Determining the impact of reviews: In view of temporal pattern and component weight assignment algorithm with SVM

Abstract

Interpersonal conversation, or word-of-mouth (WOM), is one of the important factors in affecting product sales. WOM can not only increase product awareness among potential buyers but can also affect their buying decisions [8].With the rapid growth of the Internet, the ability of users to create and publish content has created active electronic communities that provide a wealth of product information [1]. Due to large number of reviews for a single product, it is difficult for the customers to find the most useful reviews among such a large quantity and to find the true quality of the product. In this paper, we examine the reviews based on the textual characteristics in different time period to find the impact of reviews. To understand better the factors that influence consumers perception of usefulness and the factors that affect consumers the most, we conducted a two-level study. First, we performed an explanatory econometric analysis, trying to identify the aspects of a review that are important determinants of its usefulness and impact. Then, at the second level, we built a model using component weight assignment algorithm with SVM to pedict the most useful reviews.

Nudge with interface designs of online product review systems – Effects of online product review system designs on purchase behavior

“…As a result, if the default sorting method is based on recency, consumers probably only read the first page with newly published reviews. Since helpfulness votes are accumulated over a long period, those newly published reviews get very few helpfulness votes (Kohilakanagalakshmi et al. , 2012).…”

“…As a result, if the default sorting method is based on recency, consumers probably only read the first page with newly published reviews. Since helpfulness votes are accumulated over a long period, those newly published reviews get very few helpfulness votes (Kohilakanagalakshmi et al, 2012). However, if consumers read reviews from OPR systems that arrange reviews based on helpfulness votes, they will read the first page of reviews with a high volume of votes.…”