Welcome to the InfoSci Platform
A Hybrid Microblog Recommendation Model in Mobile Social Network

A Hybrid Microblog Recommendation Model in Mobile Social Network

Xiaoyan Chen
Copyright: © 2014 |Volume: 12 |Issue: 4 |Pages: 11
ISSN: 1539-2937|EISSN: 1539-2929|EISBN13: 9781466657632|DOI: 10.4018/jeco.2014100107
Cite Article Cite Article

MLA

Chen, Xiaoyan. "A Hybrid Microblog Recommendation Model in Mobile Social Network." JECO vol.12, no.4 2014: pp.69-79. http://doi.org/10.4018/jeco.2014100107

APA

Chen, X. (2014). A Hybrid Microblog Recommendation Model in Mobile Social Network. Journal of Electronic Commerce in Organizations (JECO), 12(4), 69-79. http://doi.org/10.4018/jeco.2014100107

Chicago

Chen, Xiaoyan. "A Hybrid Microblog Recommendation Model in Mobile Social Network," Journal of Electronic Commerce in Organizations (JECO) 12, no.4: 69-79. http://doi.org/10.4018/jeco.2014100107

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Recently, microblogs have emerged as a new open channel of communication for people on the Internet to read, commentate, socialize and so on. With the advent of a huge number of information in microblog spaces, including articles, profile, pictures and other multimedia resources, the “information overload” has become a critical problem for microblog users, which brings bloggers plethora of choices and options available that often varies in quality and may severely affected the recommendation quality. Accordingly, providing microblog users with articles that suit their particular preferences is an important issue. To solve this problem, this paper proposes a novel method integrating social network information and collaborative filtering. A user ranking model based on social network analysis is constructed to estimate the correlations between microblog users, and incorporated into similarity measure for improving the quality of microblog recommendation. Experiments on a real-world dataset are carried out to evaluate the performance of the presented method. The results show that the proposed method outperforms traditional KNN method and improves recommendation quality effectively.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.