An extensive bibliometric study on the db community using the collaboration network constructed from DBLP data is presented. Among many, we have found that (1) the average distance of all db scholars in the network has been stabilized to about 6 for the last 15 years, coinciding with the so-called six degrees of separation phenomenon; (2) In sync with Lotka's law on the frequency of publications, the db community also shows that a few number of scholars publish a large number of papers, while the majority of authors publish a small number of papers (i.e., following the power-law with exponent about -2); and (3) with the increasing demand to publish more, scholars collaborate more often than before (i.e., 3.93 collaborators per scholar and with steadily increasing clustering coefficients).

Bibliometrics are important measures for venue quality in digital libraries. Impacts of venues are usually the major consideration for subscription decision-making, and for ranking and recommending high-quality venues and documents. For digital libraries in the Computer Science literature domain, conferences play a major role as an important publication and dissemination outlet. However, with a recent profusion of conferences and rapidly expanding fields, it is increasingly challenging for researchers and librarians to assess the quality of conferences. We propose a set of novel heuristics to automatically discover prestigious (and lowquality) conferences by mining the characteristics of Program Committee members. We examine the proposed cues both in isolation and combination under a classification scheme. Evaluation on a collection of 2,979 conferences and 16,147 PC members shows that our heuristics, when combined, correctly classify about 92% of the conferences, with a low false positive rate of 0.035 and a recall of more than 73% for identifying reputable conferences. Furthermore, we demonstrate empirically that our heuristics can also effectively detect a set of low-quality conferences, with a false positive rate of merely 0.002. We also report our experience of detecting two previously unknown low-quality conferences. Finally, we apply the proposed techniques to the entire quality spectrum by ranking conferences in the collection.

Using graph theory, we analyze the topological landscape of web service networks formed by real-world data set, either downloaded from web service repositories or crawled by a search engine. We first propose a flexible framework to study syntactic web service matchmaking in a unified manner. Under the framework, then, the data set is analyzed from diverse perspectives and granularity. By and large, the data set is shown to exhibit small world network well and power-law-like distribution to some extent. Finally, using random graph theory, we demonstrate how to accurately estimate the size of the giant component of such web service networks.

The entity resolution (ER) problem, which identifies duplicate entities that refer to the same real world entity, is essential in many applications. In this paper, in particular, we focus on resolving entities that contain a group of related elements in them (e.g., an author entity with a list of citations, a singer entity with song list, or an intermediate result by GROUP BY SQL query). Such entities, named as grouped-entities, frequently occur in many applications. The previous approaches toward grouped-entity resolution often rely on textual similarity, and produce a large number of false positives. As a complementing technique, in this paper, we present our experience of applying a recently proposed graph mining technique, Quasi-Clique, atop conventional ER solutions. Our approach exploits contextual information mined from the group of elements per entity in addition to syntactic similarity. Extensive experiments verify that our proposal improves precision and recall up to 83% when used together with a variety of existing ER solutions, but never worsens them.

No abstract