Search for author by method

CollabSeer is a search engine for discovering potential collaborators for a given author. It uses the CiteSeerx dataset to build a coauthor network, which includes over 1,300,000 computer science related documents and over a million unique authors.

CollabSeer discovers potential collaborators by analyzing the structure of a user's coauthor network and research interests. Currently, CollabSeer supports three different network structure analysis modules for collaborator search: Jaccard similarity, cosine similarity, and our relation strength similarity. Users can further refine the recommendation results by clicking on their topics of interest, which are generated by automatically extracting key phrases from previous publications.

The design of traditional digital libraries focues on discovering relevant documents. Expert recommendation systems, like Microsoft Academia Search and ArnetMiner, return a list of experts for a particular domain. However, these lists ignore the social network of collaborators or experts of a particular author. To help efficiently discover potential collaborators, we propose a new system that considers the social network structure and research interests of users to recommend potential collaborators.

Data and code available upon request.

This project is partially supported by the National Science Foundation.