The AI Referee: How Online Interventions Shape Incivility and User Engagement in News Discussions

IF 4.9 1区文学 Q1 COMMUNICATION

Social Media + Society Pub Date : 2026-04-13 DOI:10.1177/20563051261428916

Georgia Kernell, Seonhye Noh

引用次数: 0

Abstract

This paper seeks to understand how online interventions shape incivility and user engagement with news comments. Using a novel dataset of over 39 million news comments on Korea’s largest online news source (Naver News), we examine changes in the share of comments that are categorized as uncivil before and after the introduction of two automated interventions aimed at flagging incivility. We trained two deep learning models to categorize comments and replicate each intervention. The findings reveal significant decreases in uncivil content following each intervention. Interestingly, we find mixed effects of the interventions on total engagement: while the number of comments and commenters decreased after the first intervention, both metrics increased after the second. Examining individual-level data reveals that the aggregate reduction in incivility cuts across all users regardless of pre-intervention incivility or commenting frequency.

查看原文本刊更多论文

人工智能裁判：在线干预如何塑造新闻讨论中的不文明行为和用户参与

本文旨在了解在线干预如何塑造新闻评论的不文明和用户参与。利用韩国最大的在线新闻来源（Naver news）上超过3900万条新闻评论的新数据集，我们研究了在引入两种旨在标记不文明行为的自动干预措施之前和之后，被归类为不文明的评论所占比例的变化。我们训练了两个深度学习模型来对评论进行分类并复制每个干预。研究结果显示，每次干预后，不文明的内容显著减少。有趣的是，我们发现干预对总参与度的影响是混合的：虽然评论和评论的数量在第一次干预后减少了，但这两个指标在第二次干预后都增加了。检查个人层面的数据显示，无论干预前的不文明行为或评论频率如何，所有用户的不文明行为总体上都有所减少。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Social Media + Society COMMUNICATION-

CiteScore

9.20

自引率

3.80%

发文量

111

审稿时长

12 weeks

期刊介绍： Social Media + Society is an open access, peer-reviewed scholarly journal that focuses on the socio-cultural, political, psychological, historical, economic, legal and policy dimensions of social media in societies past, contemporary and future. We publish interdisciplinary work that draws from the social sciences, humanities and computational social sciences, reaches out to the arts and natural sciences, and we endorse mixed methods and methodologies. The journal is open to a diversity of theoretic paradigms and methodologies. The editorial vision of Social Media + Society draws inspiration from research on social media to outline a field of study poised to reflexively grow as social technologies evolve. We foster the open access of sharing of research on the social properties of media, as they manifest themselves through the uses people make of networked platforms past and present, digital and non. The journal presents a collaborative, open, and shared space, dedicated exclusively to the study of social media and their implications for societies. It facilitates state-of-the-art research on cutting-edge trends and allows scholars to focus and track trends specific to this field of study.