What influences users to provide explicit feedback? A case of food delivery recommenders

Abstract

Abstract Although explicit feedback such as ratings and reviews are important for recommenders, they are notoriously difficult to collect. However, beyond attributing these difficulties to user effort, we know surprisingly little about user motivations. Here, we provide a behavioral account of the sparsity problem by theorizing the possible presence of feedback loops in user-recommender interactions. Specifically, we hypothesized that poorly motivated elicitation practices, accompanied by an algorithmic shift away from explicit feedback, might be inhibiting user feedback. To better understand underlying motivations, we administered a survey to measure constructs influencing the rating and review intentions of U.S. food delivery platform users (n = 796). Our model, combining the Technology Acceptance Model and Theory of Planned Behavior, revealed that standard industry practices for feedback collection appear misaligned with key psychological influences. Most notably, rating and review intentions were most influenced by subjective norms. This means that while most systems directly request feedback in user-to-provider relationships, eliciting them through social pressures that manifest in user-to-user relationships is likely more effective. Secondly, most hypothesized dimensions of feedback’s perceived usefulness recorded insignificant effects on feedback intentions. These disassociations provided clues for practitioners to improve perceptions through contextualized messaging. In addition, perceived pressure and users’ high stated ability to provide feedback recorded insignificant effects, suggesting that frequent feedback requests may be ineffective. Lastly, privacy concerns recorded insignificant effects, hinting that the personalization-privacy paradox might not apply to ratings and reviews. Our results provide a novel behavioral perspective to improve feedback collection in food delivery and beyond.