Year: 2015
Type: conference-paper
Abstract: Several studies have shown how to approximately predict public opinion, \nsuch as in political elections, by analyzing user activities in blogging platforms \nand on-line social networks. The task is challenging for several reasons. \nSample bias and automatic understanding of textual content are two of several \nnon trivial issues. \nIn this work we study how Twitter can provide some interesting insights concerning \nthe primary elections of an Italian political party. State-of-the-art approaches \nrely on indicators based on tweet and user volumes, often including sentiment \nanalysis. We investigate how to exploit and improve those indicators in order to \nreduce the bias of the Twitter users sample. We propose novel indicators and a \nnovel content-based method. Furthermore, we study how a machine learning approach \ncan learn correction factors for those indicators. Experimental results on \nTwitter data support the validity of the proposed methods and their improvement \nover the state of the art.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2282573215