Interactive Feedback Loop with Counterfactual Data Modification for Serendipity in a Recommendation System

AbstractUsers often encounter tedious recommendations as they are continuously exposed to the recommendation system. In response to this issue, serendipity in a recommendation system has been introduced to generate novel and unexpected recommendations while keeping them relevant to users' previous preferences. This study proposes an interactive feedback loop for a serendipity in a recommendation system that allows users to directly explore content via counterfactual manipulation of features. Specifically, users indicate their preferences through the "what-if" based customization of content meta-information, and these modifications influence their usage history, thereby enabling the elicitation of serendipitous items. To validate the proposed feedback loop, we conducted a scenario-based experiment and compared system-initiated and user-intervened recommendations. The results reveal that counterfactual exploration can help to generate serendipitous recommendations. This study contributes to providing a user-friendly recommendation system that can retrieve preference-reflected recommendations through user interaction.Keywords: Recommendation systemserendipityinteractive machine learningcounterfactual data modificationhuman intervention Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No.2022-0-00078, Explainable Logical Reasoning for Medical Knowledge Generation).Notes on contributorsGyewon JeonGyewon Jeon is a graduate student in Department of Industrial and Management Engineering at Korea University. His academic interests lie in Serendipitous Recommender System, Interactive Machine Learning, and Human Artificial Intelligence Interaction.Sangyeon KimSangyeon Kim is a visiting scholar in North Carolina State University. He has obtained his PhD degree from Sungkyunkwan University in 2022. His academic interests lie in HCI, Intelligent user interface, and accessible computing.Sangwon LeeSangwon Lee is a Professor in School of Industrial and Management Engineering at Korea University. He has obtained his PhD and Master degrees from the Pennsylvania State University in 2010 and 2006, respectively. Also, he has graduated as B.S. from Korea University in 2004. His academic interests lie in HCI, UX, XAI, and affective computing.