We present the results of applying statistical author-topic
models to a subset of the Eclipse 3.0 source code consisting
of 2,119 source files and 700,000 lines of code from 59
developers. This technique provides an intuitive and automated
framework with which to mine developer contributions
and competencies from a given code base while simultaneously
extracting software function in the form of topics.
In addition to serving as a convenient summary for program
function and developer activities, our study shows that topic
models provide a meaningful, effective, and statistical basis
for developer similarity analysis.
Description
based on the eclipse dataset the author-topic is applied
The goal of this paper is to identify the developer who will contribute to a bug most likely
%0 Conference Paper
%1 linstead2007
%A Linstead, E.
%A Rigor, P.
%A Bajracharya, S.
%A Lopes, C.
%A Baldi, P.
%B Proceedings of the Fourth International Workshop on Mining Software Repositories
%D 2007
%I IEEE Computer Society
%K datasets goals networks
%P 30
%T Mining Eclipse Developer Contributions via Author-Topic Models
%X We present the results of applying statistical author-topic
models to a subset of the Eclipse 3.0 source code consisting
of 2,119 source files and 700,000 lines of code from 59
developers. This technique provides an intuitive and automated
framework with which to mine developer contributions
and competencies from a given code base while simultaneously
extracting software function in the form of topics.
In addition to serving as a convenient summary for program
function and developer activities, our study shows that topic
models provide a meaningful, effective, and statistical basis
for developer similarity analysis.
@inproceedings{linstead2007,
abstract = {We present the results of applying statistical author-topic
models to a subset of the Eclipse 3.0 source code consisting
of 2,119 source files and 700,000 lines of code from 59
developers. This technique provides an intuitive and automated
framework with which to mine developer contributions
and competencies from a given code base while simultaneously
extracting software function in the form of topics.
In addition to serving as a convenient summary for program
function and developer activities, our study shows that topic
models provide a meaningful, effective, and statistical basis
for developer similarity analysis.},
added-at = {2008-05-26T16:41:17.000+0200},
author = {Linstead, E. and Rigor, P. and Bajracharya, S. and Lopes, C. and Baldi, P.},
biburl = {https://www.bibsonomy.org/bibtex/28b5679f3be1730633af408682fb2f69d/mstrohm},
booktitle = {Proceedings of the Fourth International Workshop on Mining Software Repositories},
description = {based on the eclipse dataset the author-topic is applied
The goal of this paper is to identify the developer who will contribute to a bug most likely},
interhash = {ef871a2300799284a9369919a6a9944d},
intrahash = {8b5679f3be1730633af408682fb2f69d},
keywords = {datasets goals networks},
pages = 30,
publisher = {IEEE Computer Society},
timestamp = {2008-05-26T16:41:17.000+0200},
title = {Mining Eclipse Developer Contributions via Author-Topic Models},
year = 2007
}