סמינר מחלקתי
The Social Aspect of Voting for Useful Reviews
Dr. Osnat Mokryn - The Academic College Tel Aviv Yaffo
Abstract:
Word-of-mouth is being replaced by online reviews on products and services. To identify the most useful reviews, many web sites enable readers to vote on which reviews they find useful. In this work we explore the following three hypotheses: The first is that useful reviews induce feelings. The second is that there are specific textual properties to useful reviews. The third hypothesis is that the reviewer’s impact history can be used as a predictor. We define a user impact metric similar to the way scientific metrics are used for assessing the impact of a scholar, namely h-index, i10-index. We analyze the performance of our hypotheses over four datasets collected from Yelp, Amazon, and IMDb. Our surprising and robust results show that the only good predictor to the usefulness of a review is the reviewer’s impact metrics score. We further devise a regression model that predicts the usefulness rating of each review. To further understand these results we characterize reviewers with high impact metrics scores and show that they write reviews frequently, and that their impact scores increase over time (on average). We suggest the term local celebs for these reviewers, and analyze the conditions for becoming local celebs on sites. An additional contribution of this paper is a devised mechanism for becoming influential contributors in such online communities.
A joint work with Asher Levi. A short version of this work was accepted for publication at SBP2014.
Short bio:
Osnat (Ossi) Mokryn is a Senior Lecturer at the Academic College Tel Aviv Yaffo, where she heads the Internet and Networks field, and a research affiliate in the Information Systems department in haifa University. Her research focuses on social media mining, social and complex networks, and cloud content acceleration.
ההרצאה תתקיים ביום שלישי 28.4.15, בשעה 14:00 בחדר 206, בנין וולפסון הנדסה, הפקולטה להנדסה, אוניברסיטת תל-אביב.
