Empirical study on overlapping community detection in question and answer sites

Meng, Zide; Gandon, Fabien; Faron-Zucker, Catherine; Song, Ge

doi:10.1109/asonam.2014.6921608

Cited by 6 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They found that NB classifier has an overall success rate of 84.16 and 92.5 percent on How-to-do-it questions category. Similarly, Meng, Gandon, Faron-Zucker and Song (2015), Meng, Gandon and Zucker (2015), Meng, Gandon, Zucker and Song (2014) suggested a proficient approach for collecting topics from Q&A to identify the communities of interest. They thoroughly compared and applied three detection methods: graph based, clustering based, and LDA based on SO.…”

Section: Mining So For Software Developmentmentioning

confidence: 99%

A survey on mining stack overflow: question and answering (Q&A) community

Ahmad

Feng

Shi

et al. 2018

DTA

View full text Add to dashboard Cite

Purpose Software developers extensively use stack overflow (SO) for knowledge sharing on software development. Thus, software engineering researchers have started mining the structured/unstructured data present in certain software repositories including the Q&A software developer community SO, with the aim to improve software development. The purpose of this paper is show that how academics/practitioners can get benefit from the valuable user-generated content shared on various online social networks, specifically from Q&A community SO for software development. Design/methodology/approach A comprehensive literature review was conducted and 166 research papers on SO were categorized about software development from the inception of SO till June 2016. Findings Most of the studies revolve around a limited number of software development tasks; approximately 70 percent of the papers used millions of posts data, applied basic machine learning methods, and conducted investigations semi-automatically and quantitative studies. Thus, future research should focus on the overcoming existing identified challenges and gaps. Practical implications The work on SO is classified into two main categories; “SO design and usage” and “SO content applications.” These categories not only give insights to Q&A forum providers about the shortcomings in design and usage of such forums but also provide ways to overcome them in future. It also enables software developers to exploit such forums for the identified under-utilized tasks of software development. Originality/value The study is the first of its kind to explore the work on SO about software development and makes an original contribution by presenting a comprehensive review, design/usage shortcomings of Q&A sites, and future research challenges.

show abstract

Section: Mining So For Software Developmentmentioning

confidence: 99%

A survey on mining stack overflow: question and answering (Q&A) community

Ahmad

Feng

Shi

et al. 2018

DTA

View full text Add to dashboard Cite

show abstract

“…A identificac ¸ão destes grupos pode ser alcanc ¸ada através de métodos de detecc ¸ão de comunidades. Para isso existem 3 principais tipos de abordagem [Meng et al 2014]: métodos baseados em grafos, métodos de agrupamento e métodos baseados em modelos. A primeira consiste em inferir um grafo através das interac ¸ões no fórum e, posteriormente, utiliza-se algum método de detecc ¸ão de comunidades em redes [Xie et al 2013][Cuijuan Wang andWang 2015] no grafo inferido.…”

Section: Grupos De Colaborac ¸ãO No Stackoverflowunclassified

“…Outra forma de abordar este problema é através da utilizac ¸ão de métodos de agrupamento. Neste caso, calcula-se a similaridade dos perfis dos usuários e utiliza-se métodos de agrupamento baseados em similaridade [Meng et al 2014]. Nesta abordagem a estrutura da rede não é considerada e cada usuário é atribuído a apenas um grupo.…”

Section: Grupos De Colaborac ¸ãO No Stackoverflowunclassified

See 1 more Smart Citation

Análise de colaboração em desenvolvimento global de software

Horta

Ströele

Oliveira

et al. 2018

Anais Do XXXIII Simpósio Brasileiro De Banco De Dados (SBBD 2018)

View full text Add to dashboard Cite

A popularidade do desenvolvimento global de software Open Source aumenta a necessidade de busca por especialistas capazes de auxiliar outros desenvolvedores na resolução de tarefas complexas. O desafio é: dada uma tarefa, como identificar o melhor especialista (ou um conjunto de especialistas) para executá-la? Este problema é chamado de localização de especialistas. Algumas das dificuldades desta pesquisa são o grande volume de dados produzido, a ausência de maiores detalhes técnicos dos envolvidos e os diferentes níveis de colaboração. O objetivo deste trabalho é detectar especialistas e identificar grupos com participantes experientes em determinados tópicos em um fórum Q&A. Para tal, o fórum StackOverflow foi modelado como uma rede complexa. O método apresentado é composto pela detecção de comunidades sobrepostas através do algoritmo NetSCAN. Através de uma análise temporal foram reveladas as aptidões dos desenvolvedores, mostrando também uma tendência de mudança de seus interesses. A avaliação do método foi feita através de uma análise de viabilidade, comparando as notas das respostas dos especialistas (apontados pelo método proposto) com as notas das respostas dos usuários comuns.

show abstract

“…Thus previous community-detection algorithms cannot apply on these social webs because they have no explicit friendship networks. There are three kinds of approaches for community detection in these networks [21], depending on their input: a graph-based approach; a clustering-based approach; and a model-based approach. The first one extracts an implicit network structure from interaction traces in order to overcome the traditional community-detection problem.…”

Section: Background and Related Workmentioning

confidence: 99%

Semantic community detection using label propagation algorithm

Kianian

Khayyambashi

Movahhedinia

2015

Journal of Information Science

View full text Add to dashboard Cite

The issue of detecting large communities in online social networks is the subject of a wide range of studies in order to explore the network sub-structure. Most of the existing studies are concerned with network topology with no emphasis on active communities among the large online social networks and social portals, which are not based on network topology like forums. Here, new semantic community detection is proposed by focusing on user attributes instead of network topology. In the proposed approach, a network of user activities is established and weighted through semantic data. Furthermore, consistent extended label propagation algorithm is presented. Doing so, semantic representations of active communities are refined and labelled with user-generated tags that are available in web.2. The results show that the proposed semantic algorithm is able to significantly improve the modularity compared with three previously proposed algorithms.

show abstract

Empirical study on overlapping community detection in question and answer sites

Cited by 6 publications

References 10 publications

A survey on mining stack overflow: question and answering (Q&A) community

A survey on mining stack overflow: question and answering (Q&A) community

Análise de colaboração em desenvolvimento global de software

Semantic community detection using label propagation algorithm

Contact Info

Product

Resources

About