Feature Extraction to Filter Out Low-Quality Answers from Social Question Answering Sites

Abstract

Social Question Answering sites (SQAs) are online platforms that allow Internet users to ask questions, and obtain answers from others in the community. SQAs have been marred by the problem of low-quality answers. Worryingly, answer quality on SQAs have been reported to be following a downward trajectory in recent years. To this end, existing research has predominantly focused on finding the best answer, or identifying high-quality answers among the available responses. However, such scholarly efforts have not reduced the volume of low-quality answers on SQAs. Therefore, the goal of this research is to extract features in order to weed out low-quality answers as soon as they are posted on SQAs. Data from Stack Exchange was used to carry out the investigation. Informed by the literature, 26 features were extracted. Thereafter, machine learning algorithms were implemented that could correctly identify 85% to 96% of low-quality answers. The key contribution of this research is the development of a system to detect subpar answers on the fly at the time of posting. It is intended to be used as an early warning system that warns users about answer quality at the point of posting.

KEYWORDS:

• Answer quality
• Data balancing
• Low-quality answers
• Social question answering

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the author(s).

Notes

1 https://archive.org/details/stackexchae [accessed online in January, 2017].

Additional information

Notes on contributors

Pradeep Kumar Roy

Pradeep Kumar Roy is currently an assistant professor with the Department of Computer Science and Engineering, Indian Institute of Information Technology (IIIT), Surat. He received his PhD in computer science and engineering from the National Institute of Technology Patna, in 2018. His area of specialisation straddles across question answering, text mining and information retrieval, and wireless sensor networks. He has published articles in different Journals, including IJIM, Neural Processing Letters, Neural Computing and Applications, Future Generation Computer Systems, and others. He has also published the papers in proceedings of various international conferences. E-mail: [email protected]

Zishan Ahmad

Zishan Ahmad received his BTech degree in computer science and engineering in 2013. He received MTech in information technology from National Institute of Technology Patna in 2017. Currently, he is working as a PhD research scholar in the Department of Computer Science and Engineering, Indian Institute of Technology (IIT), Patna. His current research area is in text mining and data analytics, social analytics. E-mail: [email protected]

Jyoti Prakash Singh

Jyoti Prakash Singh is an assistant professor in the Department of Computer science and Engineering in National Institute of Technology Patna. He has co-authored seven books in the area of C programming, data structures, operating systems and ad hoc networks. Apart from this, he has around 25 papers in international journals and more than 40 international conference proceedings. His research interests include text mining, deep learning, social network and information security. He is associate editor of International Journal of Electronic Government Research (IJEGR).

Snehasish Banerjee

Snehasish Banerjee is a lecturer at the York Management School in the University of York. He holds a PhD from Nanyang Technological University. His area of specialisation straddles across information science and digital marketing. His works have appeared in outlets such as Computers in human behaviour, internet research, journal of the Association for Information Science and Technology, Online Information Review, and Tourism Management. E-mail: [email protected]