cushioned - advantages \| 46 \| 23_grounding_yoga_soreness_cushioned \|
	\| 24 \| orthopox - chickenpox - contagious - monkey - imvamune \| 43 \| 24_orthopox_chickenpox_contagious_monkey \|
	\| 25 \| mypillows - pillowcases - blankets - bathrobes - discounts \| 41 \| 25_mypillows_pillowcases_blankets_bathrobes \|
	\| 26 \| hospital - hermann - sarasota - unvaccinated - murdered \| 41 \| 26_hospital_hermann_sarasota_unvaccinated \|
	\| 27 \| nurses - endotracheal - phlebotomist - murderers - abused \| 39 \| 27_nurses_endotracheal_phlebotomist_murderers \|
	\| 28 \| whistleblowers - colonel - dod - soldiers - theresa \| 39 \| 28_whistleblowers_colonel_dod_soldiers \|
	\| 29 \| myocarditis - endocardium - strokes - attacks - young \| 37 \| 29_myocarditis_endocardium_strokes_attacks \|
	\| 30 \| gold - 401ks - augusta - savings - trillions \| 37 \| 30_gold_401ks_augusta_savings \|
	\| 31 \| voters - ballots - recounts - arizona - november \| 35 \| 31_voters_ballots_recounts_arizona \|
	\| 32 \| fauci - darpa - treason - genocide - subpoena \| 33 \| 32_fauci_darpa_treason_genocide \|
	\| 33 \| purifiers - airwaterhealing - promo - shield - v3 \| 33 \| 33_purifiers_airwaterhealing_promo_shield \|
	\| 34 \| ivermectin - drstellamd - hydroxychloroquine - concerneddoctors - prescription \| 33 \| 34_ivermectin_drstellamd_hydroxychloroquine_concerneddoctors \|
	\| 35 \| blessings - pray - heaven - christmas - isaiah \| 32 \| 35_blessings_pray_heaven_christmas \|
	\| 36 \| sleepbreakthrough - melatonin - magbreakthrough - magnesium - supplement \| 32 \| 36_sleepbreakthrough_melatonin_magbreakthrough_magnesium \|
	\| 37 \| homeschool - masked - indoctrinating - vaxxpassport - walkout \| 31 \| 37_homeschool_masked_indoctrinating_vaxxpassport \|
	\| 38 \| airwaterhealing - purifiers - promo - protective - shungite \| 31 \| 38_airwaterhealing_purifiers_promo_protective \|
	\| 39 \| molnupiravir - vilobelimab - immunomodulators - prescriptions - dangerous \| 30 \| 39_molnupiravir_vilobelimab_immunomodulators_prescriptions \|
	\| 40 \| vaccine - poisons - shots - injectable - walgreens \| 29 \| 40_vaccine_poisons_shots_injectable \|
	\| 41 \| preppers - stockpile - survive - shortage - perishables \| 29 \| 41_preppers_stockpile_survive_shortage \|
	\| 42 \| stew - grassroots - patriots - megan - weaponizing \| 28 \| 42_stew_grassroots_patriots_megan \|
	\| 43 \| uploading - delayed - morning - discussions - struggling \| 27 \| 43_uploading_delayed_morning_discussions \|
	\| 44 \| protests - trudeau - tyrannical - nope - truckers \| 26 \| 44_protests_trudeau_tyrannical_nope \|
	\| 45 \| illegals - militia - weaponized - border - panama \| 25 \| 45_illegals_militia_weaponized_border \|
	\| 46 \| livestream - jane - morning - laurenwitzke - thrive \| 25 \| 46_livestream_jane_morning_laurenwitzke \|
	\| 47 \| drjaneruby - rumble - livestream - jane - january \| 24 \| 47_drjaneruby_rumble_livestream_jane \|
	\| 48 \| goldco - investments - riskiest - precious - protect \| 24 \| 48_goldco_investments_riskiest_precious \|
	\| 49 \| truly - heaven - gods - blessed - compassion \| 23 \| 49_truly_heaven_gods_blessed \|
	\| 50 \| hochul - nys - judicial - nonvaxxed - overturned \| 22 \| 50_hochul_nys_judicial_nonvaxxed \|
	\| 51 \| vaccinated - mandates - employer - exemption - masks \| 22 \| 51_vaccinated_mandates_employer_exemption \|
	\| 52 \| meredith - hugs - joshua - paramedics - bravery \| 22 \| 52_meredith_hugs_joshua_paramedics \|
	\| 53 \| reawaken - determinedpatriotismconference - speaker - clark - orlando \| 22 \| 53_reawaken_determinedpatriotismconference_speaker_clark \|
	\| 54 \| katherine - bioterrorism - brighteontv - bombshell - wednesday \| 22 \| 54_katherine_bioterrorism_brighteontv_bombshell \|
	\| 55 \| novavax - adjuvant - injected - baculovirus - nanoparticulate \| 22 \| 55_novavax_adjuvant_injected_baculovirus \|
	\| 56 \| drjaneruby - bioweapons - suppress - titan - fallout \| 22 \| 56_drjaneruby_bioweapons_suppress_titan \|
	\| 57 \| infowars - live - invited - hosts - shawn \| 20 \| 57_infowars_live_invited_hosts \|
	\| 58 \| vaccinepolicebook - christopher - banners4freedom - lawmakers - louisiana \| 20 \| 58_vaccinepolicebook_christopher_banners4freedom_lawmakers \|

	</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