Is Wikipedia link structure different?

Abstract

In this paper, we investigate the difference between Wikipedia and Web link structure with respect to their value as indicators of the relevance of a page for a given topic of request. Our experimental evidence is from two IR test-collections: the .GOV collection used at the TREC Web tracks and the Wikipedia XML Corpus used at INEX. We first perform a comparative analysis of Wikipedia and .GOV link structure and then investigate the value of link evidence for improving search on Wikipedia and on the .GOV domain. Our main findings are: First, Wikipedia link structure is similar to the Web, but more densely linked. Second, Wikipedia's outlinks behave similar to inlinks and both are good indicators of relevance, whereas on the Web the inlinks are more important. Third, when incorporating link evidence in the retrieval model, for Wikipedia the global link evidence fails and we have to take the local context into account.

Computational Method for Supporting Learning with Cumulative Vocabularies, Conceptual Networks and Wikipedia Linkage

“…Motivated by previous research showing that a small-world network of 10000 nodes has an average search path of 950 steps for an average degree of 10 and an average search path of 200 steps for an average degree of 30 [26] and that the Wikipedia has a mean out-degree of 20,63 (median value 12) [24], we thus coarsely estimate that in a hyperlink network of vocabulary A1&A2&B1&B2&C1&C2 having an average out degree of 8,7 (median value 5) and containing 2878 unique nouns to enable the student to at least weakly conceptualize a single relationship between a pair of concepts could possibly require exploring about 300 steps in the hyperlink network of vocabulary. Since previous research showed that in the Wikipedia on average 4,573 hyperlink steps are between a pair of concepts [27], and similarly in Facebook social network the average number of relationship steps between two users is 4,74 [29], our coarse estimate of exploring 300 steps is about 66 times the average length of the shortest path between a pair of concepts in a hyperlink network of vocabulary.…”

“…Concerning amount of arriving and departing hyperlinks, in the World Wide Web, a mean indegree is 6,10 and a mean out-degree is 38,11 [23], whereas in the Wikipedia a mean in-degree is 20,63 and a mean outdegree is 20,63, and a median indegree is 4 and a median out-degree is 12 [24]. Relation between the number of directed links L and articles N in the Wikipedia has been suggested to be approximately L=N 1,4 [25].…”

Towards Automatic Building of Learning Pathways

“…As in (Kamps and Koolen, 2009), inlinks and outlinks are deemed to be good indicators of an article's relevance to a given topic.…”

Geodesic distances for web document clustering

“…The experimental results of Kamps and Koolen [5] show that local degree priors are better than the global degree priors and weighted local/global priors are even more helpful. Thus, the proposed approach is plausible as it presents a compromise between global and local by evaluating local connectivity on the global link graph.…”

“…Wikipedia seems a good selection because it is a known fact that in contrast to general web links, Wikipedia links are good indicators of relevance. In addition to this; in Wikipedia, outlinks and inlinks are similar in character and both contribute to the semantic analysis of the documents unlike the Web in which indegrees have a dominant role in determining the semantic relatedness [5]. Thus, the clustering coefficient computations that are based on the undirected link graph of the collection are plausible choices as link-based features for the fact that there is symmetry in the semantic nature of Wikipedia (if A is relevant to B then B is relevant to A, too).…”