Perceptions of presidential candidates' personalities in twitter

Abstract

Political sentiment analysis using social media, especially T witter, has attracted wide interest in recent years. In such research, opinions about politicians are typically divided into positive, negative, or neutral. In our research, the goal is to mine political opinion from social media at a higher resolution by assessing statements of opinion related to the personality traits of politicians; this is an angle that has not yet been considered in social media research. A second goal is to contribute a novel retrieval‐based approach for tracking public perception of personality using G ough and H eilbrun's A djective C heck List ( ACL ) of 110 terms describing key traits. This is in contrast to the typical lexical and machine‐learning approaches used in sentiment analysis. High‐precision search templates developed from the ACL were run on an 18‐month span of T witter posts mentioning O bama and R omney and these retrieved more than half a million tweets. For example, the results indicated that R omney was perceived as more of an achiever and O bama was perceived as somewhat more friendly. The traits were also aggregated into 14 broad personality dimensions. For example, O bama rated far higher than R omney on the M oderation dimension and lower on the M achiavellianism dimension. The temporal variability of such perceptions was explored.