Exploring the Value of Personality in Predicting Rating Behaviors

Abstract

Prior work relevant to incorporating personality into recommender systems falls into two categories: social science studies and algorithmic ones. Social science studies of preference have found only small relationships between personality and category preferences, whereas, algorithmic approaches found a little improvement when incorporating personality into recommendations. As a result, despite good reasons to believe personality assessments should be useful in recommenders, we are left with no substantial demonstrated impact. In this work, we start with user data from a live recommender system, but study category-by-category variations in preference (both rating levels and distribution) across different personality types. By doing this, we hope to isolate specific areas where personality is most likely to provide value in recommender systems, while also modeling an analytic process that can be used in other domains. After controlling for the family-wise error rate, we find that High Agreeableness users rate at least 0.5 stars higher on a 5-star scale compared to low Agreeableness users. We also find differences in consumption in four different personality types between people who manifested high and low levels of that personality.

Preference modeling by exploiting latent components of ratings

“…In order to evaluate the accuracy of our method, five benchmark datasets are selected, namely MovieLens, Douban, Movietweetings, Epinions and Goodreads. MovieLens is a movie recommendation website, which uses individual users' rating to generate personalized recommendations [21]. Douban, launched on March 6, 2005, is a Chinese Web 2.0 web site providing user reviews and recommendation services of movies, books, and music [18].…”

Eudaimonic Modeling of Moviegoers

“…We further used the TIPI instrument to measure personality [4] in terms of the five factors openness, conscientiousness, extraversion, agreeableness and neuroticism. We used the [1,5] scale.…”

“…Among several models of personality the most widely used is the Five Factor Model (FFM), which contains the following factors: openness, conscientiousness, extraversion, agreeableness and neuroticism [7]. Several works has shown that personality is related to user preferences for entertainment content, such as music [3,10,12] and movies [5].…”

Engagement in proactive recommendations

“…Regarding trait Extraversion, for instance, early studies reported negative effects of trait Extraversion on engagement, under the assumption that people high on Extraversion would favor offline social interaction over online social interaction (Amichai-Hamburger et al 2002). The negative effect of Extraversion on user engagement is sometimes replicated (Karumur et al 2016), but more often contradicted. Among others, people engaging in online games tend to be higher on trait Extraversion (Teng 2008).…”