Edit model card

BERTopic-Indonesia-Finance-News

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:

'''
Topic 0 -> Impact of Federal Reserve Tapering on Indonesia Financial Markets
Topic 1 -> Initial Public Offering (IPO) in Indonesia State-Owned Entreprise (BUMN)
Topic 2 -> Restructuring and Transformation of Banking in Indonesia
Topic 3 -> Impact of China's Economic Slowdown on Indonesia International Trade and Investment
Topic 4 -> Exchange Rate of Indonesian Rupiah (to US Dollar)
Topic 5 -> Legal Proceedings In Indonesian
Topic 6 -> Insurances and Membership in Indonesia
Topic 7 -> Bank Indonesian's Economics Policies and Stability Measures
'''
from bertopic import BERTopic
topic_model = BERTopic.load("ZhafranR/BERTopic-Indonesia-Finance-News")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 8
  • Number of training documents: 74933
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
0 penguatan - menguat - ihsg - acuan - kamis 28336 0_penguatan_menguat_ihsg_acuan
1 perseroan - keterbukaan - sepekan - kepemilikan - hmetd 12504 1_perseroan_keterbukaan_sepekan_kepemilikan
2 perseroan - penyaluran - restrukturisasi - otoritas - transformasi 11737 2_perseroan_penyaluran_restrukturisasi_otoritas
3 sekuritas - ihsg - squawk - saksikan - cnbcindonesia 9410 3_sekuritas_ihsg_squawk_saksikan
4 menguat - penguatan - sekuritas - terpantau - jakarta 8680 4_menguat_penguatan_sekuritas_terpantau
5 penyidikan - diperiksa - kejagung - penyidik - persidangan 2616 5_penyidikan_diperiksa_kejagung_penyidik
6 iurannya - ketenagakerjaan - kepesertaan - pemberi - dibayarkan 1317 6_iurannya_ketenagakerjaan_kepesertaan_pemberi
7 likuiditas - pencatatan - berkelanjutan - sukuk - cyclicals 333 7_likuiditas_pencatatan_berkelanjutan_sukuk

Training hyperparameters

  • calculate_probabilities: False
  • language: None
  • low_memory: False
  • min_topic_size: 100
  • n_gram_range: (1, 2)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 20
  • verbose: True

Framework versions

  • Numpy: 1.24.1
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.4
  • Pandas: 1.5.3
  • Scikit-Learn: 1.3.2
  • Sentence-transformers: 2.2.2
  • Transformers: 4.35.0
  • Numba: 0.57.1
  • Plotly: 5.18.0
  • Python: 3.10.6
Downloads last month
7