API method recommendation without worrying about the task-API knowledge gap

Huang, Qiao; Xia, Xin; Xing, Zhenchang; Lo, David; Wang, Xinyu

doi:10.1145/3238147.3238191

Cited by 169 publications

(161 citation statements)

References 39 publications

Supporting

Mentioning

158

Contrasting

Order By: Relevance

“…It also should be noted that unlike BIKER, our explanations are much more generic, informative and not restricted to standard Java APIs. Thus, our solution has a much more potential than the existing alternatives (i.e., AnswerBot [2] and BIKER [4]) as also confirmed by the user study (Section IV-D). Figure 2 shows the schematic diagram of our proposed approach CROKAGE.…”

Section: Motivating Examplessupporting

confidence: 66%

“…Let us consider a use-case scenario where a developer is looking for a solution to the query: "run .exe from text file". Figure 1 presents three solutions from three different approaches: AnswerBot [2], BIKER [4] and CROKAGE respectively. The solution proposed by AnswerBot ( Fig.…”

Section: Motivating Examplesmentioning

confidence: 99%

“…One possible way is rewarding the answers based on to their APIs. First, we employ three state-of-art API recommendation systems -BIKER [4], NLP2API [1] and RACK [15] and then collect the most relevant API classes for a given query (i.e., task description). Our findings suggest that the combination of three tools provides the best results which justifies our choice for combining their API suggestions (Section IV-C).…”

Section: Searching For Relevant Answersmentioning

confidence: 99%

“…In this paper, we propose an approach namely CROKAGE (Crowd Knowledge Answer Generator) that takes a task description in natural language (the query) and then returns relevant, comprehensive programming solutions containing both code examples and succinct explanations. In particular, we address the limitations of the two earlier approaches [2,4]. First, unlike AnswerBot [2] (i.e., provides only answer summary texts), we deliver both relevant code segments and their corresponding explanations.…”

Section: Introductionmentioning

confidence: 99%

“…• A novel approach that suggests programming solutions containing both code and explanations against tasks written in natural language texts by harnessing the crowd knowledge stored in Stack Overflow. • We perform an empirical evaluation on the suggestion of relevant code examples using 97 programming tasks containing API classes in their answers and a comparison with the state-of-the-art study [4]. Our approach achieves significant improvements over six baselines and outperforms the state-of-art in retrieving relevant and comprehensive programming solutions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

Silva

Roy

Rahman

et al. 2019

2019 IEEE/ACM 27th International Conference on Program Comprehension (ICPC)

View full text Add to dashboard Cite

Developers often search for relevant code examples on the web for their programming tasks. Unfortunately, they face two major problems. First, the search is impaired due to a lexical gap between their query (task description) and the information associated with the solution. Second, the retrieved solution may not be comprehensive, i.e., the code segment might miss a succinct explanation. These problems make the developers browse dozens of documents in order to synthesize an appropriate solution. To address these two problems, we propose CROKAGE (Crowd Knowledge Answer Generator), a tool that takes the description of a programming task (the query) and provides a comprehensive solution for the task. Our solutions contain not only relevant code examples but also their succinct explanations. Our proposed approach expands the task description with relevant API classes from Stack Overflow Q&A threads and then mitigates the lexical gap problems. Furthermore, we perform natural language processing on the top quality answers and then return such programming solutions containing code examples and code explanations unlike earlier studies. We evaluate our approach using 97 programming queries, of which 50% was used for training and 50% was used for testing, and show that it outperforms six baselines including the state-of-art by a statistically significant margin. Furthermore, our evaluation with 29 developers using 24 tasks (queries) confirms the superiority of CROKAGE over the state-of-art tool in terms of relevance of the suggested code examples, benefit of the code explanations and the overall solution quality (code + explanation).

show abstract

Section: Motivating Examplessupporting

confidence: 66%

Section: Motivating Examplesmentioning

confidence: 99%

Section: Searching For Relevant Answersmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

Silva

Roy

Rahman

et al. 2019

2019 IEEE/ACM 27th International Conference on Program Comprehension (ICPC)

View full text Add to dashboard Cite

show abstract

Application programming interface recommendation according to the knowledge indexed by app feature mined from app stores

Liu

et al. 2021

J Software Evolu Process

View full text Add to dashboard Cite

Application programming interfaces (APIs) play an important role in the increasingly competitive mobile application development industry, as they can greatly improve the efficiency of app development. However, finding proper APIs is often time‐consuming for the gap between the knowledge of APIs and app features. To solve this problem, we give an approach to summarize the wisdom of developers contained in the products in app stores and establish the system of API knowledge indexed by app features for the API recommendation. First, we extract features from the app descriptions and define the feature framework. Second, we parse the APK files of apps to gain the methods in code and APIs called by them and further introduce such API knowledge into the feature framework by utilizing method names as bridges. Finally, according to features in developers' queries, we locate corresponding feature nodes in the API knowledge system and recommend related API knowledge to developers. We conduct experiments based on 38,952 apps from five categories on Google Play, and the experimental results show that our approach has a good recommendation effect for the queries on app features.

show abstract

Richen: Automated enrichment of Git documentation with usage examples and scenarios

Shen,

Yang,

Jia

et al. 2024

J Software Evolu Process

View full text Add to dashboard Cite

As the predominant modern version control system, Git has become an indispensable tool for both commercial and open‐source software projects. It substantially improves software development effectiveness and efficiency through its distributed version control system, fostering seamless collaboration among teams and across locations. However, research has found that many developers have doubts about using Git commands, while the official Git documentation is rather scanty, that is, lacking sufficient explanations and examples. To help developers learn and use Git commands, we propose the first approach (Richen) for enriching Git documentation with usage examples and scenarios by leveraging crowd knowledge from Stack Overflow. Richen retrieves Git‐related posts from Stack Overflow, extracts relevant Q&A pairs, and selects representative command usages, including usage examples and scenarios, for different Git commands. Experimental results have shown that Richen can extract informative and concise command usages for Git commands. Compared with alternative methods adapted from API usage mining, the command usages obtained by Richen have significant advantages in terms of relevance, readability, and usability. Furthermore, we have shown through an empirical study that the command usages extracted by Richen can better help developers complete Git command‐related tasks.

show abstract

API method recommendation without worrying about the task-API knowledge gap

Cited by 169 publications

References 39 publications

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge

Application programming interface recommendation according to the knowledge indexed by app feature mined from app stores

Richen: Automated enrichment of Git documentation with usage examples and scenarios

Contact Info

Product

Resources

About