Rational, Emotional, and Attentional Choice Models for Recommender Systems
- 1.2k Downloads
This work analyzes the decision-making process underlying choice behavior. First, neural and gaze activity were recorded experimentally from different subjects performing a choice task in a Web Interface. Second, choice models were fitted using rational, emotional and attentional features. The model’s predictions were evaluated in terms of their accuracy and rankings were made for each user. The results show that (1) the attentional models are the best in terms of its average performance across all users, but (2) each subject shows a different best model.
KeywordsRecommender systems Decision-making Dual Process Theory Choice models
We want to acknowledge the collaboration of Movistar, the leading Spanish Telco, which provided the list of real movies that were used as stimuli during the choice experiments.
- 1.Saavedra, P., Barreiro, P., Duran, R., Crujeiras, R., Loureiro, M., Vila, E.S.: Choice-based recommender systems. In: RecTour@ RecSys, pp. 38–46 (2016)Google Scholar
- 3.Kahneman, D.: Think Fast, Think Slow. Farrar, Straus and Giroux, New York (2011)Google Scholar
- 4.Scott, J.: Rational choice theory, p. 129. Understanding Contemporary Society, Theories of the Present (2000)Google Scholar
- 6.Pradeep, A.K., Patel, H.: The Buying Brain: Secrets for Selling to the Subconscious Mind. Wiley, Hoboken (2010)Google Scholar
- 8.McFadden, D.: Conditional logit analysis of qualitative choice behavior (1973)Google Scholar
- 9.Croissant, Y.: Estimation of multinomial logit models in R: the mlogit packages. R package version 02–2 (2012)Google Scholar