MARTINI_enrich_BERTopic_FionaRoseDiamond

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_FionaRoseDiamond")

topic_model.get_topic_info()

Topic overview

• Number of topics: 22
• Number of training documents: 2313

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	covid - police - london - jab - worldwide	21	-1_covid_police_london_jab
0	haters - liars - bullying - divisive - hope	1485	0_haters_liars_bullying_divisive
1	protests - arrest - convicted - westminster - magistrates	114	1_protests_arrest_convicted_westminster
2	criminalise - protests - parliament - reforms - lawful	67	2_criminalise_protests_parliament_reforms
3	vaxpass - parliament - repeal - compulsory - togetherdeclaration	59	3_vaxpass_parliament_repeal_compulsory
4	worldcouncilforhealth - pandemic - sovereignty - saveourrights - amendments	57	4_worldcouncilforhealth_pandemic_sovereignty_saveourrights
5	lockdowns - globalist - oligarchy - trojan - ubi	51	5_lockdowns_globalist_oligarchy_trojan
6	westminster - vaccine - backbench - expelled - saveoursovereignty	45	6_westminster_vaccine_backbench_expelled
7	novavax - fatalities - anaphylaxis - injected - card	40	7_novavax_fatalities_anaphylaxis_injected
8	oraclefilms - covileaks - documentary - reupload - anarchapulco	40	8_oraclefilms_covileaks_documentary_reupload
9	vaccine - truth - canwetalkaboutit - sheffield - campaigning	35	9_vaccine_truth_canwetalkaboutit_sheffield
10	bbc - notonthebeeb - disinformation - wtfisgoingonofficial - campaign	35	10_bbc_notonthebeeb_disinformation_wtfisgoingonofficial
11	croydon - whitehall - notourwar - mi5 - eventbrite	33	11_croydon_whitehall_notourwar_mi5
12	wwdunitedkingdomlocations - londonofficialworldwiderally - worldwidedemonstration - holyrood - dublin	30	12_wwdunitedkingdomlocations_londonofficialworldwiderally_worldwidedemonstration_holyrood
13	eric - protester - nhs - counterspinmedia - july	30	13_eric_protester_nhs_counterspinmedia
14	vaxxers - bbc - safeandeffective - documentaries - sharman	27	14_vaxxers_bbc_safeandeffective_documentaries
15	vaccinations - consent - parents - solicitors - gillick	25	15_vaccinations_consent_parents_solicitors
16	scammers - fionacovileaksofficial - message - bot - blocked	25	16_scammers_fionacovileaksofficial_message_bot
17	astrazeneca - 2021 - paralysed - anaphylaxis - misinformation	24	17_astrazeneca_2021_paralysed_anaphylaxis
18	londonofficialworldwiderally - wwdunitedkingdomlocations - unvaxxed - november - w1a1aa	24	18_londonofficialworldwiderally_wwdunitedkingdomlocations_unvaxxed_november
19	vaccinations - vaccinated - pfizer - child - lancet	24	19_vaccinations_vaccinated_pfizer_child
20	vaccinate - twickenham - centres - april - jabbed	22	20_vaccinate_twickenham_centres_april

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