1. Assisting Code Search with
Automatic Query Reformulation
for Bug Localization
Bunyamin Sisman & Avinash Kak
bsisman@purdue.edu | kak@purdue.edu
Purdue University
MSR’13

2. Outline
I. Motivation
II. Past Work on Automatic Query Reformulation
III. Proposed Approach: Spatial Code Proximity (SCP)
IV. Data Preparation
V. Results
VI. Conclusions
MSR'13

3. Main Motivation
It is extremely common for software developers to use
arbitrary
abbreviations & concatenations
in software. These are generally difficult to predict when
searching the code base of a project.
The question is “Is there some way to automatically
reformulate a user’s query so that all such relevant terms
are also used in retrieval?”
MSR'13

4.  We show how a query can be automatically
reformulated for superior retrieval accuracy
 We propose a new framework for Query
Reformulation, which leverages the spatial proximity
of the terms in files
 The approach leads to significant improvements over
the baseline and the competing Query Reformulation
approaches
MSR'13
Summary of Our Contribution

5.  Our approach preserves or improves the retrieval
accuracy for 76% of the 4,393 bugs we analyzed for
Eclipse and Chrome projects
 Our approach improves the retrieval accuracy for 42%
of the 4,393 bugs
 Improvements are 66% for Eclipse and 90% for Chrome
in terms of MAP (Mean Average Precision)
 We also describe the conditions under which Query
Reformulation may perform poorly.
MSR'13
Summary of Our Contribution

6. Query Reformulation with
Relevance Feedback
1. Perform an initial retrieval with the original query
2. Analyze the set of top retrieved documents vis-
à-vis the query
3. Reformulate the query
MSR'13

7. Acquiring Relevance
Feedback
 Implicitly: infer feedback from user interactions
 Explicitly: user provides feedback [Gay et al.
2009]
 Pseudo Relevance Feedback (PRF): Automatic
QR
 This is our work!
MSR'13

8. Data Flow in the Proposed
Retrieval Framework
MSR'13

9. Automatic Query Reformulation
 No user involvement!
 It takes less than a second to reformulate a query on
ordinary desktop hardware!
 It is cheap!
 It is effective!
MSR'13

10. Previous Work on Automatic
QR (for Text Retrieval)
Rocchio’s Formula (ROCC)
Relevance Model (RM)
MSR'13

11. The Proposed Approach to QR:
Spatial Code Proximity (SCP)
 Spatial Code Proximity is an elegant approach to
giving greater weights to terms in source code that
occur in the vicinity of the terms in a users’ query
 Proximities may be created through commonly used
concatenations
 Punctuation characters
 Camel Casing etc…
 Underscores: tab_strip_gtk
 Camel casing: kPinnedTabAnimationDurationMs
MSR'13

12. Spatial Code Proximity (SCP)
(Cont’d)
 Tokenize source files and index the positions of the
terms in each source file:
 Use the distance between terms to find relevant terms
vis-à-vis a query!
MSR'13

13. SCP: Bringing the Query into the Picture
MSR'13
 Example Query: “Browser Animation”
 First perform an initial retrieval with the original query
 Increase the weights of those nearby terms!

14. Research Questions
 Question 1: Does the proposed QR approach improve
the accuracy of source code retrieval. If so, to what
extent?
 Question 2: How do the QR techniques that are
currently in the literature perform for source code
retrieval?
 Question 3: How does the initial retrieval performance
affect the performance of QR?
 Question 4: What are the conditions under which QR
may perform poorly?
MSR'13

15. Data Preparation
 For evaluation, we need a set of queries
and the relevant files
 We use the titles of the bug reports as
queries
 We have to link the repository commits
to the bug tracking database!
 Used regular expressions to detect Bug Fix
commits based on commit messages
MSR'13

16. Data Preparation (Cont’d)
Eclipse v3.1 Chrome v4.0
#Bugs 4,035 358
Avg. # Relevant Files 2.76 3.82
Avg. #Commits 1.36 1.23
MSR'13
1https://engineering.purdue.edu/RVL/Database/BUGLinks/
Resulting dataset: BUGLinks1

17. Evaluation Framework
 We use Precision and Recall based metrics to evaluate
the retrieval accuracy.
 Determine the query sets for which the proposed QR
approaches lead to
1. improvements in the retrieval accuracy
2. degradation in the retrieval accuracy
3. no change in the retrieval accuracy
 Analyze these sets to understand the characteristics of
the queries each set contains
MSR'13

18. Evaluation Framework (Cont’d)
 For comparison of these sets, we used the following Query
Performance Prediction (QPP) metrics [Haiduc et al. 2012, He
et al. 2004]:
 Average Inverse Document Frequency (avgIDF)
 Average Inverse Collection Term Frequency (avgICTF)
 Query Scope (QS)
 Simplified Clarity Score (SCS)
 Additionally, we analyzed
 Query Lengths
 Number of Relevant files per bug
MSR'13

19. QR with Bug Report Titles
ROCC
RM
SCP (Proposed)
0
500
1000
1500
2000
#Bugs
ROCC RM SCP (Proposed)
MSR'13

20. Improvements in Retrieval
Accuracy (% Increase in MAP)
ROCC
RM
SCP (Proposed)
0%
20%
40%
60%
80%
100%
Eclipse Chrome
ROCC RM SCP (Proposed)
MSR'13

21. Conclusions & Future Work
 Our framework can use a weak initial query
as a jumping off point for a better query.
 No user input is necessary
 We obtained significant improvements over
the baseline and the well-known Automatic
QR methods.
 Future Work includes evaluation of different
term proximity metrics in source code for QR
MSR'13

22. References
 [1] B. Sisman and A. Kak, “Incorporating version
histories in information retrieval based bug
localization,” in Proceedings of the 9th Working
Conference on Mining Software Repositories (MSR’12).
IEEE, 2012, pp. 50–59
 [2] G. Gay, S. Haiduc, A. Marcus, and T. Menzies, “On
the use of relevance feedback in IR-based concept
location,” in International Conference on Software
Maintenance (ICSM’09), sept. 2009, pp. 351 –360.
 [3] A. Marcus, A. Sergeyev, V. Rajlich, and J. I.
Maletic, “An information retrieval approach to
concept location in source code,” in Proceedings of
the 11th Working Conference on Reverse Engineering
(WCRE’04). IEEE Computer Society, 2004, pp. 214–223
MSR'13

23. References
 [4] S. Haiduc, G. Bavota, R. Oliveto, A. De Lucia, and
A. Marcus, “Automatic query performance assessment
during the retrieval of software artifacts,” in
Proceedings of the 27th International Conference on
Automated Software Engineering (ASE’12) .
ACM, 2012, pp. 90–99
 [5] B. He and I. Ounis, “Inferring query performance
using pre-retrieval predictors,” in Proc. Symposium on
String Processing and Information Retrieval . Springer
Verlag, 2004, pp. 43–54
MSR'13