TY - GEN
T1 - Hate, Obscenity, and Insults
T2 - 30th World Wide Web Conference, WWW 2021
AU - Alshamrani, Sultan
AU - Abusnaina, Ahmed
AU - Abuhamad, Mohammed
AU - Nyang, Daehun
AU - Mohaisen, David
N1 - Funding Information:
Acknowledgement. This work was supported in part by NRF grant NRF-2016K1A1A2912757 (GRL program), GPU award by NVIDIA.
Publisher Copyright:
© 2021 ACM.
PY - 2021/4/19
Y1 - 2021/4/19
N2 - Social media has become an essential part of the daily routines of children and adolescents. Moreover, enormous efforts have been made to ensure the psychological and emotional well-being of young users as well as their safety when interacting with various social media platforms. In this paper, we investigate the exposure of those users to inappropriate comments posted on YouTube videos targeting this demographic. We collected a large-scale dataset of approximately four million records and studied the presence of five age-inappropriate categories and the amount of exposure to each category. Using natural language processing and machine learning techniques, we constructed ensemble classifiers that achieved high accuracy in detecting inappropriate comments. Our results show a large percentage of worrisome comments with inappropriate content: we found 11% of the comments on children's videos to be toxic, highlighting the importance of monitoring comments, particularly on children's platforms.
AB - Social media has become an essential part of the daily routines of children and adolescents. Moreover, enormous efforts have been made to ensure the psychological and emotional well-being of young users as well as their safety when interacting with various social media platforms. In this paper, we investigate the exposure of those users to inappropriate comments posted on YouTube videos targeting this demographic. We collected a large-scale dataset of approximately four million records and studied the presence of five age-inappropriate categories and the amount of exposure to each category. Using natural language processing and machine learning techniques, we constructed ensemble classifiers that achieved high accuracy in detecting inappropriate comments. Our results show a large percentage of worrisome comments with inappropriate content: we found 11% of the comments on children's videos to be toxic, highlighting the importance of monitoring comments, particularly on children's platforms.
KW - NLP
KW - Online Behavior Analysis
KW - YouTube Comments
UR - http://www.scopus.com/inward/record.url?scp=85107626898&partnerID=8YFLogxK
U2 - 10.1145/3442442.3452314
DO - 10.1145/3442442.3452314
M3 - Conference contribution
AN - SCOPUS:85107626898
T3 - The Web Conference 2021 - Companion of the World Wide Web Conference, WWW 2021
SP - 508
EP - 515
BT - The Web Conference 2021 - Companion of the World Wide Web Conference, WWW 2021
PB - Association for Computing Machinery, Inc
Y2 - 19 April 2021 through 23 April 2021
ER -