1. Introduction
Review comments are one of the most powerful and expressive source of user preferences. Product review forums and discussion groups are popular ways for consumers to exchange their experiences with a product [2] [3] [4]. There is growing evidence that such forums inform and influence consumers' purchase decisions [5] [6]. These reviews provide valuable source of information for recommender systems. Although the importance and value of such information has been recognized, there are not many recommendation systems utilize this information due to the difficulties of incorporating unstructured data [7]. The consumer reviews are in free form text. It is difficult for a program to “understand” the text information and make recommendation based on these data. A recommender agent, which utilizes review comments to create recommendations, was recently developed by the authors [1]. Our earlier research is focused on the development of the framework. A selection and retrieval process based on consumer level of expertise in using a product has been proposed. A prioritizing mechanism for producing the recommendation results was developed. To make the recommendation process be able to utilize the textual information, an ontology was defined so the review comments can be represented in structured formats. Each piece of review comment should be mapped into the ontology as an instance. In this paper, an automatic mapping process using text mining techniques is presented. It is a critical process in the system. The mapping results are the knowledge base of the system. The quality of the recommendation highly relies on the accuracy of the mapping results.