TY - GEN
T1 - When the crowd is not enough
T2 - 19th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2016
AU - Pelleg, Dan
AU - Rokhlenko, Oleg
AU - Szpektor, Idan
AU - Agichtein, Eugene
AU - Guy, Ido
N1 - Publisher Copyright:
© 2016 ACM.
PY - 2016/2/27
Y1 - 2016/2/27
N2 - Social media gives voice to the people, but also opens the door to low-quality contributions, which degrade the experience for the majority of users. To address the latter issue, the prevailing solution is to rely on the "wisdom of the crowds" to promote good content (e.g., via votes or "like" buttons), or to downgrade bad content. Unfortunately, such crowd feedback may be sparse, subjective, and slow to accumulate. In this paper, we investigate the effects, on the users, of automatically filtering question-answering content, using a combination of syntactic, semantic, and social signals. Using this filtering, a large-scale experiment with real users was performed to measure the resulting engagement and satisfaction. To our knowledge, this experiment represents the first reported large-scale user study of automatically curating social media content in real time. Our results show that automated quality filtering indeed improves user engagement, usually aligning with, and often outperforming, crowd-based quality judgments.
AB - Social media gives voice to the people, but also opens the door to low-quality contributions, which degrade the experience for the majority of users. To address the latter issue, the prevailing solution is to rely on the "wisdom of the crowds" to promote good content (e.g., via votes or "like" buttons), or to downgrade bad content. Unfortunately, such crowd feedback may be sparse, subjective, and slow to accumulate. In this paper, we investigate the effects, on the users, of automatically filtering question-answering content, using a combination of syntactic, semantic, and social signals. Using this filtering, a large-scale experiment with real users was performed to measure the resulting engagement and satisfaction. To our knowledge, this experiment represents the first reported large-scale user study of automatically curating social media content in real time. Our results show that automated quality filtering indeed improves user engagement, usually aligning with, and often outperforming, crowd-based quality judgments.
KW - A/b testing
KW - Automatic quality evaluation
KW - Quantitative analysis
KW - User engagement
UR - http://www.scopus.com/inward/record.url?scp=84963614945&partnerID=8YFLogxK
U2 - 10.1145/2818048.2820022
DO - 10.1145/2818048.2820022
M3 - Conference contribution
AN - SCOPUS:84963614945
T3 - Proceedings of the ACM Conference on Computer Supported Cooperative Work, CSCW
SP - 1080
EP - 1090
BT - Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work and Social Computing, CSCW 2016
PB - Association for Computing Machinery
Y2 - 27 February 2016 through 2 March 2016
ER -