36 lines
1.5 KiB
TeX
36 lines
1.5 KiB
TeX
\section{Conclusion\&Future Work}
|
||
\label{sec:Concl}
|
||
|
||
In this paper,
|
||
we conduct a case study on three popular OSS projects hosted on GitHub,
|
||
and construct a fine-grained taxonomy
|
||
including 11 sub-categories for review comments.
|
||
According to the defined taxonomy
|
||
we manually label over 5,600 review comments
|
||
and propose a two-stage hybrid classification algorithm to automatically classify
|
||
review comments.
|
||
The comparative experiment results show that
|
||
our approach can return reasonably good results for most categories.
|
||
|
||
%further work
|
||
Nevertheless, \TSHC performs poorly on a few Level-2 categories.
|
||
More work could be done in the future to improve it.
|
||
%帖子情感分析 更多的人工标注集（extend the training set）
|
||
we plan to address the shortcomings of our approach
|
||
by extending the manually labeled data set
|
||
and introducing a sentiment analysis.
|
||
Moreover, we will try to improve reviewer recommendation
|
||
and pull-request prioritization
|
||
based on the result in this paper.
|
||
|
||
|
||
%%%%%%可借鉴的
|
||
% [**
|
||
% While our results need to be confirmed by a more representative sample they are an initial step into the study of emotions and related factors in open source projects.
|
||
% ***]
|
||
%%%%%%可借鉴的
|
||
|
||
|
||
\section*{Acknowledgment}
|
||
The research is supported by the National Natural Science Foundation of China (Grant No.61432020, 61303064, 61472430, 61502512) and National Grand R\&D Plan (Grant No. 2016YFB1000805).
|
||
% The authors would like to thank... more thanks here |