In modern politics, parties and individual candidates must have an online presence and usually have dedicated social media coordinators. In this context, we study the usefulness of analysing Twitter messages to identify both the characteristics of political parties and the political leaning of users. As a case study, we collected the main stream of Twitter related to the 2010 UK General Election during the associated period—gathering around 1,150,000 messages from about 220,000 users. We examined the characteristics of the three main parties in the election and highlighted the main differences between parties. First, the retweet structure is highly clustered according to political parties. Second, users are more likely to refer to their preferred party and use more positive affect words for the party compared with other parties. Finally, the self-description of users and the List feature can reflect the political orientation of users. From these observations, we develop both an incremental and practical classification method which uses the number of Twitter messages referring to a particular political party or retweets, and a classifier leveraging the valuable semantic content of the List feature to estimate the overall political leaning of users. The experimental results showed that the proposed incremental method achieved an accuracy of 86 % for classifying the users’ political leanings and outperforms other classification methods that require expensive costs for tuning classifier parameters and/or knowledge about network topology. This advantage allows this approach to be a good candidate for social media analytics application in real time for political institution. The proposed method using List feature, in turn, achieved an accuracy of 92 %.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below