|
Cluster :
|
eBusiness
|
|
|
|
Session Information
|
: Tuesday Oct 16, 16:30 - 18:00
|
|
|
|
Title:
|
Personalized Recommender Systems
|
|
Chair:
|
Nachiketa Sahoo,Boston University, 595 Commonwealth Ave, Office 627, Boston MA 02215, United States of America, nachi@bu.edu
|
|
|
|
Abstract Details
|
|
|
|
Title:
|
Product Comparison Networks for Competitive Analysis of Online Word-of-mouth
|
|
|
Presenting Author:
|
Zhu Zhang,Assistant Professor, University of Arizona, 1130 E Helen St, Rm 430, Tucson AZ 85721, United States of America, zhuzhang@email.arizona.edu
|
|
|
|
Abstract:
|
By integrating network analysis with text sentiment mining techniques, we propose product comparison networks as a novel construct, computed from consumer product reviews. To test the validity of the therefrom derived product ranking measures, we conduct an empirical study based on a digital camera dataset from Amazon.com. The results demonstrate significant effect of network-based measures on product sales.
|
|
|
|
|
Title:
|
Manipulation Resistant News Recommender Systems with Feedback
|
|
|
Presenting Author:
|
Shankar Prawesh,University of South Florida, 4202 E. Fowler Avenue, Tampa FL, United States of America, sprawesh@usf.edu
|
|
|
Co-Author:
|
Balaji Padmanabhan,Associate Professor, University of South Florida, 4202 E. Fowler Avenue, Tampa FL, United States of America, bp@usf.edu
|
|
|
|
Abstract:
|
The focus of our presentation is the issue of manipulation in Top-N news recommender systems (NRS). These automated systems are target of manipulators who hire people to promote their articles or apps farther up in the roster. We address the issue of manipulation in NRS through a class of feedback functions and an adapted influence limiter algorithm – both are used in conjunction. We show that the proposed recommendation technique performs very well to thwart common manipulation strategies.
|
|
|
|
|
|
|
|
|
|
|
|