Mining StackOverflow to turn the IDE into a self-confident programming prompter
The DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
Developers often require knowledge beyond the one they possess, which often boils down to consulting sources of information like Application Programming Interfaces (API) documentation, forums, Q&A websites, etc. Knowing what to search for and how is non- trivial, and developers spend time and energy to formulate their problems as queries and to peruse and process the results. We propose a novel approach that, given a context in the IDE, automatically retrieves pertinent discussions from Stack Overflow, evaluates their relevance, and, if a given confidence threshold is surpassed, notifies the developer about the available help. We have implemented our approach in Prompter, an Eclipse plug-in. Prompter has been evaluated through two studies. The first was aimed at evaluating the devised ranking model, while the second was conducted to evaluate the usefulness of Prompter.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Our quantitative task performance results for the current version of this NL2Code plugin, while negative, do not imply that future, better performing such systems will also not be markedly useful in practice; the qualitative data from our our study participants already suggests otherwise, as does quantitative data from prior research on the usefulness of in-IDE code search plugins [92].”
From In-IDE Code Generation from Natural Language: Promise and Challenges (2022) · cites this paper as [92]
Citations
Cites
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
Binary Codes capable of currecting deletions, insertions, and reversals
Levenshtein, V. I. (1965) · Soviet physics. Doklady · Cited by 14,804
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Baeza-Yates, R. A., & Ribeiro-Neto, B. A. (1999) · Cited by 11,505
Questionnaire Design, Interviewing and Attitude Measurement
Albuam, G., & Oppenheim, A. N. (1993) · Journal of Marketing Research · doi:10.2307/3172892 · Cited by 4,971
Violin Plots: A Box Plot-Density Trace Synergism
Hintze, J. L., & Nelson, R. D. (1998) · The American Statistician · doi:10.1080/00031305.1998.10480559 · Cited by 1,802 · cited 1×
“We quantitatively analyzed participants' answers through violinplots [12] to assess the ability of Prompter in identifying relevant Stack Overflow discussions given a piece of code.”
Anvik, J., Hiew, L., & Murphy, G. C. (2006) · Proceedings of the 28th international conference on Software engineering · doi:10.1145/1134285.1134336 · Cited by 924 · cited 5×
“The information is retrieved from different sources, such as forums, mailing lists [2], blogs, Q&A websites, bug trackers [1], etc.”
InfluentialEffect sizes for research: A broad practical approach.
Grissom, R. J., & Kim, J. J. (2005) · Cited by 732
Maintaining mental models: a study of developer work habits
LaToza, T. D., Venolia, G., & DeLine, R. (2006) · Proceedings of the 28th international conference on Software engineering · doi:10.1145/1134285.1134355 · Cited by 628 · cited 1×
“While asking team mates is the preferred means to obtain help [20], their availability may fall short.”
BackgroundDesign lessons from the fastest q&a site in the west
Mamykina, L., Manoim, B., Mittal, M., Hripcsak, G., & Hartmann, B. (2011) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1978942.1979366 · Cited by 553 · cited 1×
“Stack Overflow is vast: In 2010 it already had 300k users, and millions of questions, answers, and comments [23].”
BackgroundQuestionnaire design, interviewing and attitude measurement
Oppenheim, A. N. (1992) · Cited by 535
Information Needs in Collocated Software Development Teams
Ko, A. J., DeLine, R., & Venolia, G. (2007) · 29th International Conference on Software Engineering (ICSE'07) · doi:10.1109/icse.2007.45 · Cited by 499 · cited 1×
“A helping hand is often required, either by team mates [18], through pair programming sessions [6], or the perusal of vast amounts of knowledge available on the Internet [41].”
BackgroundMining Version Histories to Guide Software Changes
Zimmermann, T., Member, S., Weißgerber, P., Diehl, S., Zeller, A., & Ieee Computer Society (2004) · Cited by 494
Using task context to improve programmer productivity
Kersten, M., & Murphy, G. C. (2006) · Proceedings of the 14th ACM SIGSOFT international symposium on Foundations of software engineering · doi:10.1145/1181775.1181777 · Cited by 452 · cited 1×
“A milestone in identifying relevant code elements in the IDE is Mylyn [17].”
BackgroundParseweb: a programmer assistant for reusing open source code on the web
Thummalapenta, S., & Xie, T. (2007) · Proceedings of the twenty-second IEEE/ACM international conference on Automated software engineering · doi:10.1145/1321631.1321663 · Cited by 391 · cited 1×
“Different works [31, 38, 39] tackled this problem and provided the developers with the capability of searching, ranking and adapting open source code.”
