Textual Characteristics based High Quality Online Reviews Evaluation and Detection
Hui Nie, Chengying Gao, Zhe Rong · 2013
With the rapid growth of internet, a wealth of product reviews has been spread to the web. The user-generated on-line information varies greatly in quality, which making harder for review readers to identify the most useful reviews and understand the true underlying quality of a product. In this paper, we studied the problem of evaluating and detecting high-quality product reviews. We particularly examined how the textual aspect of a review affects the perceived usefulness of it. Based on a real-world data set, our results indicate that the text-specific characteristics are significantly associated with the perceived helpfulness of reviews. A review is perceived to be useful if the content of the review focusing on the given subject, with rich information and being moderately expressed in subjective ways.