MARTINI_enrich_BERTopic_GoodLionNews

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_GoodLionNews")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 28
  • Number of training documents: 3150
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 fauci - redpills - full - podcast - pervywood 20 -1_fauci_redpills_full_podcast
0 lies - phildo - sued - followers - idiot 1439 0_lies_phildo_sued_followers
1 netflix - youtube - bitchute - lion - great 302 1_netflix_youtube_bitchute_lion
2 xrp - redpills - netflix - conspiracy - telegram 199 2_xrp_redpills_netflix_conspiracy
3 mariupol - zelensky - russians - kazakhstan - sanctions 142 3_mariupol_zelensky_russians_kazakhstan
4 trumps - biden - ballots - cnn - mccarthy 85 4_trumps_biden_ballots_cnn
5 epstein - tucker - liondisclosure1 - headlines - trafficking 81 5_epstein_tucker_liondisclosure1_headlines
6 ariibrand - detox - autistic - oils - soni 74 6_ariibrand_detox_autistic_oils
7 patriot - discount - episodes - july - mugclub 74 7_patriot_discount_episodes_july
8 redpill - netflix - documentary - uncover - bolshevik 73 8_redpill_netflix_documentary_uncover
9 pill - budweiser - risen - happydays - unapologetically 59 9_pill_budweiser_risen_happydays
10 arrested - prisoners - nicolas - patriots - january 58 10_arrested_prisoners_nicolas_patriots
11 lion - good - streaming - exclusives - audiobooks 50 11_lion_good_streaming_exclusives
12 migrants - assaulted - prostitutes - lybia - belfast 46 12_migrants_assaulted_prostitutes_lybia
13 thetruthseekerschannel - greatest - show - lion - nashville 40 13_thetruthseekerschannel_greatest_show_lion
14 sctransformyourhealth - website - doctor - plandemic - vein 40 14_sctransformyourhealth_website_doctor_plandemic
15 murdered - michael - murdoch - winehouse - naked 39 15_murdered_michael_murdoch_winehouse
16 redpill - netflix - website - links - discover 38 16_redpill_netflix_website_links
17 tartarians - empire - cherokee - mongol - egypt 34 17_tartarians_empire_cherokee_mongol
18 kubrick - moon - nasa - landings - 1969 33 18_kubrick_moon_nasa_landings
19 terrorists - riots - gendarmerie - marseille - belgium 32 19_terrorists_riots_gendarmerie_marseille
20 pedophiles - lgbtq - traffickers - arrested - audrey 32 20_pedophiles_lgbtq_traffickers_arrested
21 zionists - israel - netanyahu - mossad - gaza 31 21_zionists_israel_netanyahu_mossad
22 tartaria - liondisclosure - episodes - vip - discounts 30 22_tartaria_liondisclosure_episodes_vip
23 pervywood - hollywood - creepiest - oprah2 - figureheads 28 23_pervywood_hollywood_creepiest_oprah2
24 trudeau - ontario - trucker - convoys - freedom 26 24_trudeau_ontario_trucker_convoys
25 footballer - panthers - died - collapses - flu 25 25_footballer_panthers_died_collapses
26 vaccine - luciferase - detected - pzifer - syncytial 20 26_vaccine_luciferase_detected_pzifer

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
Downloads last month
4
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.