BackgroundRecommendation Systems for Software Engineering
Robillard, M., Walker, R., & Zimmermann, T. (2010) · IEEE Software · doi:10.1109/ms.2009.161 · Cited by 388 · cited 1×
“Recommender systems [33] represent a possible solution to this problem.”
BackgroundUsing structural context to recommend source code examples
Holmes, R., & Murphy, G. C. (2005) · Proceedings of the 27th international conference on Software engineering - ICSE '05 · doi:10.1145/1062455.1062491 · Cited by 379 · cited 1×
“[16, 15, 30] presented Strathcona, a tool to recommend relevant code fragments that automatically extracts queries from structural context of the code.”
Binary Codes capable of currecting deletions, insertions, and reversals
Levenshtein, I. V. (1966) · Medical Entomology and Zoology · Cited by 360
Hipikat: recommending pertinent software development artifacts
Čubranić, D., & Murphy, G. C. (2003) · doi:10.5555/776816.776866 · Cited by 317
Portfolio: finding relevant functions and their usage
McMillan, C., Grechanik, M., Poshyvanyk, D., Xie, Q., & Fu, C. (2011) · Proceedings of the 33rd International Conference on Software Engineering · doi:10.1145/1985793.1985809 · Cited by 313 · cited 1×
“The mining of open source repositories has also been used to identify API and framework usage and to find highly relevant applications to be reused [25, 26, 40].”
MethodReiss, S. P. (2009) · 2009 IEEE 31st International Conference on Software Engineering · doi:10.1109/icse.2009.5070525 · Cited by 307
Mica: A Web-Search Tool for Finding API Components and Examples
Stylos, J., & Myers, B. A. (2006) · Visual Languages and Human-Centric Computing (VL/HCC'06) · doi:10.1109/vlhcc.2006.32 · Cited by 224 · cited 1×
“Examples are Codetrail [10], Mica [36], FishTail [34], Dora [19], and SurfClipse [29].”
Approximate Structural Context Matching: An Approach to Recommend Relevant Examples
Holmes, R., Walker, R. J., & Murphy, G. C. (2006) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2006.117 · Cited by 158 · cited 1×
“[16, 15, 30] presented Strathcona, a tool to recommend relevant code fragments that automatically extracts queries from structural context of the code.”
MethodExemplar: A Source Code Search Engine for Finding Highly Relevant Applications
McMillan, C., Grechanik, M., Poshyvanyk, D., Fu, C., & Xie, Q. (2011) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2011.84 · Cited by 149 · cited 1×
“The mining of open source repositories has also been used to identify API and framework usage and to find highly relevant applications to be reused [25, 26, 40].”
MethodConstantine, L. L. (1995) · Medical Entomology and Zoology · Cited by 130
Discovering Essential Code Elements in Informal Documentation
Rigby, P. C., & Robillard, M. P. (2013) · Cited by 112
How Well Do Search Engines Support Code Retrieval on the Web?
Sim, S. E., Umarji, M., Ratanotayanon, S., & Lopes, C. V. (2011) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/2063239.2063243 · Cited by 102 · cited 11×
“MSR '14, May 31 – June 1, 2014, Hyderabad, India Copyright 2014 ACM 978-1-4503-2863-0/14/05 ...$15.00. problems, the main one being the absence of automation: Every time developers need to look for information, they interrupt their work flow, leave the IDE, and use a Web browser to perform and refine searches, and ass…”
InfluentialSpotWeb: Detecting Framework Hotspots and Coldspots via Mining Open Source Code on the Web
Thummalapenta, S., & Xie, T. (2008) · 2008 23rd IEEE/ACM International Conference on Automated Software Engineering · doi:10.1109/ase.2008.43 · Cited by 89 · cited 1×
“The mining of open source repositories has also been used to identify API and framework usage and to find highly relevant applications to be reused [25, 26, 40].”
MethodStrathcona example recommendation tool
Holmes, R., Walker, R. J., & Murphy, G. C. (2005) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/1081706.1081744 · Cited by 88 · cited 1×
“[16, 15, 30] presented Strathcona, a tool to recommend relevant code fragments that automatically extracts queries from structural context of the code.”
MethodLeveraging Crowd Knowledge for Software Comprehension and Development
Ponzanelli, L., Bacchelli, A., & Lanza, M. (2013) · Euromicro Conference on Software Maintenance and Reengineering (CSMR) · doi:10.1109/csmr.2013.16 · Cited by 83 · cited 1×
“Our previous work in this context [28] only used text similarity as a means to retrieve Stack Overflow discussions related to the actual code.”
