Trust and nuanced profile similarity in online social networks
ACM Transactions on the Web (TWEB)
Predicting personality with social media
CHI '11 Extended Abstracts on Human Factors in Computing Systems
| Hi-index | 0.00 |
Personality is an important factor that influences people's decisions, actions, and tastes. While previous research has used surveys to establish a connection between personality and media preferences, to date there has been no research that connects these attributes to users' opinions of and use of recommender systems nor to their movie rating and viewing histories. In this paper, we present our results on the relationship between personality and users' movie preferences, and their opinions about, use of, and trust in recommender systems. Using surveys and analysis of system data for 73 Netflix users, we show correlations between personality and preferences for specific movie genres that replicate and extend previous results. Our most significant result is that the personality trait of Conscientious is consistently positively correlated with a higher opinion about the usefulness and trustworthiness of recommendations, self-reports of how frequently they were used, and ratings of recommended items. We discuss the implications these results have for evaluating and improving recommender systems.