Recent years have witnessed the increasing popu-larity of mobile and networking devices,as well as social networking sites,where users engage in a variety of activities in the cyberspace on a daily and real-time basis.While such systems provide tremendous convenience and enjoyment for users,malicious usages,such as bullying,cruelty,extremism,and toxi-city behaviors,also grow noticeably,and impose significant threats to individuals and communities.In this paper,we review computational approaches for cyberbullying and cyberviolence detection,in order to understand two major factors:1)What are the defining features of online bullying users,and 2)How to detect cyberbullying and cyberviolence.To achieve the goal,we propose a user-activities-content(UAC)triangular view,which defines that users in the cyberspace are centered around the UAC triangle to carry out activities and generate content.Accordingly,we categorize cyberbully features into three main categories:1)User centered features,2)Content centered features,and 3)Activity centered features.After that,we review methods for cyberbully detection,by taking supervised,unsupervised,transfer learning,and deep learning,etc.,into consideration.The UAC centered view provides a coherent and complete summary about features and characteristics of online users(their activities),approaches to detect bullying users(and malicious content),and helps defend cyberspace from bullying and toxicity.

Shuwen Wang;Xingquan Zhu;Weiping Ding;Amir Alipour Yengejeh

Department of Electrical Engineering and Computer Science,Florida Atlantic University,Boca Raton,FL 33431 USA;School of Information Science and Technology,Nantong University,Nantong 226019,China

自动化学报（英文版）

[1]Shuwen Wang;Xingquan Zhu;Weiping Ding;Amir Alipour Yengejeh-.Cyberbullying and Cyberviolence Detection:A Triangular User-Activity-Content View)[J].自动化学报（英文版）,2022(08):1384-1405

Cyberbullying,Cyberviolence,cruelty,extremism,toxi,cyberbullying,cyberviolence,cyberbully

Detection,Triangular,User,Activity,Content,View,Recent,years,have,witnessed,increasing,popu,larity,mobile,networking,devices,well,social,sites,where,users,engage,variety,activities,cyberspace,daily,real,basis,While,such,systems,tremendous,convenience,enjoyment,malicious,usages,behaviors,also,grow,noticeably,impose,significant,threats,individuals,communities,In,this,paper,review,computational,approaches,detection,order,understand,major,factors,What,are,defining,features,online,How,To,achieve,goal,propose,content,UAC,triangular,which,defines,that,centered,around,triangle,carry,generate,Accordingly,categorize,into,three,main,categories,After,methods,by,taking,unsupervised,transfer,learning,deep,etc,consideration,provides,coherent,complete,summary,about,characteristics,their,helps,defend,from,toxicity

0.512526