TY - GEN
T1 - The role of comments' controversy in large-scale online discussion forums
AU - Aggarwal, Adithya
AU - López, Claudia
AU - Hsiao, Ihan
N1 - Funding Information:
From the Stratton Laboratory for the Study of Liver Disease, Department of Pathology, Mount Sinai School of Medicine of the City University of New York, New York, New York 10029, and the Roche Institute of Molecular Biology, Nutley, New Jersey 07110. Some of the original observations reported have been conducted under U.S. Public Health Service Grant AM 03846 and under U.S. Army Medical Research and Development Command Contract DA-49-193-MD.2822. Requests for reprints should be addressed to Dr. Hans Popper, Department of Pathology, Mount Sinai School of Medicine of the City University of New York, Fifth Avenue and lOOth Street, New York, New York 10029.
Publisher Copyright:
© 2016 ACM.
PY - 2016/7/10
Y1 - 2016/7/10
N2 - In this paper, we examine the value of comments in large-scale discussion forums. We survey the relevant literature and employ the key content quality identification features. We then construct comment semantics features and build several regression models to explore the value of comment semantics dynamics. The results reconfirm the usefulness of several essential quality predictors, including time, reputation, length, and editorship. We also found that comment semantics are valuable to shape the answer quality. Specifically, the diversity of comments significantly contributes to the answer quality. In addition, when searching for good quality answers, it is important to look for diversity in the comments, rather than observing local differences (disputable content). Finally, the presence of comments shepherds the community to revise the posts by attracting attentions to the posts and eventually facilitate the editing process.
AB - In this paper, we examine the value of comments in large-scale discussion forums. We survey the relevant literature and employ the key content quality identification features. We then construct comment semantics features and build several regression models to explore the value of comment semantics dynamics. The results reconfirm the usefulness of several essential quality predictors, including time, reputation, length, and editorship. We also found that comment semantics are valuable to shape the answer quality. Specifically, the diversity of comments significantly contributes to the answer quality. In addition, when searching for good quality answers, it is important to look for diversity in the comments, rather than observing local differences (disputable content). Finally, the presence of comments shepherds the community to revise the posts by attracting attentions to the posts and eventually facilitate the editing process.
KW - Constructive learning
KW - Content controversy
KW - Discussion forum
KW - Programming
KW - Q&A
KW - Stackoverflow
UR - http://www.scopus.com/inward/record.url?scp=84980328147&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84980328147&partnerID=8YFLogxK
U2 - 10.1145/2914586.2914636
DO - 10.1145/2914586.2914636
M3 - Conference contribution
AN - SCOPUS:84980328147
T3 - HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media
SP - 179
EP - 182
BT - HT 2016 - Proceedings of the 27th ACM Conference on Hypertext and Social Media
PB - Association for Computing Machinery, Inc
T2 - 27th ACM Conference on Hypertext and Social Media, HT 2016
Y2 - 10 July 2016 through 13 July 2016
ER -