Self-citationIntegrating pair programming into a software development process
Williams, L. A. (2002) · doi:10.1109/csee.2001.913816 · Cited by 80 · cited 1×
“These developers have different roles, i.e., the driver, who is in charge of writing code, and the observer, who observes the work of the driver [42], tries to understand the context, and, if she has enough confidence, interrupts the driver by giving suggestions.”
Rahman, M. M., Yeasmin, S., & Roy, C. K. (2014) · 2014 Software Evolution Week - IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE) · doi:10.1109/csmr-wcre.2014.6747170 · Cited by 75 · cited 2×
“Other tools used Stack Overflow as main source for recommendation systems to suggest, within the IDE, code samples and discussions to the developer [7, 32, 37, 29].”
MethodArchetypal Internet-Scale Source Code Searching
Umarji, M., Sim, S. E., & Lopes, C. V. (2008) · IFIP International Federation for Information Processing/IFIP · doi:10.1007/978-0-387-09684-1_21 · Cited by 75
Archetypal Internet-Scale Source Code Searching
Umarji, M., & Sim, S. E. (2013) · Springer eBooks · doi:10.1007/978-1-4614-6596-6_3 · Cited by 74 · cited 5×
“The post-study questionnaire was composed of: (i) three questions asking if participants used Internet, the suggestions by Prompter, and their own knowledge during implementation.”
InfluentialContent Classification of Development Emails
Bacchelli, A., Sasso, T. D., & Lanza, M. (2013) · Cited by 72
Self-citationDeep intellisense: a tool for rehydrating evaporated information
Holmes, R., & Begel, A. (2008) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/1370750.1370755 · Cited by 61 · cited 1×
“Seminal tools, such as eRose [43], Hipikat [9] and DeepIntellisense [14], suggest project artifacts in the IDE aiming at providing developers with additional information on specific parts of the system.”
Context-based recommendation to support problem solving in software development
Cordeiro, J., Antunes, B., & Gomes, P. (2012) · doi:10.5555/2666719.2666739 · Cited by 56
Codetrail: Connecting source code and web resources
Goldman, M., & Miller, R. C. (2009) · Journal of Visual Languages & Computing · doi:10.1016/j.jvlc.2009.04.003 · Cited by 50 · cited 1×
“Examples are Codetrail [10], Mica [36], FishTail [34], Dora [19], and SurfClipse [29].”
Mining search topics from a code search engine usage log
Bajracharya, S. K., & Lopes, C. V. (2009) · International Conference on Mining Software Repositories (MSR) · doi:10.1109/msr.2009.5069489 · Cited by 50 · cited 2×
“Other studies analyzed the usage and the habits of the developers in performing researches with code search engines (e.g., Koders) [4, 22, 41], and how general purpose search engines (e.g., Google) outperform code search engines when retrieving code samples from the Web [35].”
BackgroundA spontaneous code recommendation tool based on associative search
Watanabe, T., & Masuhara, H. (2011) · International Workshop on Search-Driven Development: Users, Infrastructure, Tools, and Evaluation (SUITE) · doi:10.1145/1985429.1985434 · Cited by 48 · cited 1×
“Other tools used Stack Overflow as main source for recommendation systems to suggest, within the IDE, code samples and discussions to the developer [7, 32, 37, 29].”
MethodFishtail: from task context to source code examples
Sawadsky, N., & Murphy, G. C. (2011) · International Workshop on Developing Tools as Plug-Ins (TOPI) · doi:10.1145/1984708.1984722 · Cited by 47 · cited 1×
“Examples are Codetrail [10], Mica [36], FishTail [34], Dora [19], and SurfClipse [29].”
MethodContext-based recommendation to support problem solving in software development
Cordeiro, J., Antunes, B., & Gomes, P. (2012) · International Workshop on Recommendation Systems for Software Engineering (RSSE) · doi:10.1109/rsse.2012.6233418 · Cited by 46 · cited 1×
“Other tools used Stack Overflow as main source for recommendation systems to suggest, within the IDE, code samples and discussions to the developer [7, 32, 37, 29].”
MethodAutomatically locating relevant programming help online
Kononenko, O., Dietrich, D., Sharma, R., & Holmes, R. (2012) · IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vlhcc.2012.6344497 · Cited by 28 · cited 1×
“Examples are Codetrail [10], Mica [36], FishTail [34], Dora [19], and SurfClipse [29].”
