Towards Text-Based Recommendations

Abstract

Recommender systems have become, like search engines, a tool that cannot be ignored by a website with a large selection of products, music, news or simply webpages. The performance of this kind of system depends on a large amount of information. At the same time, the amount of information on the Web is continuously growing, especially due to increased User Generated Content since the apparition of Web 2.0. The great majority of this content is composed of unstructured textual data. In this paper, we propose a method allowing for recommendation with only textual data. The method we propose has two steps. First, subjective texts are labelled according to their expressed opinion in order to build a user-item-rating matrix. Second, this matrix is used to establish recommendations thanks to a collaborative filtering technique. We describe the complete processing chain and evaluate it.