EAGER: Collaborative: BystanderBots: Automated Bystander Intervention for Cyberbullying Mitigation

EAGER：协作：BystanderBots：缓解网络欺凌的自动旁观者干预

• 批准号: 1720268
• 负责人: Suma Bhat
• 金额: $ 20万
• 依托单位: University of Illinois at Urbana-Champaign
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-15 至 2021-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1720268&HistoricalAwards=false
• 关键词: EAGER; Collaborative; BystanderBots; Automated; Bystander

Bullying has lasting negative psychological and physical effects on victims, bystanders, and bullies alike; online settings can magnify both the scale and impact of these effects, as anonymity can embolden people to make hostile posts about individuals or groups. This project aims to reduce the prevalence of such posts through the design of active, automated "bystander interventions" in online comment threads. Bystander interventions, in which one or more witnesses to a bullying incident pressures the bully to stop, are often effective in schoolyards, but people are often reluctant to intervene in online scenarios. Instead, a computer program could post comments that contain these interventions, potentially reducing follow-on aggression from the original poster or others who might pile on -- if bullies perceive these posts as coming from human bystanders, and if bullies under the cover of pseudonyms react to bystander interventions as they do in in-person confrontations. The project will proceed in three main stages. The first stage involves improving cyberbullying detection through better detection of non-standard language use associated with bullying in a particular commenting system. The second stage involves developing a dialogue system that acts like a human bystander, creating messages that look appropriate in the context of given a comment thread and that contain psychologically-valid bystander interventions. The third stage involves deploying the tool in a large video sharing site and monitoring its ability to detect and, through interventions, mitigate further bullying. If successful, the project could have real impacts in reducing online aggression in social media systems while reducing the need for (and possible harms to) human moderators; the tools will also be released to the community to support other kinds of research around how chatbots and humans might interact in online comments.The work on detection aims to advance natural language processing (NLP) and computational pragmatics, particularly around non-canonical language use, because state-of-the-art bullying detection schemes typically use bag-of-words approaches that do not consider the linguistic and structural features of cyberbullying. The team will explore how to identify both explicit indicators of bullying, by developing topic models based on complex features where particular topics are more often associated with bullying, and implicit indicators, through looking for words whose use in a given context diverges from their location in other contexts. The context will be represented as a subspace of words, where the words themselves occur as low-dimensional word embeddings. The dialogue generation portion of the project will characterize and represent properties of effective bystander interventions from the psychology literature. This representation will drive a dialogue manager designed to generate bystander responses automatically so that the responses contain features that are both believable and are known to be effective in reducing bullying online. These components will first be evaluated through offline testing, using comment data labeled for bullying content and human ratings of the generated dialogue. Once a reasonably effective pipeline has been built, it will be evaluated in a series of online experiments in which comment threads are monitored and automated bystander responses generated for some, but not all, threads detected as containing bullying. The software will log the monitored threads and any generated responses, along with behavior both before and after the automated bystander response in a particular thread; these data will allow the team to evaluate the impact of the bystander intervention on bullying incidents later in the thread.

欺凌对受害者、旁观者和欺凌者都有持久的负面心理和生理影响；网络环境可以放大这些影响的规模和影响，因为匿名可以鼓励人们发表针对个人或团体的敌对帖子。该项目旨在通过在在线评论线程中设计主动、自动的“旁观者干预”来减少此类帖子的流行。旁观者干预，即欺凌事件的一个或多个目击者迫使欺凌者停止，在校园往往是有效的，但人们往往不愿意干预网络场景。相反，计算机程序可以发布包含这些干预措施的评论，如果恶霸认为这些帖子来自人类旁观者，如果假名掩护下的恶霸对旁观者的干预做出反应，就像他们在面对面的对抗中一样，可能会减少原始发帖者或其他人的后续攻击。该项目将分三个主要阶段进行。第一阶段涉及通过更好地检测特定评论系统中与欺凌相关的非标准语言使用来改进网络欺凌检测。第二阶段涉及开发一个对话系统，它的行为就像一个人类旁观者，创建在给定评论线程的上下文中看起来合适的消息，并包含心理上有效的旁观者干预。第三阶段涉及在大型视频分享网站部署该工具，并监测其检测并通过干预减轻进一步欺凌行为的能力。如果成功，该项目可能会对减少社交媒体系统中的在线攻击产生实际影响，同时减少对人类版主的需求（以及对人类版主的可能伤害）；这些工具还将发布给社区，以支持有关聊天机器人和人类如何在在线评论中互动的其他研究。检测方面的工作旨在推进自然语言处理（NLP）和计算语用学，特别是在非规范语言使用方面，因为最先进的欺凌检测方案通常使用词袋方法，而不考虑网络欺凌的语言和结构特征。该团队将探索如何识别欺凌的显性指标，通过开发基于复杂特征的主题模型（其中特定主题更常与欺凌相关）和隐性指标，通过寻找在特定上下文中使用的单词与其在其他上下文中的位置不同。上下文将被表示为单词的子空间，其中单词本身作为低维单词嵌入出现。该项目的对话生成部分将描述和代表心理学文献中有效的旁观者干预的属性。此表示将驱动对话管理器，该对话管理器旨在自动生成旁观者响应，以便响应包含可信且已知可有效减少在线欺凌的特征。这些组件将首先通过离线测试进行评估，使用标记为欺凌内容的评论数据和生成对话的人工评级。一旦建立了一个合理有效的管道，它将在一系列在线实验中进行评估，在这些实验中，评论线程被监控，并为一些（但不是全部）被检测为包含欺凌的线程自动生成旁观者反应。该软件将记录监控线程和任何生成的响应，以及在特定线程中自动旁观者响应之前和之后的行为；这些数据将使团队能够评估旁观者干预对后续欺凌事件的影响。

项目成果

Self-Supervised Euphemism Detection and Identification for Content Moderation

• DOI: 10.1109/sp40001.2021.00075
• 发表时间: 2021-03
• 期刊: 2021 IEEE Symposium on Security and Privacy (SP)
• 作者: Wanzheng Zhu;Hongyu Gong;Rohan Bansal;Zachary Weinberg;Nicolas Christin;G. Fanti;S. Bhat

Generate, Prune, Select: A Pipeline for Counterspeech Generation against Online Hate Speech

• DOI: 10.18653/v1/2021.findings-acl.12
• 发表时间: 2021-06
• 期刊: ArXiv
• 作者: Wanzheng Zhu;S. Bhat

Abusive Language Detection in Heterogeneous Contexts: Dataset Collection and the Role of Supervised Attention

• DOI: 10.1609/aaai.v35i17.17738
• 发表时间: 2021-05
• 作者: Hongyu Gong;Alberto Valido;Katherine M. Ingram;G. Fanti;S. Bhat;D. Espelage