了解仇恨言论:HateInsights数据集和模型可解释性
Muhammad Umair Arshad1, Waseem Shahzad1
1Department of Artificial Intelligence and Data Science, National University of Computer and Emerging Sciences, Islamabad, Pakistan.
PeerJ. Computer science
|December 9, 2024
概括
新的仇恨言论数据集提高了模型的解释性. 即使是先进的模型也难以解释,但人类注释的理由对透明的仇恨言论检测有希望.
科学领域:
- 自然语言处理自然语言处理.
- 计算社会科学 计算社会科学
- 人工智能伦理学 人工智能伦理学
背景情况:
- 在线仇恨言论在社交媒体平台上仍然是一个重大挑战.
- 现有的仇恨言论检测模型缺乏足够的解释性和解释性.
- 需要全面的数据集,支持在这个领域中解释性AI.
研究的目的:
- 介绍HateInsights数据集,这是仇恨言论研究的新基准.
- 评估最新的仇恨言论检测模型的可解释性.
- 调查人类注释的理由对模型性能和可解释性的影响.
主要方法:
- 开发了带有双重注释的HateInsights数据集:三类分类 (仇恨言论,冒犯性语言,正常话语) 和支持的理由.
- 利用最先进的模型来对仇恨言论进行分类和可解释性评估.
- 分析了对分类和可解释性指标 (可信度,可信度) 的模型性能.
主要成果:
- 先进的仇恨言论检测模型显示了可解释性指标的局限性,例如可信性和忠实性.
- 用人类注释的理性训练的模型表现出更好的解释性.
- 仇恨见解数据集为推进可解释的仇恨言论检测研究提供了宝贵的资源.
结论:
- 在仇恨言论检测方面,解释性仍然是一个关键挑战,即使对于高性能模型来说也是如此.
- 人类注释的推理为提高模型透明度和公平性提供了一个有希望的途径.
- 发布HateInsights数据集和代码库的目的是促进协作研究,并推动内容调节的伦理人工智能的进展.
相关概念视频
02:16Stereotype Content Model
14.0K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.0K
02:55Stereotypes, Prejudice, and Discrimination
90.0K
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who...
90.0K
01:12Hindsight Biases
3.4K
Hindsight bias leads you to believe that the event you just experienced was predictable, even though it really wasn’t. In other words, you knew all along that things would turn out the way they did. Can you relate this to the phrase "Hindsight is 20/20" now?
3.4K
01:11Statistical Analysis: Overview
6.1K
When we take repeated measurements on the same or replicated samples, we will observe inconsistencies in the magnitude. These inconsistencies are called errors. To categorize and characterize these results and their errors, the researcher can use statistical analysis to determine the quality of the measurements and/or suitability of the methods.
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
One of the most commonly used statistical quantifiers is the mean, which is the ratio between the sum of the numerical values of all results and the...
6.1K
02:13The Representativeness Heuristic
15.8K
The representative heuristic describes a biased way of thinking, in which you unintentionally stereotype someone or something. For example, you may assume that your professors spend their free time reading books and engaging in intellectual conversation, because the idea of them spending their time playing volleyball or visiting an amusement park does not fit in with your stereotypes of professors.
15.8K
01:16Statistical Hypothesis Testing
1.9K
Hypothesis testing is a critical statistical procedure facilitating informed, evidence-based decisions. It begins with a hypothesis, which is a tentative explanation, or a prediction about a population parameter. This hypothesis can be either a null hypothesis (H0), indicating no effect or difference, or an alternative hypothesis (Ha), suggesting an effect or difference.
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
Statistical significance measures the probability that an observed result occurred by chance. If this probability, known as...
1.9K