Critiquing-based Modeling of Subjective Preferences

Applications designed for entertainment and other non-instrumental purposes are challenging to optimize because the relationships between system parameters and user experience can be unclear. Ideally, we would like to crowdsource these design questions, but existing approaches are geared towards systems evaluation or ranking discrete choices and not for optimizing over continuous parameter spaces. In addition, users are accustomed to informally expressing opinions about experiences as critiques (e.g. it was too cold, too spicy, too big), rather than give precise feedback as an optimization algorithm would require. Unfortunately, it can be difficult to analyze qualitative feedback, especially in the context of quantitative modeling. In this article, we present collective criticism, a critiquing-based approach for modeling relationships between system parameters and subjective preferences. Critiques, such as "it was too easy/too challenging", are transformed into intervals and modeled using interval regression. Collective criticism has several advantages over other approaches: "too much/too little"-style feedback is intuitive for users and allows us to build predictive models for the optimal parameterization of the variables being critiqued. We present two studies where we model: (i) aesthetic preferences for images generated with neural style transfer and (ii) users' experiences of challenge in the video game Tetris. These studies demonstrate the flexibility of our approach, and show that it produces robust results that are straightforward to interpret and inline with users' stated preferences.