EnTagRec : an enhanced tag recommendation system for software information sites

S. Wang, D. Lo, B.N. Vasilescu, A. Serebrenik

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    74 Citations (Scopus)
    289 Downloads (Pure)

    Abstract

    Software engineers share experiences with modern technologies by means of software information sites, such as STACK OVERFLOW. These sites allow developers to label posted content, referred to as software objects, with short descriptions, known as tags. However, tags assigned to objects tend to be noisy and some objects are not well tagged. To improve the quality of tags in software information sites, we propose ENTAGREC, an automatic tag recommender based on historical tag assignments to software objects and we evaluate its performance on four software information sites, STACK OVERFLOW, ASK UBUNTU, ASK DIFFERENT, and FREECODE. We observe that that ENTAGREC achieves Recall@5 scores of 0.805, 0.815, 0.88 and 0.64, and Recall@10 scores of 0.868, 0.876, 0.944 and 0.753, on STACK OVERFLOW, ASK UBUNTU, ASK DIFFERENT, and FREECODE, respectively. In terms of Recall@5 and Recall@10, averaging across the 4 datasets, ENTAGREC improves TAGCOMBINE, which is the state of the art approach, by 27.3% and 12.9% respectively.
    Original languageEnglish
    Title of host publication30th International Conference on Software Maintenance and Evolution (ICSME'14), Victoria, BC, Canada, September 28-October 3, 2014
    PublisherIEEE Computer Society
    Pages291-300
    ISBN (Print)978-0-7695-5303-0
    DOIs
    Publication statusPublished - 2014
    Event30th International Conference on Software Maintenance and Evolution (ICSME 2014) - Victoria, Canada
    Duration: 28 Sep 20143 Oct 2014
    Conference number: 30

    Conference

    Conference30th International Conference on Software Maintenance and Evolution (ICSME 2014)
    Abbreviated titleICSME 2014
    CountryCanada
    CityVictoria
    Period28/09/143/10/14

    Fingerprint Dive into the research topics of 'EnTagRec : an enhanced tag recommendation system for software information sites'. Together they form a unique fingerprint.

    Cite this