Back To Schedule
Debate in (E)motion
Feedback form is now closed.
Feedback Submitted
Speakers 
Columbia University - Facultad de Ingeniería UBA
Xavier Ignacio González is a Data Scientist with +15 years of experience in the Industry and Academia. In Argentina, his home country, he completed an Industrial Engineering Major in the University of Buenos Aires. Before graduation, he started working for big companies like IBM...
Read More →
Media Fair
- twitter @xavierign
- whereYouLive Buenos Aires
- checkInDay 42991
- checkOutDay 42993
- cityOfOrigin Buenos Aires
- Have you been to Media Party bef yes
- MF url carlosespino11.github.io/devfest2016/#
- MF terms conditions true
- MF logo www.columbia.edu/~xig2000/link/Slide1.jpg
- MF description Debate in (E)motion The goal of this project is to add a new narrative to political debates by detecting exploring, and analysing emotions of presidential candidates during debates. To do so, we took as a sample the debate between Hillary Clinton and Bernie Sanders, which took place on February 4th, 2016. We did this analysis in two sections: the first one corresponds to the emotion shown by the facial expression of the candidates (one timeline for each candidate) using Microsoft Oxford APIs and the second one consists in entity extraction and sentiment based on their transcribed speech using Alchemy API. Other technologies used in the project are Python for processing, MongoDB for database (connecting through pyMogo), The front-end has been implemented using jQuery, d3.js and nvd3, and Matlab for video processing. The project was demonstrated during NYC medial Lab'16 at Columbia university and won the honourable mention. It was initially developed in a 24hr hackathon using the Microsoft Oxford API and Alchemy API and we won the Microsoft Prize. Team members: Carlos Espino (Mexico) Amirhos Imani (Iran) Xavier González (Argentina) Diego Llarrull (Argentina)
