Title :
Mining the coherence of GNOME bug reports with statistical topic models
Author :
Linstead, Erik ; Baldi, Pierre
Author_Institution :
Dept. of Comput. Sci., Univ. of California, Irvine, CA
Abstract :
We adapt latent Dirichlet allocation to the problem of mining bug reports in order to define a new information-theoretic measure of coherence. We then apply our technique to a snapshot of the GNOME Bugzilla database consisting of 431,863 bug reports for multiple software projects. In addition to providing an unsupervised means for modeling report content, our results indicate substantial promise in applying statistical text mining algorithms for estimating bug report quality. Complete results are available from our supplementary materials Web site at http://sourcerer.ics.uci.edu/msr2009/gnome_coherence.html.
Keywords :
data mining; program debugging; statistical analysis; text analysis; GNOME Bugzilla database; GNOME bug report coherence mining; debugging process; information-theoretic measure; latent Dirichlet allocation; software project; statistical text mining algorithm; statistical topic model; Bayesian methods; Coherence; Computer science; Databases; Information theory; Linear discriminant analysis; Software measurement; Text mining; Vocabulary; XML;
Conference_Titel :
Mining Software Repositories, 2009. MSR '09. 6th IEEE International Working Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4244-3493-0
DOI :
10.1109/MSR.2009.5069486