MethodMining Internet-Scale Software Repositories
Linstead, E. J., Rigor, P., Bajracharya, S. K., Lopes, C. V., & Baldi, P. (2007) · Cited by 28
Exploiting code search engines to improve programmer productivity
Thummalapenta, S. (2007) · doi:10.1145/1297846.1297946 · Cited by 7 · cited 1×
“Different works [31, 38, 39] tackled this problem and provided the developers with the capability of searching, ranking and adapting open source code.”
Background
Research works printed but not linked: 8
- 10.5555/2337223.2337268 · doi:10.5555/2337223.2337268
- R. D. Baker . Modern permutation test software . In Randomization Tests. Marcel Decker , 1995 . R. D. Baker. Modern permutation test software. In Randomization Tests. Marcel Decker, 1995.
- 10.5555/129837 · doi:10.5555/129837
- S. Holm . A simple sequentially rejective Bonferroni test procedure . Scandinavian Journal of Statistics , 6 : 65 – 70 , 1979 . S. Holm. A simple sequentially rejective Bonferroni test procedure. Scandinavian Journal of Statistics, 6:65–70, 1979.
- 10.5555/1394399 · doi:10.5555/1394399
- 10.5555/2486788.2486897 · doi:10.5555/2486788.2486897
- 10.5555/794193.794899 · doi:10.5555/794193.794899
- 10.5555/998675.999460 · doi:10.5555/998675.999460
Cited by
Gu, X., Zhang, H., & Kim, S. (2018) · Proceedings of the 40th International Conference on Software Engineering · doi:10.1145/3180155.3180167 · Cited by 547
“[61] proposed an approach that automatically retrieves pertinent discussions from Stack Overflow given a context in the IDE.”
BackgroundA survey of the use of crowdsourcing in software engineering
Mao, K., Capra, L., Harman, M., & Jia, Y. (2017) · Journal of Systems and Software · doi:10.1016/j.jss.2016.09.015 · Cited by 385
“…2012; Bruch, 2012; Watson et al., 2012; Bacchelli et al., 2012; Ponzanelli, 2012; Ponzanelli et al., 2013a,b; Wightman, 2013; Barzilay et al., 2013; Ponzanelli et al., 2014a,b; de Souza et al., 2014;950 Fast et al., 2014; Chen and Kim, 2015), each of which we describe below: HelpMeOut (Hartmann et…”
BackgroundAugmenting API documentation with insights from stack overflow
Treude, C., & Robillard, M. P. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884800 · Cited by 239
Jumping through hoops: why do Java developers struggle with cryptography APIs?
Nadi, S., Krüger, S., Mezini, M., & Bodden, E. (2016) · Proceedings of the 38th International Conference on Software Engineering · doi:10.1145/2884781.2884790 · Cited by 218
“, [24,30,33]).”
API method recommendation without worrying about the task-API knowledge gap
Huang, Q., Xia, X., Xing, Z., Lo, D., & Wang, X. (2018) · Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering · doi:10.1145/3238147.3238191 · Cited by 192
“[32] proposed Prompter to automatically generate queries based on code context, and retrieve pertinent discussions from SO.”
Metadata
- Authors
- Ponzanelli, L., Bavota, G., Di Penta, M., Oliveto, R., & Lanza, M.
- Affiliations
- Università della Svizzera italiana (CH)
- University of Sannio (IT)
- University of Sannio, Italy
- University of Molise (IT)
- Venue
- Proceedings of the 11th Working Conference on Mining Software Repositories
- Publisher
- ACM
- Published
- 2014-05-31
- Pages
- 102-111
- OpenAlex
- W2014755981
- Cited by
- 240
- References
- 45
- Citations by year
- 2026: 3 · 2025: 2 · 2024: 9 · 2023: 17 · 2022: 24 · 2021: 25 · 2020: 26 · 2019: 35 · 2018: 25 · 2017: 23 · 2016: 27 · 2015: 20 · 2014: 4
- FWCI
- 21.04
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Mining Software Repositories (MSR) (publishedVersion)
- Archivio Istituzionale della Ricerca - Università degli Studi del Molise (submittedVersion)
- Open Research (University of Surrey) (submittedVersion)
- Funders
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Topics
- Physical Sciences › Computer Science › Information Systems › Software Engineering Research
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Information Systems › Expert finding and Q&A systems
- Keywords
- Stack Overflow, programming question answering, integrated development environment, relevance ranking, developer assistance, Eclipse plug-in, prompter, API documentation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.