Edit model card

BERTopic_hurricane_tweet

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("cindyangelira/BERTopic_hurricane_tweet")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 11
  • Number of training documents: 811
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 medicare - theft - medical - harvey - identity 1 -1_medicare_theft_medical_harvey
0 gofundme - donate - houstonstrong - texas - houston 111 Weather Updates
1 plaza - txmedcenter - medical - instagram - here 516 Relief Efforts
2 hurricaneharvey - houston - harvey - hurricane - houstonflood 74 Rescue Operations
3 harvey - hurricane - flooded - houston - tx 33 Flooding Reports
4 houston - astros - harvey - snow - houstonstrong 28 Storm Damage Reports
5 harvey - reliefforharvey - hurricaneharvey - relief - houstonians 23 5_harvey_reliefforharvey_hurricaneharvey_relief
6 rescued - hurricaneharvey - - - 14 6_rescued_hurricaneharvey__
7 hurricaneharvey - hurricane - - - 4 7_hurricaneharvey_hurricane__
8 harvey - flooding - houston - floodwaters - flood 4 8_harvey_flooding_houston_floodwaters
9 houston - hurricaneseason - hurricaneharvey - harvey - weather 3 9_houston_hurricaneseason_hurricaneharvey_harvey

Training hyperparameters

  • calculate_probabilities: False
  • language: None
  • low_memory: False
  • min_topic_size: 15
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: False
  • zeroshot_min_similarity: 0.85
  • zeroshot_topic_list: ['Weather Updates', 'Evacuation Information', 'Emergency Services', 'Relief Efforts', 'Rescue Operations', 'Flooding Reports', 'Traffic and Road Closures', 'Government and Local Authority Announcements', 'Personal Stories and Experiences', 'Storm Damage Reports', 'Others']

Framework versions

  • Numpy: 1.26.4
  • HDBSCAN: 0.8.38.post1
  • UMAP: 0.5.6
  • Pandas: 2.2.2
  • Scikit-Learn: 1.2.2
  • Sentence-transformers: 3.1.0
  • Transformers: 4.44.0
  • Numba: 0.60.0
  • Plotly: 5.22.0
  • Python: 3.10.14
Downloads last month
2
Inference Examples
Inference API (serverless) is not available, repository is disabled.