"A Tale on Abuse and Its Detection over Online Platforms, Especially over Emails" - From the Context of Bangladesh.

NSysS(2021)

引用 0|浏览11
暂无评分
摘要
With the advent of pervasive usage of online platforms, online abusive behavior has become an indispensable part of our life demanding great attention from the research community. Accordingly, the research community is spending its effort on the demanding task, however, perhaps having much less effort on emails, even though emails are identified as a prominent source of exchanging online abusive behaviors. To fill in this gap in the literature, we conduct an in-depth study to investigate online abusive behavior having a special focus on emails. To do so, we perform a mixed-method user study consisting of formative interviews (n=15) and a survey (n=65) over user’s experience, coping strategies, etc., pertinent to online abuse in Bangladesh, especially focusing on abuse over emails. We also dig into users’ perspectives to analyze strengths and challenges associated with different types of abuse detection systems for online platforms, especially for emails. One of the noteworthy findings of our study is that there exists a significant demand for abuse detection systems over emailing platforms even after having a lesser frequency of abuse occurring over emails. Our findings also highlight a certain level of user preference for an automated abuse detection system potentially considering its more control and fewer privacy concerns to users, however, being challenged due to having the limitation of lesser ability to detect implicit abuse. We also identify several limiting factors associated with a human-moderator-based abuse detection system, including less comfort, less trust in different types of moderators, inhumane demands to the moderators, and time delay in detecting abuses. These findings point to opportunities for design interventions for hybrid abuse detection systems, which is the most preferred system to the users, to overcome all the limitations of automated and human-moderator-based systems.
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要