Analysis and prediction of hotel ratings from crowdsourced data

Crowdsourcing has become an essential source of information for tourism stakeholders. Every day, tourists leave large volumes of feedback data in the form of posts, likes, textual reviews, and ratings in dedicated crowdsourcing platforms. This behavior makes the analysis of crowdsourced information strategic, allowing the discovery of important knowledge regarding tourists and tourism resources. This paper presents a survey on the analysis and prediction of hotel ratings from crowdsourced data, covering both off‐line (batch) and on‐line (stream‐based) processing. Specifically, it reports multiple rating‐based profiling, recommendation, and evaluation techniques. While most of the surveyed works adopt entity‐based multicriteria profiling, prerecommendation filtering, and off‐line processing, the latest hotel rating prediction trends include feature‐based, trust and reputation modeling, postrecommendation filtering, and on‐line processing. Additionally, since the volume of crowdsourced ratings tends to increase, the deployment of profiling and recommendation algorithms on high‐performance computing resources should be further explored. This article is categorized under: Application Areas > Internet and Web‐Based Applications We present a state‐of‐the‐art review on off‐line and on‐line hotel recommendation supported by crowdsourced ratings, which covers profiling (single and multicriteria rating together with trust & reputation modeling), prediction, and evaluation.