Description / Project Intention

During times of crisis, social media has been the main platform for airing opinions, good and bad, practical and absurd. These can make for a read that’s informational, entertaining, or a combination of both. Our Twitter mood analyzer will take a user-provided tweet thread and using IBM’s Tone Analyzer, display the overall emotion of each post and its series of responses as a map of colorful points. The user can click on these points to see a more detailed breakdown of how the Tone Analyzer understood the nuances of a particular response. The analyzed tweet will also be embedded on this page for direct comparison.


COVID-19 was partially an inspiration, but we also wanted something that could be used as a light search tool for curiosity during large (or small) scale events that generate discussion. Our web app allows others to hone in on specific Tweets conveying a specific emotion in a conversation. Instead of reading through comments one by one, they can start with a Tweet that sparks interest, whether they're looking for positive content for comfort or angry statements for informational purposes.

What We Learned

Learning New Concepts:

  • Data Models: many-to-many, one-to-many, many-to-one (+ unidirectional/bidirectional variants)

Learning New Frameworks:

  • ORMs/databases
  • Bootstrap
  • Flask

Best Practices:

  • Consistency in design: visually and structurally
  • Organization
  • Distribution of tasks (backend vs. frontend distinction)
  • Directory structuring & packaging
  • Proper use of version control (Git)


  • Avoiding merge conflicts
  • Switching / handing off tasks
  • Checking in with each other
  • Discussing major changes with the entire team before committing
+ 2 more
Share this project: