The authors propose a quantitative approach for describing entertainment products, in a way that allows for improving the predictive performance of consumer choice models for these products. Their approach is based on the media psychology literature, which suggests that people’s consumption of entertainment products is influenced by the psychological themes featured in these products. They classify psychological themes on the basis of the “character strengths” taxonomy from the positive psychology literature (Peterson and Seligman 2004). They develop a natural language processing tool, guided latent Dirichlet allocation (LDA), that automatically extracts a set of features of entertainment products from their descriptions. Guided LDA is flexible enough to allow features to be informed by psychological themes while allowing other relevant dimensions to emerge. The authors apply this tool to movies and show that guided LDA features help better predict movie-watching behavior at the individual level. They find this result with both award-winning movies and blockbuster movies. They illustrate the potential of the proposed approach in pure content-based predictive models of consumer behavior, as well as in hybrid predictive models that combine content-based models with collaborative filtering. They also show that guided LDA can improve the performance of models that predict aggregate outcomes.