In this abstract propose a product aspect ranking framework to automatically identify the important aspects of products from numerous consumer reviews. It develop a probabilistic aspect ranking algorithm to infer the importance of various aspects by simultaneously exploiting aspect frequency and the influence of consumers’ opinions given to each aspect over their overall opinions on the product. It demonstrate the potential of aspect ranking in real-world applications. Significant performance improvements are obtained on the applications of document-level sentiment classification and extractive review summarization by making use of aspect ranking.
You are here: / / PRODUCT ASPECT RANKING FOR AUTOMATICALLY IDENTIFY THE IMPORTANT ASPECTS OF PRODUCTS FROM NUMEROUS CONSUMER REVIEWS