Prediction of Users' Response Time in Q&A Communities

Nikolay Burlutskiy, Andrew Fish, Nour Ali, Miltiadis Petridis

Research output: Chapter in Book/Conference proceeding with ISSN or ISBNConference contribution with ISSN or ISBN

Abstract

Social media and online Question and Answer (Q&A) communities in particular have become a successful solution for finding answers on diverse topics. However, not all questions are answered by these communities. Also, many questions are not answered quickly enough. In this paper, we propose a framework for predicting users' response time. The framework uses a diverse set of features including information on users, the content they generate while communicating, question tags, spatial and temporal features. Then these features are used as input for training predictive models by various machine learning algorithms. As a case study, three diverse Q&A communities from Stack Exchange are selected to test the framework. We demonstrate that Deep Belief Networks outperform Logistic Regression (LR), k-nearest neighbors (k-NN), and Decision Trees (DT) in the accuracy of the prediction across the three diverse Q&A communities.
Original languageEnglish
Title of host publication14th International Conference on Machine Learning and Applications (ICMLA)
Place of PublicationMiami
PublisherIEEE
Pages618-623
Number of pages6
ISBN (Print)9781509002863
DOIs
Publication statusPublished - 3 Mar 2016
Event14th International Conference on Machine Learning and Applications (ICMLA) - Miami, 9-11 December 2015
Duration: 3 Mar 2016 → …

Conference

Conference14th International Conference on Machine Learning and Applications (ICMLA)
Period3/03/16 → …

Fingerprint Dive into the research topics of 'Prediction of Users' Response Time in Q&A Communities'. Together they form a unique fingerprint.

  • Cite this

    Burlutskiy, N., Fish, A., Ali, N., & Petridis, M. (2016). Prediction of Users' Response Time in Q&A Communities. In 14th International Conference on Machine Learning and Applications (ICMLA) (pp. 618-623). IEEE. https://doi.org/10.1109/ICMLA.2015.190