Material Detail

This video was recorded at European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Athens 2011. Item reviews are a valuable source of information for potential buyers, who are looking for information on a product's attributes before making a purchase decision. This search of information is often hindered by overwhelming numbers of available reviews, as well as low-quality and noisy content. While a significant amount of research has been devoted to filtering and organizing review corpora toward the benefit of the buyers, a crucial part of the reviewing process has been overlooked: reviewer satisfaction. As in every content-based system, the content-generators, in this case the reviewers, serve as the driving force. Therefore, keeping the reviewers satisfied and motivated to continue submitting high quality content is essential. In this paper, we propose a system that helps potential buyers by focusing on high-quality and informative reviews, while keeping reviewers content and motivated.

Disciplines:

• Science and Technology  / Computer Science