%0 Journal Article %A Kangas, Sara E.N. %T What can software tell us about political candidates?: A critical analysis of a computerized method for political discourse %D 2014 %J Journal of Language and Politics %V 13 %N 1 %P 77-97 %@ 1569-2159 %R https://doi.org/10.1075/jlp.13.1.04kan %K personality %K political election %K political discourse %K LIWC %I John Benjamins %X This study evaluates a computerized text analysis program, Linguistic Inquiry and Word Count (LIWC), by investigating the relationship between the discourse and personalities of presidential and vice presidential candidates in the 2008 presidential election in the United States. Analyses of speech samples (N = 141) from Barack Obama, Joe Biden, John McCain, and Sarah Palin were conducted using LIWC. The results show that in the context of political speech events, such as media interviews, political candidates make unique linguistic choices, which may be interpreted as displaying distinct personality traits. Yet, despite the statistical significance of the results, there are salient limitations of utilizing computerized methodologies to analyze political speech events, such as the limited interpretative capacity of the software to understand pragmatic and contextual language use. %U https://www.jbe-platform.com/content/journals/10.1075/jlp.13.1.04kan