MARTINI_enrich_BERTopic_realx22report

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_realx22report")

topic_model.get_topic_info()

Topic overview

• Number of topics: 30
• Number of training documents: 3061

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	biden - fbi - vaccinated - impeachment - anyone	21	-1_biden_fbi_vaccinated_impeachment
0	patriotism - freedoms - tyranny - volunteer - never	1651	0_patriotism_freedoms_tyranny_volunteer
1	ballots - maricopa - recount - auditors - leaked	165	1_ballots_maricopa_recount_auditors
2	protests - unvaccinated - masks - austria - mandatory	145	2_protests_unvaccinated_masks_austria
3	vaccinated - pfizer - vaers - antibodies - delisted	91	3_vaccinated_pfizer_vaers_antibodies
4	twitter - musk - shadowbanning - censored - takeover	79	4_twitter_musk_shadowbanning_censored
5	donetsk - putin - zelensky - bioweapons - nazis	76	5_donetsk_putin_zelensky_bioweapons
6	fauci - pcr - false - test - swabs	74	6_fauci_pcr_false_test
7	truthsocial - impersonating - verified - bots - deleted	47	7_truthsocial_impersonating_verified_bots
8	biden - teleprompter - michelle - jimmy - reporters	47	8_biden_teleprompter_michelle_jimmy
9	thesecretcurriculum - indoctrinating - teachers - hillsdale - antifa	46	9_thesecretcurriculum_indoctrinating_teachers_hillsdale
10	trump - indicted - courthouse - guantanamo - supreme	44	10_trump_indicted_courthouse_guantanamo
11	mueller - clinton - dossier - colluded - indictments	42	11_mueller_clinton_dossier_colluded
12	truckers - trudeau - beltway - blockade - protesters	42	12_truckers_trudeau_beltway_blockade
13	traffickers - immigration - blinken - border - texas	41	13_traffickers_immigration_blinken_border
14	vaccine - mandatory - eeoc - defendingtherepublic - injunction	39	14_vaccine_mandatory_eeoc_defendingtherepublic
15	senators - filibuster - voted - trillion - taxpayers	37	15_senators_filibuster_voted_trillion
16	taliban - kabul - bombing - evacuees - stormypatriotjoe	35	16_taliban_kabul_bombing_evacuees
17	taiwan - norad - cyberattack - stratotankers - zhangjiakou	32	17_taiwan_norad_cyberattack_stratotankers
18	ghislaine - unsealed - docket - incriminating - john	32	18_ghislaine_unsealed_docket_incriminating
19	fauci - darpa - nanoscientist - deepfakes - unredacted	32	19_fauci_darpa_nanoscientist_deepfakes
20	desantis - florida - governor - mandates - brandon	32	20_desantis_florida_governor_mandates
21	facebook - censorship - misinformation - campaigns - announced	32	21_facebook_censorship_misinformation_campaigns
22	firearms - illegal - amendment - disarming - hr3015	30	22_firearms_illegal_amendment_disarming
23	cnn - newscast - reporter - warnermedia - allegations	29	23_cnn_newscast_reporter_warnermedia
24	fbi - insurrectionists - january - carlson - congressman	28	24_fbi_insurrectionists_january_carlson
25	shootings - killed - suspect - deputies - george	27	25_shootings_killed_suspect_deputies
26	bidenlaptopemails - disinformation - rudy - investigators - huawei	23	26_bidenlaptopemails_disinformation_rudy_investigators
27	trump - inauguration - accusations - andrews - 45th	21	27_trump_inauguration_accusations_andrews
28	nyt - defamation - depositions - constitutionally - unverifiable	21	28_nyt_defamation_depositions_constitutionally

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