What is ActiveTigger?

ActiveTigger1 is an open-source software designed to support collaborative text annotation for computational social sciences. It is designed to assist exploration and model fine-tuning (BERT) to annotate text datasets relying on active learning.

ActiveTigger could help you if you…

  • want to classify large datasets of texts (social media posts, news articles...)
  • are working collaboratively with other human annotators
  • want to get an overview of key topics in your text data
  • are curious about supervised machine learning for text and want an easy introduction

How to start?


  1. The current version is a refactor of R Shiny ActiveTigger app (Julien Boelaert & Etienne Ollion). ActiveTigger name is a pun that draws on the similarity between the words 'Tagger' and 'Tigger', and the possibility to use active learning (and yes, we're aware that good jokes shouldn't need a footnote).