WANQA: uma Abordagem para Identificar Novas Questões Não Respondíveis em Comunidades de Perguntas e Respostas
Resumo
Grandes repositórios de conhecimento estão distribuídos pela Web, sendo que um dos mais colaborativos são as comunidades de perguntas e respostas (CQAs). Diariamente, os seus usuários postam grandes volumes de questões e boa parte delas não recebe respostas, tornando-se conteúdo inútil. Trabalhos existentes, que se propõem a resolver esse problema, são dependentes das características presentes em cada comunidade. Neste artigo, é proposta uma abordagem baseada em classificação, que gera um modelo capaz de identificar uma nova questão como respondível ou não, usando características presentes na grande maioria das CQAs. Experimentos com dados de diferentes CQAs mostram que o método proposto cumpre seus objetivos.
Palavras-chave:
Comunidades CQA, questões não respondíveis, classificação
Referências
Aggarwal, C. C. (2015). Mining text data. In Data Mining: The Textbook, chapter 13, pages 288–291;429–433. Springer Publishing Company, Incorporated.
Asaduzzaman, M., Mashiyat, A. S., Roy, C. K., and Schneider, K. A. (2013). Answering questions about unanswered questions of stack overflow. In Proceedings of the 10th Working Conference on Mining Software Repositories, MSR ’13, pages 97–100, Piscataway, NJ, USA. IEEE Press.
Baeza-Yates, R. and Ribeiro-Neto, B. (2008). Modern Information Retrieval. Addison-Wesley Publishing Company, USA, 2nd edition.
Chua, A. Y. and Banerjee, S. (2015). Answers or no answers: Studying question answerability in stack overflow. Journal of Information Science, 41(5):720–731.
Dror, G., Maarek, Y., and Szpektor, I. (2013). Will my question be answered? predicting ”question answerability”in community question-answering sites. In Proceedings of the 2013th European Conference on Machine Learning and Knowledge Discovery in Databases - Volume Part III, ECMLPKDD’13, pages 499–514, Berlin. Springer.
Fong, S., Zhou, S., and Moutinho, L. (2015). Text analytics for predicting question acceptance rates. IT Professional, 17(4):34–41.
Saha, R. K., Saha, A. K., and Perry, D. E. (2013). Toward understanding the causes of unanswered questions in software information sites: A case study of stack overflow. In Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering, ESEC/FSE 2013, pages 663–666, New York, NY, USA. ACM.
Srba, I. and Bielikova, M. (2016). A comprehensive survey and classification of approaches for community question answering. ACM Transactions on the Web, 10(3):18:1–18:63.
Yang, L., Bao, S., Lin, Q., Wu, X., Han, D., Su, Z., and Yu, Y. (2011a). Analyzing and predicting not-answered questions in community-based question answering services. In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI’11, pages 1273–1278. AAAI Press.
Yang, X.-S., Deb, S., and Fong, S. (2011b). Accelerated particle swarm optimization and support vector machine for business optimization and applications. Networked Digital Technologies, pages 53–66.
Zhou, S. and Fong, S. (2016). Exploring the feature selection-based data analytics solutions for text mining online communities by investigating the influential factors: A case study of programming cqa in stack overflow. In Big Data Applications and Use Cases, pages 49–93. Springer.
Asaduzzaman, M., Mashiyat, A. S., Roy, C. K., and Schneider, K. A. (2013). Answering questions about unanswered questions of stack overflow. In Proceedings of the 10th Working Conference on Mining Software Repositories, MSR ’13, pages 97–100, Piscataway, NJ, USA. IEEE Press.
Baeza-Yates, R. and Ribeiro-Neto, B. (2008). Modern Information Retrieval. Addison-Wesley Publishing Company, USA, 2nd edition.
Chua, A. Y. and Banerjee, S. (2015). Answers or no answers: Studying question answerability in stack overflow. Journal of Information Science, 41(5):720–731.
Dror, G., Maarek, Y., and Szpektor, I. (2013). Will my question be answered? predicting ”question answerability”in community question-answering sites. In Proceedings of the 2013th European Conference on Machine Learning and Knowledge Discovery in Databases - Volume Part III, ECMLPKDD’13, pages 499–514, Berlin. Springer.
Fong, S., Zhou, S., and Moutinho, L. (2015). Text analytics for predicting question acceptance rates. IT Professional, 17(4):34–41.
Saha, R. K., Saha, A. K., and Perry, D. E. (2013). Toward understanding the causes of unanswered questions in software information sites: A case study of stack overflow. In Proceedings of the 2013 9th Joint Meeting on Foundations of Software Engineering, ESEC/FSE 2013, pages 663–666, New York, NY, USA. ACM.
Srba, I. and Bielikova, M. (2016). A comprehensive survey and classification of approaches for community question answering. ACM Transactions on the Web, 10(3):18:1–18:63.
Yang, L., Bao, S., Lin, Q., Wu, X., Han, D., Su, Z., and Yu, Y. (2011a). Analyzing and predicting not-answered questions in community-based question answering services. In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, AAAI’11, pages 1273–1278. AAAI Press.
Yang, X.-S., Deb, S., and Fong, S. (2011b). Accelerated particle swarm optimization and support vector machine for business optimization and applications. Networked Digital Technologies, pages 53–66.
Zhou, S. and Fong, S. (2016). Exploring the feature selection-based data analytics solutions for text mining online communities by investigating the influential factors: A case study of programming cqa in stack overflow. In Big Data Applications and Use Cases, pages 49–93. Springer.
Publicado
25/08/2018
Como Citar
KNOCHENHAUER, Lucas V.; DORNELES, Carina F.; WIVES, Leandro K..
WANQA: uma Abordagem para Identificar Novas Questões Não Respondíveis em Comunidades de Perguntas e Respostas. In: SIMPÓSIO BRASILEIRO DE BANCO DE DADOS (SBBD), 33. , 2018, Rio de Janeiro.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2018
.
p. 1-12.
ISSN 2763-8979.
DOI: https://doi.org/10.5753/sbbd.2018.22214.
