arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01646cs.SIcs.HCcs.IR
收藏

TweetInfo:一个用于减轻在线伤害的交互式系统

TweetInfo: An Interactive System to Mitigate Online Harm

Gautam Kishore Shahi

AI总结:

针对社交媒体仇恨言论与错误信息问题,本文提出交互式系统 TweetInfo,通过内容分析和多维元信息过滤帮助用户自定义时间线,从而减少有害内容消费。

摘要:

社交网站(SNSs)活跃用户的增加,也伴随着社交媒体网站上有害内容的增多。有害内容被描述为旨在伤害或欺骗个人或一群用户的不当活动。除了现有的错误信息和仇恨言论检测方法之外,用户仍需充分了解 SNSs 上内容的有害性。本研究提出了一个用户交互系统 TweetInfo,通过提供帖子的元信息来减少用户对有害内容的消费。它聚焦于两类有害内容:仇恨言论和错误信息。TweetInfo 通过内容分析提供对推文的洞察。基于以往研究,我们选取了一系列元信息,并提供依据元信息过滤内容的选项,包括 Bot(机器人账号)、Hate Speech(仇恨言论)、Misinformation(错误信息)、Verified Account(认证账号)、Sentiment(情感)、Tweet Category(推文类别)和 Language(语言)。所提出的用户界面允许自定义用户时间线,以减轻有害内容。本研究展示了 TweetInfo 所提议用户界面的演示版本。

英文摘要:

The increase in active users on social networking sites (SNSs) has also observed an increase in harmful content on social media sites. Harmful content is described as an inappropriate activity to harm or deceive an individual or a group of users. Alongside existing methods to detect misinformation and hate speech, users still need to be well-informed about the harmfulness of the content on SNSs. This study proposes a user-interactive system TweetInfo for mitigating the consumption of harmful content by providing metainformation about the posts. It focuses on two types of harmful content: hate speech and misinformation. TweetInfo provides insights into tweets by doing content analysis. Based on previous research, we have selected a list of metainformation. We offer the option to filter content based on metainformation Bot, Hate Speech, Misinformation, Verified Account, Sentiment, Tweet Category, Language. The proposed user interface allows customising the user's timeline to mitigate harmful content. This study present the demo version of the propose user interface of TweetInfo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