Mining the peanut gallery: opinion extraction and semantic classification of product reviews
WWW '03 Proceedings of the 12th international conference on World Wide Web
Hi-index | 0.00 |
Online reputation is useful for choosing products and marketing research. However, it is not easy to grasp reputational contents at a glance because it usually involves textual information such as blogs and word-of-mouth information. As described in this paper, we propose a mode of visualizing reputation using evaluative expression dictionaries. To create the dictionaries automatically, we use a review site with review texts and ratings. We evaluate the dictionaries by comparing the ratings of a product in the review site and the scores that our system calculates based on the review texts.