The Psychological Underpinnings of Conservative/Liberal Ideology in the Australian Federal Parliament: A Computational Linguistic Analysis

The purpose of this article is to examine the psychological underpinnings of the conservative/liberal ideological spectrum in the Australian Federal Parliament. The cohort consists of the 485 Labor, Liberal and National parliamentarians who were in parliament over the period April 1996 to July 2014. I use computational linguistics to extract linguistic variables from first speeches in parliament of those in the cohort. I then draw from methods used in machine learning to develop a classifier which has a 74% out of sample (LOOCV) accuracy in classifying parliamentarians as liberal (ALP) or conservative (Liberal/National). Finally, I examine the salient variables and find that there are five linguistic markers of conservative/liberal ideology in the Australian federal parliament. Of these, four are consistent with the previous findings that liberals tend to display more psychological “openness” than conservatives and less psychological “conscientiousness”. However, there is one variable that strongly challenges the idea that conservatives look to the past and liberals to the future. I support this finding with a discussion of extracts from speeches that represent the extreme ends of the spectrum.