Mining Context Information from Consumer's Reviews

SILVANA ACIAR

Barcelona

Workshop; 2nd Workshop on Context-Aware Recommender Systems (CARS-2010); 2010

Consumer reviews, opinions and shared experiences are popular ways to express preferences and interest of tourists in most of the popular tourism sites inside of the typical valuation of product using any valuation scale. The most critical issue on opinion mining is how to extract information that can be understood and utilized by computers from written text by users/consumers in natural language. Several approaches using artificial intelligence have been used to deal with this problem even so; problem that has been less addressed but not less important is the identification of context information embedded in consumer’s opinions due the arduous task of processing natural language in which reviews have been expressed. This paper addresses this problem based on classification text mining techniques to identify review’s sentences containing contextual information to be then processing and incorporated in a recommender system. This approach was exemplified by a case study using reviews from www.tripadvisor.com.