From star rating to sentiment rating: using textual content of online reviews to develop more effective reputation systems for peer-to-peer accommodation platforms

ABSTRACT Star ratings on P2P accommodation platforms are highly positive. Such biases have led many users to utilise selective processing strategies to evaluate the textual content of online reviews. However, when many reviews are available for a product or a service, these strategies would be suboptimal at best, posing several challenges to the users of peer-to-peer (P2P) accommodation platforms. To enable the guests to perform more informed evaluations and overcome the challenges that the skewed distribution of star ratings creates for decision-making, we employ content analysis tools to derive an aggregated sentiment score for each listing. Using this score, we define a new measure, called “sentiment rating”, that compares a listing with other similar listings based on their textual reviews. Our choice-based conjoint experiment suggests that unlike users’ initial perception about the function of star rating as the most salient factor in evaluating P2P listings, users actually attribute more importance to sentiment ratings of P2P accommodations. Therefore, a text-based summary of online reviews would indeed help users in evaluating alternatives on a P2P platform and in decision making. We argue that a text-based quantitative summary of user reviews could be a useful supplements to (or substitutes for) star ratings on P2P accommodation platforms and even online retailing websites.