DigitsignProjects Sentiment visualization on live Political Tweets

Sentiment visualization on live Political Tweets

In partnership with the University of Antwerp (spinoff project textgain), we organised a series of sentiment visualization experiments on live Political Tweets produced during the run-up to the Dutch local-election to determine whether a tweet is positive, negative or neutral.This project aims to process live Twitter’s data both automatically with sentiment analysis algorithms, and also manually using annotation to produce qualitative trend judgements and determine whether voters are talking positively or negatively about a specific topic e.g. health care, immigration, EU,…
we were interested in how the public views the top election candidates. To achieve a large, diverse dataset of current public opinions on the candidates, we decided to use Twitter.
Politieketrend Project