MARTINI_enrich_BERTopic_BBCisTheVIRUS

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_BBCisTheVIRUS")

topic_model.get_topic_info()

Topic overview

• Number of topics: 31
• Number of training documents: 5095

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	protest - bbc - truth - freedom - covid	20	-1_protest_bbc_truth_freedom
0	sticker - printable - sheets - a4 - canva	3288	0_sticker_printable_sheets_a4
1	bbcisthevirus - march - lies - nhk - 28th	149	1_bbcisthevirus_march_lies_nhk
2	bbc - belfast - nottingham - wales - salford	141	2_bbc_belfast_nottingham_wales
3	bbc - uncovered - bombshell - reporters - whores	127	3_bbc_uncovered_bombshell_reporters
4	meetup - attending - idk - cancelled - date	119	4_meetup_attending_idk_cancelled
5	arrested - cops - policeman - constables - idiots	116	5_arrested_cops_policeman_constables
6	vigimedias - presse - propaganda - fevrier - souverainete	107	6_vigimedias_presse_propaganda_fevrier
7	vaccinated - injectuon - mumps - nhs - colds	87	7_vaccinated_injectuon_mumps_nhs
8	spammers - messages - deleted - admin - teligram	80	8_spammers_messages_deleted_admin
9	manchester - posters - wednesday - 11am - picnic	78	9_manchester_posters_wednesday_11am
10	deleted - links - messages - hmm - video	68	10_deleted_links_messages_hmm
11	infighting - clown - normie - pointless - sh1t	65	11_infighting_clown_normie_pointless
12	flyposting - posters - defacement - sticker - advertisers	63	12_flyposting_posters_defacement_sticker
13	protesting - extremists - conformists - revolutions - attend	58	13_protesting_extremists_conformists_revolutions
14	revolt - fighting - ennemie - droits - violente	48	14_revolt_fighting_ennemie_droits
15	unvaxxed - astrazeneca - bleeding - 2021 - pneumonia	48	15_unvaxxed_astrazeneca_bleeding_2021
16	freeview - unlicensed - cibtractvwith - beatthebailiffs - refunded	45	16_freeview_unlicensed_cibtractvwith_beatthebailiffs
17	vaxgenocide - vandals - cittadini - videosorveglianza - nazista	42	17_vaxgenocide_vandals_cittadini_videosorveglianza
18	bristol - manchesterat - wolverhampton - attending - rhondda	39	18_bristol_manchesterat_wolverhampton_attending
19	australians - nsw - rallys - mebourne - nbn	38	19_australians_nsw_rallys_mebourne
20	appreciated - yesterday - participated - greatest - congratulate	34	20_appreciated_yesterday_participated_greatest
21	upl_unioneperleliberta - difendiamo - tutto - nati_liberi_to_be_free - silenzio	31	21_upl_unioneperleliberta_difendiamo_tutto_nati_liberi_to_be_free
22	stickers - whiteboard - lol - postcard - decoration	29	22_stickers_whiteboard_lol_postcard
23	irishpatriots - antifa - diarmaid - belgium - sovereign	29	23_irishpatriots_antifa_diarmaid_belgium
24	worldwidedemonstration - wwrforfreedom - nationwideralliesforfreedom - fnqfreedomalliancenetwork - tiananmen	27	24_worldwidedemonstration_wwrforfreedom_nationwideralliesforfreedom_fnqfreedomalliancenetwork
25	cashless - spycoin - wallet - tracked - currency	25	25_cashless_spycoin_wallet_tracked
26	bbcisthevirus - manchester - thevmedia - confirmed - blackburn	25	26_bbcisthevirus_manchester_thevmedia_confirmed
27	worldwidedemonstration - scotlandtgr - holyrood - edinburg - liberties	25	27_worldwidedemonstration_scotlandtgr_holyrood_edinburg
28	qrcode - barcodes - scanned - smartphone - supermarket	22	28_qrcode_barcodes_scanned_smartphone
29	bbc - arrests - stickered - newcastle - misinformation	22	29_bbc_arrests_stickered_newcastle

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