• DocumentCode
    2474698
  • Title

    Field weighting for automatic bug triaging systems

  • Author

    Jain, Vibhor ; Rath, Anand ; Ramaswamy, S.

  • Author_Institution
    Int. Inst. of Inf. Technol., Bangalore, India
  • fYear
    2012
  • fDate
    14-17 Oct. 2012
  • Firstpage
    2845
  • Lastpage
    2848
  • Abstract
    Every organization strives to provide online support for their customers in an attempt to rapidly provide solutions to customer bug reports. In the automation software industry, wherein software bugs can have significant repercussions for the client, rapid response to reported bugs is a very critical function. Current approaches to such response focuses on a 911 type of dispatch mechanism, wherein a dispatcher coordinates the assignment process with the help of Subject Matter Experts (SMEs). In this exploratory paper, we propose a mechanism to automate this process. As a case study, we present comparative work on bug data from Firefox and Eclipse bug reports. We have proposed and demonstrated a field-based weighting scheme. Comparing well with other such reported efforts, our approach has achieved 96.25% accuracy on Firefox (out of 1764 bug reports) and 97.83% accuracy on Eclipse bug data (out of 1986 bug reports).
  • Keywords
    DP industry; customer services; program debugging; Eclipse bug report; Firefox bug report; assignment process; automatic bug triaging system; automation software industry; customer bug report; dispatch mechanism; field weighting; online customer support; subject matter experts; Accuracy; Computer bugs; Data mining; Industries; Routing; Software; Vectors; bug triaging; dimension reduction; domain specific intelligence; field based weighting;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Systems, Man, and Cybernetics (SMC), 2012 IEEE International Conference on
  • Conference_Location
    Seoul
  • Print_ISBN
    978-1-4673-1713-9
  • Electronic_ISBN
    978-1-4673-1712-2
  • Type

    conf

  • DOI
    10.1109/ICSMC.2012.6378180
  • Filename
    6378180