/Fun-Text-Mining-with-Simpsons

Exploratory data analysis for approximately 600 Simpsons episodes and scripts, topic modeling and text generation.

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Fun Text Mining with Simpsons

Exploratory data analysis for approximately 600 Simpsons episodes and scripts, topic modeling and text generation.

Table of Content

  • Identify most on-screen characters
  • Group the most common words for each character (WordClouds)
  • Vectorizing
    • Bag-Of-Words
    • TF-IDF
    • Word-Vector (Google's Word2Vec)
  • Sentiment Analysis
  • Topic Modeling
  • Best & worst episode

Credits, Sources & Links