Source code to support semi-supervised, iterative bootstrapping process for the identification (and evaluation) of linguistic patterns encapsulating smell experiences in text.

Table of contents

• Thesis Paper
• Presentation
• Requirements
• Example run-through:

  • Catalogue all English language Project Gutenberg resources

    • Rank by high smell association keyword
    • Plot the keyword search frequences

  • Creating Harvesting, Validation and Evaluation datasets

  • Create the Gold Standard

  • Iterative bootstrapping process

  • Evaluation