MARTINI_enrich_BERTopic_BLUEPRINT_Q

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_BLUEPRINT_Q")

topic_model.get_topic_info()

Topic overview

• Number of topics: 14
• Number of training documents: 1373

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	patriot - slaves - trump - overthrow - constitution	23	-1_patriot_slaves_trump_overthrow
0	trump - tyranny - undefeated - stratagem - jackson	823	0_trump_tyranny_undefeated_stratagem
1	liberty - founders - believed - revelation - 1776	79	1_liberty_founders_believed_revelation
2	ballots - corrupt - hobbs - governor - maricopa	67	2_ballots_corrupt_hobbs_governor
3	fbi - clinton - dossier - allegations - sussman	61	3_fbi_clinton_dossier_allegations
4	fauci - vaccinated - pfizer - hydroxychloroquine - antibodies	59	4_fauci_vaccinated_pfizer_hydroxychloroquine
5	putin - mariupol - bioweapons - fauci - fascists	46	5_putin_mariupol_bioweapons_fauci
6	trump - clintons - epstein - cnn - trafficking	45	6_trump_clintons_epstein_cnn
7	andweknow - patriot - salute - awesome - nazis	34	7_andweknow_patriot_salute_awesome
8	qanon - twitter - awakening - campaign - false	31	8_qanon_twitter_awakening_campaign
9	imposter - scam - telegram - unwatermarked - zelenko	28	9_imposter_scam_telegram_unwatermarked
10	republicans - mccarthy - ballot - cosponsored - committees	28	10_republicans_mccarthy_ballot_cosponsored
11	counterinsurgency - treason - nsa - dod - government	26	11_counterinsurgency_treason_nsa_dod
12	lgbtq - pedophile - genderism - communists - progressive	23	12_lgbtq_pedophile_genderism_communists

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