Learning to Recommend Product with the Content of Web Page
Hui Li, Cunhua Li, Shu Zhang · 2009
Recommender systems improve access to relevant products and information by making suggestions based on page ranking technology. Existing approaches to learning to rank, however, did not consider the pages in the deep Web which have valuable information. In this paper, we present a novel product recommendation algorithm based on the content of Web pages including the product information and customer reviews. Our algorithm uses the customer reviews to calculate the score of dynamic Web pages. The paper further focus on classifying the semantic orientation of the customer reviews through a progressed Bayesian classifier and calculating the support value of each review. In addition, we also analyze the change tendency of customer reviews based on the temporal dimension. Experimental results shows that this approach can produce accurate recommendations.