How to find people who can help to answer a question? – Analyses of metrics and machine learning in online communities

Procaci, Thiago Baesso; Siqueira, Sean W. M.; Braz, Maria Helena Lima Baptista; Andrade, Leila Nalis Paiva da Silva

doi:10.1016/j.chb.2014.12.026

Cited by 18 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Online communities have emerged as an essential element of the knowledge economy and for organisations are often considered as a source of competitive advantage, as well as a channel for organisational learning (Balasubramanian & Mahajan, 2001, Guo & Sheffield, 2008Procaci, Siqueira, Braz, & Andrade, 2015).…”

Section: Consumer Intention To Participate In An Online Communitymentioning

confidence: 99%

Understanding consumer intention to participate in online travel community and effects on consumer intention to purchase travel online and WOM: An integration of innovation diffusion theory and TAM with trust

Agag

El‐Masry

2016

Computers in Human Behavior

440

312

View full text Add to dashboard Cite

The growing presence of online travel communities is leading to great developments in the travel industry. Grounded in the innovation diffusion theory (IDT) and the technology acceptance model (TAM), this paper seek to develop and empirically test a comprehensive framework to examine the antecedents of customers' intention to participate in online travel community. Using SEM to analyse the data collected from a sample of 495 members, the results indicate that innovation diffusion theory and TAM with trust provide an appropriate model for explaining consumers' intention to participate; this intention in turn has a positive influence on intention to purchase and positive WOM. Furthermore, religiosity plays an important role in understanding consumers' behavioural intention. The results offer important implications for online service provider and are likely to stimulate further research in the area of online travel community.

show abstract

Section: Consumer Intention To Participate In An Online Communitymentioning

confidence: 99%

Understanding consumer intention to participate in online travel community and effects on consumer intention to purchase travel online and WOM: An integration of innovation diffusion theory and TAM with trust

Agag

El‐Masry

2016

Computers in Human Behavior

440

312

View full text Add to dashboard Cite

show abstract

“…Message content, such as keywords [9], clusters of words that appear in user profiles [8], [43] and interrelatedness of message topics [40] is also used to identify mediated community. A further group of 12 studies studied the content of online interaction in a more qualitative manner.…”

Section: Inter-personal and Situational Levelmentioning

confidence: 99%

Internet Science

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

“…É importante ressaltar que este método pode ser realizado independentemente de qualquer mecanismo de reputação ou classificação prévia dos usuários. Mais detalhes podem ser encontrados em [Procaci, 2014] e [Procaci et al, 2014d].…”

Section: Aprendizado De Máquina Para Encontrar Usuáriosunclassified

Identificando Colegas para Ajudar em Minhas Dúvidas: Um Estudo Empírico em Comunidades de Perguntas e Respostas

Procaci

Siqueira

Andrade

2015

Workshops Do Congresso Brasileiro De Informática Na Educação

View full text Add to dashboard Cite

Online communities of questions and answers have become important places for users to exchange information and build knowledge through interactions. People ask questions and want to get answers. Colleagues (other users), called reliable users, who are willing to help and may provide good answers in such communities can support the knowledge building. Therefore, we investigated users' attributes with artificial neural network and clustering algorithm for finding reliable users. The results show that the usage of an artificial neural network is a good approach as around 90% of the users were correctly identified while the clustering algorithm makes easier to find groups of reliable users.Resumo. As comunidades online de perguntas e respostas tornaram-se lugares para usuários construírem novos conhecimentos. As perguntas são feitas e os usuários esperam obter respostas. Colegas (outros usuários) que possam ajudar a prover boas respostas, chamados de usuários confiáveis, podem apoiar esta construção de conhecimento. Assim, investigamos atributos de usuários de comunidades online juntamente com o uso de rede neural artificial e algoritmo de agrupamento para encontrar os usuários confiáveis das comunidades. 90% dos usuários foram corretamente identificados como confiáveis através de rede neural e o algoritmo de agrupamento possibilitou encontrar grupos de usuários confiáveis com mais facilidade.

show abstract

How to find people who can help to answer a question? – Analyses of metrics and machine learning in online communities

Cited by 18 publications

References 22 publications

Understanding consumer intention to participate in online travel community and effects on consumer intention to purchase travel online and WOM: An integration of innovation diffusion theory and TAM with trust

Understanding consumer intention to participate in online travel community and effects on consumer intention to purchase travel online and WOM: An integration of innovation diffusion theory and TAM with trust

Internet Science

Identificando Colegas para Ajudar em Minhas Dúvidas: Um Estudo Empírico em Comunidades de Perguntas e Respostas

Contact Info

Product

Resources

About