Tag recommendation for open source software

  • Authors:

  • Tao Wang;Huaimin Wang;Gang Yin;Charles X. Ling;Xiao Li;Peng Zou

  • Affiliations:

  • National Laboratory for Parallel and Distributed Processing, College of Computer, National University of Defense Technology, Changsha, China 410073;National Laboratory for Parallel and Distributed Processing, College of Computer, National University of Defense Technology, Changsha, China 410073;National Laboratory for Parallel and Distributed Processing, College of Computer, National University of Defense Technology, Changsha, China 410073;Department of Computer Science, The University of Western Ontario, London, Canada N6A5B7;National Laboratory for Parallel and Distributed Processing, College of Computer, National University of Defense Technology, Changsha, China 410073 and Department of Computer Science, The Universi ...;National Laboratory for Parallel and Distributed Processing, College of Computer, National University of Defense Technology, Changsha, China 410073 and Academy of Equipment, Beijing, China 101400

  • Venue:
  • Frontiers of Computer Science: Selected Publications from Chinese Universities
  • Year:
  • 2014

Quantified Score

Hi-index 0.00

Visualization

Abstract

Nowadays open source software becomes highly popular and is of great importance for most software engineering activities. To facilitate software organization and retrieval, tagging is extensively used in open source communities. However, finding the desired software through tags in these communities such as Freecode and ohloh is still challenging because of tag insufficiency. In this paper, we propose TRG (tag recommendation based on semantic graph), a novel approach to discovering and enriching tags of open source software. Firstly, we propose a semantic graph to model the semantic correlations between tags and the words in software descriptions. Then based on the graph, we design an effective algorithm to recommend tags for software. With comprehensive experiments on large-scale open source software datasets by comparing with several typical related works, we demonstrate the effectiveness and efficiency of our method in recommending proper tags.