Automatically Labelled Software Topic Model

Q4 Computer Science

International Journal of Open Source Software and Processes Pub Date : 2020-01-01 DOI:10.4018/ijossp.2020010104

Youcef Bouziane, M. Abdi, Salah Sadou

{"title":"Automatically Labelled Software Topic Model","authors":"Youcef Bouziane, M. Abdi, Salah Sadou","doi":"10.4018/ijossp.2020010104","DOIUrl":null,"url":null,"abstract":"Public software repositories (SR) maintain a massive amount of valuable data offering opportunities to support software engineering (SE) tasks. Researchers have applied information retrieval techniques in mining software repositories. Topic models are one of these techniques. However, this technique does not give an interpretation nor labels to the extracted topics and it requires manual analysis to identify them. Some approaches were proposed to automatically label the topics using tags in SR, but they do not consider the existence of spam-tags and they have difficulties to scale to large tag space. This article introduces a novel approach called automatically labelled software topic model (AL-STM) that labels the topics based on observed tags in SR. It mitigates the shortcomings of manual and automatic labelling of topics in SE. AL-STM is implemented using 22K GitHub projects and evaluated in a SE task (tag recommending) against the currently used techniques. The empirical results suggest that AL-STM is more robust in terms of MAP and nDCG, and more scalable to large tag space.","PeriodicalId":53605,"journal":{"name":"International Journal of Open Source Software and Processes","volume":"25 1","pages":"57-78"},"PeriodicalIF":0.0000,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Open Source Software and Processes","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijossp.2020010104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Computer Science","Score":null,"Total":0}

引用次数: 2

Abstract

Public software repositories (SR) maintain a massive amount of valuable data offering opportunities to support software engineering (SE) tasks. Researchers have applied information retrieval techniques in mining software repositories. Topic models are one of these techniques. However, this technique does not give an interpretation nor labels to the extracted topics and it requires manual analysis to identify them. Some approaches were proposed to automatically label the topics using tags in SR, but they do not consider the existence of spam-tags and they have difficulties to scale to large tag space. This article introduces a novel approach called automatically labelled software topic model (AL-STM) that labels the topics based on observed tags in SR. It mitigates the shortcomings of manual and automatic labelling of topics in SE. AL-STM is implemented using 22K GitHub projects and evaluated in a SE task (tag recommending) against the currently used techniques. The empirical results suggest that AL-STM is more robust in terms of MAP and nDCG, and more scalable to large tag space.

查看原文本刊更多论文

自动标记软件主题模型

公共软件存储库(SR)维护大量有价值的数据，为支持软件工程(SE)任务提供了机会。研究人员将信息检索技术应用于软件资源库的挖掘。主题模型就是其中一种技术。然而，这种技术没有对提取的主题给出解释和标签，需要手工分析来识别它们。提出了一些利用SR中的标签自动标记主题的方法，但它们没有考虑垃圾标签的存在，并且难以扩展到大的标签空间。本文介绍了一种新的方法，即自动标记软件主题模型(AL-STM)，它基于sr中观察到的标签对主题进行标记，减轻了SE中手动和自动标记主题的缺点。AL-STM是使用22K GitHub项目实现的，并根据当前使用的技术在SE任务(标签推荐)中进行评估。实证结果表明，AL-STM在MAP和nDCG方面具有更强的鲁棒性，并且具有更大的标签空间可扩展性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Open Source Software and Processes Computer Science-Software

CiteScore

1.90

自引率

0.00%

发文量

期刊介绍： The International Journal of Open Source Software and Processes (IJOSSP) publishes high-quality peer-reviewed and original research articles on the large field of open source software and processes. This wide area entails many intriguing question and facets, including the special development process performed by a large number of geographically dispersed programmers, community issues like coordination and communication, motivations of the participants, and also economic and legal issues. Beyond this topic, open source software is an example of a highly distributed innovation process led by the users. Therefore, many aspects have relevance beyond the realm of software and its development. In this tradition, IJOSSP also publishes papers on these topics. IJOSSP is a multi-disciplinary outlet, and welcomes submissions from all relevant fields of research and applying a multitude of research approaches.