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

Abstract

This study focuses on personality prediction of protagonists in novels based on the Five-Factor Model of personality. We present and publish a novel collaboratively built dataset of fictional character personality and design our task as a text classification problem. We incorporate a range of semantic features, including WordNet and VerbNet sense-level information and word vector representations. We evaluate three machine learning models based on the speech, actions and predicatives of the main characters, and show that especially the lexical-semantic features significantly outperform the baselines. The most predictive features correspond to reported findings in personality psychology.

Deep Dungeons and Dragons: Learning Character-Action Interactions from Role-Playing Game Transcripts

“…This work focuses on infering the latent ties between actions and characters, and whether one aspect can help predict the other. Flekova and Gurevych (2015) present recent work related to this latter idea. They classify characters based on their speech and actions into an introvert or extrovert class.…”

Advances in Machine Learning for the Behavioral Sciences

“…Similarly, in (Komisin and Guinn, 2012), SVM and Bayes classifiers were used to identify persona types based on word choice. Profiling using SVMs was also successfully applied for distinguishing among fictional characters (Flekova and Gurevych, 2015).…”

Analyzing Framing through the Casts of Characters in the News

“…Much NLP has focused on identifying entities or events (Ratinov and Roth, 2009;Ritter et al, 2012), analyzing schemes or narrative events in terms of characters (Chambers and Jurafsky, 2009), inferring the relationships between entities (O' Connor et al, 2013;Iyyer et al, 2016), and predicting personality types from text (Flekova and Gurevych, 2015). Bamman also applied variants of the DPM to characters in novels (Bamman et al, 2014).…”