What it does
The goal of this project is to explore and analyse the variation in presidential candidates' emotions during debates. For that matter, we took as a sample the debate between Hillary Clinton and Bernie Sanders, which took place on February 4th, 2016.
How we built it
- All data processing was done in Python 3 with MongoDB as the database, connecting through pyMongo.
- Text and grep-hacking was done using Sublime Text 3 and Atom.
- The front-end has been implemented using jQuery, d3.js and nvd3.
- The video file was split sequentially using Matlab.
This project relies heavily on the following APIs:
- Microsoft® Project Oxford Video API
- Microsoft® Project Oxford Emotion API
- Alchemy® Entity Extraction API
Challenges we ran into
- Defining the scope of project.
- Tailoring the data.
- Merging data from various sources like matching the text with the image.
- Data conversion
Accomplishments that we're proud of
We brainstormed to define a project from scratch. we defined it and did it!
What we learned
- In the technical side we learnt how to use MongoDB and Project Oxford APIs.
- In the political side, a lot!
What's next for DEBATE IN EMOTION
- We are excited to analyse other debates specially in the Republicans side
- Real-time emotion analysis of debates by using speech to text api
- Possibly sentiment analysis of tweets using debate hashtags