Share This Author
A New Hybrid Popular Model for Personalized Tag Recommendation
A new model IBHP is put forward to recommend personalized tags for users, which can get better performance than currently widely used popularity-based methods, which also use the same available information: <user, item, tag> ternary relations.
A Method of Personalized Web Search Result Clustering Based on Formal Concept Analysis
This paper incorporates a target user’s categorization preferences into the Web search result clustering process using Formal Concept Analysis (FCA), and focuses on the target user's categorization preference extracting and cluster hierarchy building based on FCA.
Ranking Social Image Tags via Neighbor Voting and Random Walk
- Jing Wang
- Computer Science
Experimental results demonstrate that the proposed algorithm outperforms exiting methods, and it can effectively boost the performance of social image retrieval as well.
Methods and Systems to Identify Potential Users Using Click-Based Referral of Website Visitors
This document describes systems and processes for an advertising platform that increases a size of a target audience of an advertiser by using information that is known about the visitors to the advertiser’s website.
Association-Rule-Based Random Walk Method for Personalized Tag Recommendation
A new method ARRW is proposed to alleviate the sparsity problem of graph sparsity by introducing Association Rules to Random Walk for digging up more relevance among nodes in graphs.
Search Engine Result Bias: An Empirical Investigation of Commercial Web Based Search Tools
Bias was previously never a serious issue in traditional IRS because the information being retrieved from them was not subject to systematic manipulation since it was largely non-commercial in nature, but today the competitive and commercial nature of search engines on the Web makes them vulnerable to systematic manipulations of results.