Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources

www.ukp.tu-darmstadt.de “Always be yourself, unless you can be Batman. Then always be Batman.” – Bill Murray This study focuses on personality predic-tion of protagonists in novels based on the Five-Factor Model of personality. We present and publish a novel collaboratively built dataset of fictional character person-ality and design our task as a text classifi-cation problem. We incorporate a range of semantic features, including WordNet and VerbNet sense-level information and word vector representations. We evalu-ate three machine learning models based on the speech, actions and predicatives of the main characters, and show that espe-cially the lexical-semantic features signifi-cantly outperform the baselines. The most predictive features correspond to reported findings in personality psychology.