Trust and Reputation Modelling for Tourism Recommendations Supported by Crowdsourcing

摘要: Tourism crowdsourcing platforms have a profound influence on the tourist behaviour particularly in terms of travel planning. Not only they hold opinions shared by other tourists concerning tourism resources, but, with help recommendation engines, are pillar personalised resource recommendation. However, since prospective unaware trustworthiness or reputation crowd publishers, fact taking leap faith when then rely wisdom. In this paper, we argue that modelling publisher Trust & Reputation improves quality recommendations supported crowdsourced information. Therefore, present system which integrates: (i) user profiling using multi-criteria ratings; (ii) k-Nearest Neighbours (k-NN) prediction (iii) modelling; and (iv) incremental model update, i.e., providing near real-time recommendations. contributions, paper provides two different approaches: general employing pairwise trust values all users; neighbour-based common neighbours. The proposed method was experimented datasets from Expedia TripAdvisor platforms.