Abstract
In the next point-of-interest (POI) recommendation, users may visit individual POIs within larger gathering places, such as shopping malls (termed as collective POIs), leading to uncertain check-ins. Our data analysis unveils that (1) the presence of such uncertain check-ins raises a new type of bias, termed as scale bias, that is, the recommender tends to recommend collective POIs over individual POIs, which further exacerbates the commonly-observed popularity bias, that is, the recommender tends to recommend popular POIs rather than unpopular ones; and (2) the existence of the above two types of biases significantly affects the fairness of next POI recommendation with uncertain check-ins. Therefore, we propose a Personalized Conversational Debiasing framework (PCDe) by exploiting the advantages of conversational techniques to capture personalized dynamic user preferences, thereby mitigating both scale and popularity biases at a personalized level. Specifically, the inquiry component designs an improved question-and-answer manner based on personalized information entropy, thus mitigating the scale bias. The rewarding component then introduces a novel debiasing reward mechanism based on the Jensen–Shannon divergence to make the recommendations better aligned with users’ historical preferences on popularity, thereby addressing the popularity bias. Extensive experiments demonstrate the superiority of our proposed PCDe over state-of-the-arts (SOTAs) regarding mitigating scale and popularity biases while enhancing recommendation accuracy thanks to its personalized debiasing mechanism.
•We propose personalized debiasing for next POI recommendation with uncertain check-ins.•We define scale bias from uncertain check-ins and analyze its relation to popularity bias.•We design a conversational framework with two components to address both bias types.•Experiments show our model improves both accuracy and fairness under uncertain check-ins.