Erik Cambria , Bing Liu , Yongzheng Zhang, Yunqing Xia
Twitter is one of the most popular micro-blogging services in the world, often studied in the context of political opinion mining for its peculiar nature of online public discussion platform. In our work we analyse the phenomenon of political disaffection defined as the “lack of confidence in the political process, politicians, and democratic institutions, but with no questioning of the political regime”. Disaffection for organised political parties and institutions has been object of studies and media attention in several Western countries. Especially the Italian case has shown a wide diffusion of this attitude. For this reason, we collect a massive database of Italian Twitter data (about 35 millions of tweets from April 2012 to October 2012) and we exploit scalable state-of-the-art machine learning techniques to generate time-series concerning the political disaffection discourse. In order to validate the quality of the time-series generated, we compare them with indicators of political disaffection from public opinion surveys. We find political disaffection on Twitter to be highly correlated with the indicators of political disaffection in the public opinion surveys. Moreover, we show the peaks in the timeseries are often generated by external political events reported on the main newspapers.
Proceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining. Wisdom '13, 2013
Political disaffection; Classification; Twitter; Sentiment Analysis
Main Research Area:
The 2nd International Workshop on Issues of Sentiment Discovery and Opinion Mining. Wisdom '13, 2013