Inspiration
*The 2016 elections!!!! *
What it does
It analyzes Tweets about candidates in geographical locations and cross references with economic and political data to show and predict correlations about users and their political proclivities.
How we built it
We used Tweepy, a Twitter API to retrieve public tweets. We used Python to parse the Tweets and created an algorithm that predicts whether Tweets have positive or negative opinion towards the candidate. We then used GeoCharts to show the statistics on a map.
Challenges we ran into
We couldn't use get geocode to show the location so we had to generate and parse the data ourselves. GeoCharts is limited in that it can only show one statistic at a time.
Accomplishments that we're proud of
We managed to create an algorithm to parse a tweet for positive or negative sentiment.
What we learned
How to get Twitter data, how to mine data, how to format in JSON, how to use csv and GeoCharts
What's next for GeoStats
We will implement a real machine learning algorithm to predict whether the tweet is positive or negative.
Built With
- geocharts
- javascript
- jquery
- python
- tweepy
Log in or sign up for Devpost to join the conversation.