MARTINI_enrich_BERTopic_Anti_Feminist_Gang

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_Anti_Feminist_Gang")

topic_model.get_topic_info()

Topic overview

• Number of topics: 42
• Number of training documents: 6617

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	rape - feminst - पर - raha - india	21	-1_rape_feminst_पर_raha
0	feminsts - misogynist - ladkiyon - isliye - chanakya	3753	0_feminsts_misogynist_ladkiyon_isliye
1	ladkiyan - bhai - dekho - durga - priyadarshani	270	1_ladkiyan_bhai_dekho_durga
2	hindus - jainism - sanatana - atharveda - atheistic	234	2_hindus_jainism_sanatana_atharveda
3	promiscuity - virginity - marry - oxytocin - brahmachraya	212	3_promiscuity_virginity_marry_oxytocin
4	antihindu - bjp - jihad - hitler - modi	204	4_antihindu_bjp_jihad_hitler
5	shaadi - bhai - vivah - rahul - brahmachraya	141	5_shaadi_bhai_vivah_rahul
6	hypergamy - attractive - strong - bodybuilder - males	126	6_hypergamy_attractive_strong_bodybuilder
7	brainwashed - anyway - arguments - rekt - dumb	120	7_brainwashed_anyway_arguments_rekt
8	feminazi - misogynistic - bitches - shit - brainwash	112	8_feminazi_misogynistic_bitches_shit
9	bhaasha - khudaai - pehle - tujhe - samjega	96	9_bhaasha_khudaai_pehle_tujhe
10	tumhare - dikhayega - chaar - dad - mohalla	90	10_tumhare_dikhayega_chaar_dad
11	gendered - dysphoria - stereotypes - socity - natural	90	11_gendered_dysphoria_stereotypes_socity
12	feminsts - rape - men - punishment - biased	81	12_feminsts_rape_men_punishment
13	rape - allegations - rajveer - falsely - bail	79	13_rape_allegations_rajveer_falsely
14	grp - pleasebahar - bnayega - kharab - chodu	63	14_grp_pleasebahar_bnayega_kharab
15	equality - patriarchy - samaj - haramipanti - ladies	63	15_equality_patriarchy_samaj_haramipanti
16	policewala - safai - shekhar - ladkiys - khilooo	60	16_policewala_safai_shekhar_ladkiys
17	housewife - equal - hardwork - dhundti - income	59	17_housewife_equal_hardwork_dhundti
18	lgbtq - homophobic - marginalises - hilaunga - btayege	54	18_lgbtq_homophobic_marginalises_hilaunga
19	fraud - cases - patekar - badhte - victims	50	19_fraud_cases_patekar_badhte
20	porn - belissa - empowered - sister - aapka	45	20_porn_belissa_empowered_sister
21	bhai - mujse - rishtedaro - rudrani - madhvi	42	21_bhai_mujse_rishtedaro_rudrani
22	rape - uttarakhand - bachayega - victims - mujhee	41	22_rape_uttarakhand_bachayega_victims
23	alimony - dowry - shadi - wali - sudhregi	41	23_alimony_dowry_shadi_wali
24	crimee - women - kabhi - victim - isliye	40	24_crimee_women_kabhi_victim
25	ladkiya - jagha - manipur - reserved - castism	37	25_ladkiya_jagha_manipur_reserved
26	ramji - joked - muslims - madhuri - smjhaarha	35	26_ramji_joked_muslims_madhuri
27	vedio - youtube - jagrukta - bharmachari - anyaye	33	27_vedio_youtube_jagrukta_bharmachari
28	muslims - quranic - muhammad - superstitions - haleem	32	28_muslims_quranic_muhammad_superstitions
29	rape - consensual - ladki - sakta - लय	31	29_rape_consensual_ladki_sakta
30	pornography - masturbating - objectification - watching - empowering	30	30_pornography_masturbating_objectification_watching
31	genders - unequally - compulsory - leadership - segregates	26	31_genders_unequally_compulsory_leadership
32	misogynist - metoo - barkha - deepika - false	24	32_misogynist_metoo_barkha_deepika
33	ladkiyi - teachers - dekho - badha - homework	24	33_ladkiyi_teachers_dekho_badha
34	ladkiyi - rakhegi - parinaam - duniya - nature	24	34_ladkiyi_rakhegi_parinaam_duniya
35	argue - tumhari - sahaanubhooti - baar - kalank	24	35_argue_tumhari_sahaanubhooti_baar
36	violences - casemai - surpanakha - daughters - vajh	23	36_violences_casemai_surpanakha_daughters
37	naukri - dhoondti - chaprasi - jobless - jaataa	22	37_naukri_dhoondti_chaprasi_jobless
38	slaves - islamic - muhammed - racism - african	22	38_slaves_islamic_muhammed_racism
39	twitter - influencer - plz - kangana - bjp	22	39_twitter_influencer_plz_kangana
40	bollywood - amitabh - salman - varun - villian	21	40_bollywood_amitabh_salman_varun

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