Extracting Features of Entertainment Products: A Guided Latent Dirichlet Allocation Approach Informed by the Psychology of Media Consumption

Abstract

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.

Grounded reality meets machine learning: A deep-narrative analysis framework for energy policy research

“…A total of 311 documents were created in the DTM. It is a widely-used methodology for TM, and the cross-validation measures determine its reliability [42] , [66] , [69] , [70] . The third hyperparameter, gamma (γ) that controls the number of topics the algorithm will detect has to be set while implementing LDA.…”

“…More recently, LDA was used as a means of data-driven geotopic detection of urban emergencies for natural hazards, manmade disasters and other emergencies [40] . Topic modelling is now being used to map consumer sentiments and understanding their behavioural choices on a geographical scale for enhancing business potential [41] , [42] . Critical environmental and social problems are now being identified using twitter-based geo-topics that provide rich knowledge of important events (e.g., cultural activities, political campaigns, accidents, crisis) at an urban scale.…”

Marketing ecosystem: An outside-in view for sustainable advantage

“…For example, data from the Google Book corpus, news media, government reports, song lyric websites, and movie script databases can provide a wealth of information. Although these text generators are not the firm's customers, they could nevertheless shed light on broad consumer cultural trends such as tastes in movies (Toubia et al, 2019) and music (Berger & Packard, 2018).…”

A nested computational social science approach for deep-narrative analysis in energy policy research

“…More recently, LDA was used as a means of data-driven geotopic detection of urban emergencies for natural hazards, manmade disasters and other emergencies (Wang & Taylor, 2019). Topic modelling is now being used to map consumer sentiments and understanding their behavioural choices on a geographical scale for enhancing business potential (Qi, Procter, Zhang, & Guo, 2019;Toubia, Iyengar, Bunnell, & Lemaire, 2019). Critical environmental and social problems are now being identified using twitter-based geotopics that provide rich knowledge of important events (e.g., cultural activities, political campaigns, accidents, crisis) on an urban scale.…”