As people increasingly make hotel booking decisions relying on online reviews, how to effectively improve customer ratings has become a major point for hotel managers. Online reviews serve as a promising data source to enhance service attributes in order to improve online bookings. This paper employs online customer ratings and textual reviews to explore the bidirectional performance (good performance in positive reviews and poor performance in negative reviews) of hotel attributes in terms of four hotel star ratings. Sentiment analysis and a combination of the Kano model and importance-performance analysis (IPA) are applied. Feature extraction and sentiment analysis techniques are used to analyze the bidirectional performance of hotel attributes in terms of four hotel star ratings from 1,090,341 online reviews of hotels in London collected from TripAdvisor.com (accessed on 4 January 2022). In particular, a new sentiment lexicon for hospitality domain is built from numerous online reviews using the PolarityRank algorithm to convert textual reviews into sentiment scores. The Kano-IPA model is applied to explain customers’ rating behaviors and prioritize attributes for improvement. The results provide determinants of high/low customer ratings to different star hotels and suggest that hotel attributes contributing to high/low customer ratings vary across hotel star ratings. In addition, this paper analyzed the Kano categories and priority rankings of six hotel attributes for each star rating of hotels to formulate improvement strategies. Theoretical and practical implications of these results are discussed in the end.

Under the global consensus of carbon peaking and carbon neutrality, new energy vehicles have gradually become mainstream, driven by the dual crises regarding the atmospheric environment and energy security. When choosing new energy vehicles, consumers prefer to browse the post-purchase reviews and star ratings of various new energy vehicles on platforms. However, it is easy for consumers to become lost in the high-star text reviews and mismatched reviews. To solve the above two issues, this study selected nine new energy vehicles and used a multi-attribute decision making method to rank the vehicles. We first designed adjustment rules based on star ratings and text reviews to cope with the issue of high star ratings but negative text reviews. Secondly, we classified consumers and recommended the optimal alternative for each type of consumer to deal with the issue of mismatched demands between review writers and viewers. Finally, this study compared the ranking results with the sales charts of the past year to verify the feasibility of the proposed method initially. The feasibility and stability of the proposed method were further verified through comparative and sensitivity analyses.

Online travel website reviews contain abundant hotel attribute information. Nevertheless, evaluations of such hotel attributes are not completely objective, as they are affected by subjective perceptions from different types of travelers. This study explores the correlations of attribute perceptions across different traveler groups and optimizes hotel recommendation models from the perspective of attribute correlation. Hotel attributes are analyzed based on online reviews collected from TripAdvisor, and the TOPSIS method is used to identify the core attributes. The SentiWordNet sentiment lexicon and PolarityRank algorithm are utilized to calculate attribute sentiment values, which are then applied to OLS regression analysis to explore the relationships between attributes. Finally, a hotel recommendation model based on the collaborative filtering algorithm is constructed, incorporating traveler types and attribute correlation. The research results show core attributes for different types of travelers, verify the existence of attribute perception correlation, and demonstrate that a model considering attribute correlation enhances recommendation accuracy, with an accuracy improvement of 3.16 percentage points.