The Blame Game: Understanding Blame Assignment in Social Media
The Blame Game: Understanding Blame Assignment in Social Media
复制标题
DOI：
10.1109/tcss.2023.3261242
复制
发表时间：
2023-02
影响因子：
5
通讯作者：
Rui Xi;Munindar P. Singh
中科院分区：
文献类型：
--
作者：
Rui Xi;Munindar P. Singh
道德心理学研究提出了潜在的语言和语义因素。然而，目前的实证研究往往缺乏现实生活的细微差别和复杂性。这篇文章考察了之前的研究结果如何很好地概括了提交给一个流行的社交媒体论坛的30000多个紧张社会情境的叙述。海报描述人际道德状况或疑虑；其他用户从帖子中判断是发帖者（主角）还是反对方（对手）在道德上有罪。我们扩展并应用自然语言处理（NLP）技术来理解这些帖子中涉及的人的描述的影响。我们进行了大量的实验来研究特征的效应大小，以了解它们如何影响社交媒体上的责任分配。我们的研究结果表明，综合心理学理论有助于理解现实生活中的道德状况。我们还在社交媒体上发现了偏见指责分配的证据，比如男性更容易受到指责，无论他们是主角还是对手。
Psychological studies on morality have proposed underlying linguistic and semantic factors. However, current empirical studies often lack the nuances and complexity of real life. This article examines how well the findings of prior studies generalize to a corpus of over 30000 narratives of tense social situations submitted to a popular social media forum. A poster describes interpersonal moral situations or misgivings; other users judge from the post whether the poster (protagonist) or an opposing side (antagonist) is morally culpable. We extend and apply natural language processing (NLP) techniques to understand the effects of descriptions of the people involved in these posts. We conduct extensive experiments to investigate the effect sizes of features to understand how they affect the assignment of blame on social media. Our findings show that aggregating psychological theories enables understanding real-life moral situations. We also find evidence of bias blame assignment on social media, such as that males are likelier to receive blame no matter whether they are protagonists or antagonists.