POPSTAR (Public Opinion Sentiment Tracking, Analysis, and Research)


POPSTAR is a collaborative research initiative by ICS-UL, INESC-ID, FEUP and NIPE-UM that explores web-based conventional and social media with text mining and generates indicators of both frequency and polarity (positivity/negativity) of mentions to political actors, the economy, and economic policies across sources, types of sources, and across time. The project is funded by the Portuguese Science Foundation. Our ultimate goal is to analyze the relationship between survey/poll-based indicators of public opinion and indicators of salience and polarity of opinion in web-based conventional and social media texts. My role in the project is to collect and manage the dataset of public opinion surveys published in the media and to update the website with new data available.