Lambretta: Learning to Rank for Twitter Soft Moderation
Lambretta: Learning to Rank for Twitter Soft Moderation
复制标题
DOI：
10.1109/sp46215.2023.10179392
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Pujan Paudel;Jeremy Blackburn;Emiliano De Cristofaro;Savvas Zannettou;G. Stringhini
中科院分区：
文献类型：
--
作者：
Pujan Paudel;Jeremy Blackburn;Emiliano De Cristofaro;Savvas Zannettou;G. Stringhini
为了遏制虚假信息的问题，Twitter等社交媒体平台开始在讨论被揭穿的叙述的内容上添加警告标签，目的是为受众提供更多背景信息。不幸的是，这些标签的应用并不统一，导致大量虚假内容未经审核。本文介绍了LAMBRETTA，一个使用学习排名（LTR）自动识别软审核候选推文的系统。我们在Twitter数据上运行Lambretta，以减少与2020年美国大选相关的虚假声明，发现它标记的推文数量是Twitter的20多倍，只有3.93%的假阳性和18.81%的假阴性，优于基于关键字提取和语义搜索的其他最先进的方法。总的来说，LAMBRETTA帮助人工版主识别和标记社交媒体上的虚假信息。
To curb the problem of false information, social media platforms like Twitter started adding warning labels to content discussing debunked narratives, with the goal of providing more context to their audiences. Unfortunately, these labels are not applied uniformly and leave large amounts of false content unmoderated. This paper presents LAMBRETTA, a system that automatically identifies tweets that are candidates for soft moderation using Learning To Rank (LTR). We run Lambretta on Twitter data to moderate false claims related to the 2020 US Election and find that it flags over 20 times more tweets than Twitter, with only 3.93% false positives and 18.81% false negatives, outperforming alternative state-of-the-art methods based on keyword extraction and semantic search. Overall, LAMBRETTA assists human moderators in identifying and flagging false information on social media.