Co-Occurrence-Based Diffusion for Expert Search on the Web

Friend recommendation with content spread enhancement in social networks

“…These include recommending item ratings [34], tags [12], documents [14], friends [5,15], experts [21,13] and many others in social networks. Various recommendation algorithms are exploited in these systems, ranging from the canonical collaborative filtering [16], graph-based propagation [12,14], to the new list-wise probabilistic matrix factorization [22], etc.…”

A formal approach for the specification and verification of a Trustworthy Human Resource Discovery mechanism in the Expert Cloud

“…Some papers and researches such as Guan, Miao, McLoughlin, Yan, and Cai (2013), Ounis (2008, 2011), Moreira and Wichert (2013), Santos, Macdonald, andYuh-Jzer, Shy-Min, Chih-Chang, andChiu, 2013 studied the searching of experts in distributed systems. In an expert search, the users' need is to identify people who have relevant expertise to a topic of interest.…”

“…As another research in the scope of expert search, Guan et al (2013) has examined a general expert search problem: searching experts on the web, where millions of webpages and thousands of names are considered. They considered two challenging issues: webpages could be of varying quality and full of noises; and the expertise evidences scattered in webpages are usually vague and ambiguous.…”

A technical study on Information Retrieval using web mining techniques

“…Ziyu Guan et al [23] observed some challenging issues on expert search on the web for co-occurrence-based diffusion to get effective web pages while browsing and searching. The authors were mainly concentrating relevancy of the contents in the web pages.…”

“…PickOne algorithm was a greedy heuristic and this was reflected in its rapidly degraded performance and also was providing inaccurate ranking of the top 100 results [22]. CoDiffusion did not show superior performance with Global ranking scheme, compared with LM and RW rankings because each query keyword was treated independently by the algorithm [23]. The Ranking algorithm gave better results in local ranking.…”