Full Program »
Incremental Hotel Recommendation with Inter-Guest Trust and Similarity Post-Filtering
Crowdsourcing has become an essential source of information for tourists and tourism industry. Every day, large volumes of data are exchanged among stakeholders in the form of searches, posts, shares, reviews or ratings. Specifically, this paper explores inter-guest trust and similarity post-filtering, using crowdsourced ratings collected from the Expedia and TripAdvisor platforms, to improve hotel recommendations generated by incremental collaborative filtering. First, hotels and guests are modelled using multi-criteria profiling. Then, incremental model-based collaborative filtering is applied to predict on-line hotel ratings and, finally, a post-recommendation filter based on the inter-guest trust and similarity sorts the generated predictions. The proposed method was tested in both off-line (static data) and on-line (dynamic data) scenarios for performance comparison. The results highlight the relevance of modelling and applying the inter-guest trust and similarity to improve the accuracy of on-line personalised recommendations. In terms of contributions, this work proposes: (i) an incremental hotel recommendation implementation; and (ii) a post-recommendation filter based on inter-guest trust and similarity.