Abstract

In this talk, I present a novel academic search and mining system, AMiner1, the second generation of the ArnetMiner system [9]. Different from traditional academic search systems that focus on document (paper) search, AMiner aims to provide a systematic modeling approach to gain a deep understanding of the large and heterogeneous networks formed by authors, papers they have pub-lished, and venues in which they were published. The system ex-tracts researchers ’ profiles automatically from the Web [7] and in-tegrates them with published papers after name disambiguation [3]. It has collected a large scholar dataset, with more than 130,000,000 researcher profiles and 100,000,000 papers from multiple publica-tion databases. We have also developed an approach named COS-NET [12] to connect AMiner with several professional social net-works, such as LinkedIn and VideoLectures, which significantly enriches the scholar metadata. Based on our integrated big scholar data, we devised a unified topic modeling approach to modeling the different entities (authors, papers, venues) simultaneously and providing a topic-level expertise search by leveraging the modeling results [8]. In addition, AMiner offers a set of researcher-centered functions, including social influence analysis [5], influence visu-alization [1], collaboration recommendation [6], relationship min-ing [4, 10], similarity analysis [11], and community evolution [2]. The system has been in operation since 2006 and has attracted more than 7,000,000 independent IP accesses from over 200 coun-tries/regions.