Aspect-based currency of customer reviews: A novel probability-based metric to pave the way for data quality-aware decision-making

Abstract Customer reviews from digital platforms are a vital data resource for recommender and other decision support systems. The performance of these systems is highly dependent on the quality of the underlying data—particularly its currency. Existing metrics for assessing the currency of customer reviews are often based solely on data age. They do not consider that customer reviews can be outdated with respect to one aspect (e.g., guest room after renovation) while still being up-to-date with respect to others (e.g., location). Moreover, they disregard that customer reviews can only become outdated due to state changes of the corresponding item (e.g., renovation), which are associated with uncertainty. We propose a probability-based metric for the aspect-based currency of customer reviews. The values of the metric represent the probability that information in a set of customer reviews is still up-to-date. Our evaluation on a large TripAdvisor dataset shows that the values of the metric are reliable and discriminate well between up-to-date and outdated data, paving the way for data quality-aware decision-making based on customer reviews.