Muhammad, KhalilKhalilMuhammadLawlor, AonghusAonghusLawlorSmyth, BarryBarrySmyth2017-11-062017-11-062016 Assoc2016-05-18http://hdl.handle.net/10197/9032FLAIRS 2016, the 29th International Florida Artificial Intelligence Research Society Conference, Key Largo, FloridaExplanations are an important part of modern recommendersystems. They help users to make better decisions, improvethe conversion rate of browsers into buyers, and lead togreater user satisfaction in the long-run. In this paper, we extendrecent work on generating explanations by mining userreviews. We show how this leads to a novel explanation formatthat can be tailored for the needs of the individual user.Moreover, we demonstrate how the explanations themselvescan be used to rank recommendations so that items which canbe associated with a more compelling explanation are rankedahead of items that have a less compelling explanation. Weevaluate our approach using a large-scale, real-world TripAdvisordataset.enRecommender SystemsExplanationsOpinion miningSentiment analysisConference Publication2016-11-10https://creativecommons.org/licenses/by-nc-nd/3.0/ie/