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

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1805–1816, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Personality Profiling of Fictional Characters using Sense-Level Links between Lexical Resources Lucie Flekova† and Iryna Gurevych†‡ † Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit¨at Darmstadt ‡ Ubiquitous Knowledge Processing Lab (UKP-DIPF) German Institute for Educational Research www.ukp.tu-darmstadt.de “Always be yourself, unless you can be Batman. Then always be Batman.” – Bill Murray Abstract 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. 1 Introduction Recent progress in NLP has given rise to the field of personality profiling - automated classification of personality traits based on written, verbal and multimodal behavior of an individual. This re- search builds upon findings from classical person- ality psychology and has applications in a wide range of areas from medicine (suicide prevention) across security (forensics, paedophile detection, cyberbullying) to marketing and sales (recommen- dation systems, target group profiles). The gold standard labels for an objective evaluation of per- sonality are mostly obtained by means of personal- ity tests of the Five Factor Model (FFM) (McCrae and Costa, 1987; Goldberg, 1990), which is well- known and widely accepted in psychology and other research fields. The FFM defines personality along five bipolar scales: Extraversion (sociable vs. reserved), Emotional stability (secure vs. neu- rotic), Agreeableness (friendly vs. unsympathic), Conscientiousness (organized vs. careless) and Openness to experience (insightful vs. unimagi- native). Psychologists have shown that these five personality traits are stable across individual lifes- pan, demographical and cultural differences (John and Srivastava, 1999) and affect many life aspects. (Terracciano et al., 2008; Rentfrow et al., 2011). It has been shown that the personality traits of readers impact their literature preferences (Tirre and Dixit, 1995; Mar et al., 2009). Psychology researchers also found that perceived similarity is predictive of interpersonal attraction (Montoya et al., 2008; Byrne, 1961; Chartrand and Bargh, 1999). More explicitly, recent research (Kaufman and Libby, 2012) shows that readers of a narrative develop more favorable attitudes and less stereo- type application towards a character, if his differ- ence (e.g. racial) is revealed only later in the story. We therefore hypothesize that readers might have a preference for reading novels depicting fictional characters that are similar to themselves. Finding a direct link between reader’s and protagonist’s per- sonality traits would advance the development of content-based recommendation systems. As a first step to explore this hypothesis further, it needs …

Content truncated to 500 words