ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2021, Vol. 58 ›› Issue (2): 253-263.doi: 10.7544/issn1000-1239.2021.20200727

所属专题: 2021数据治理与数据透明专题

• 人工智能 • 上一篇    下一篇



  1. 1(广西可信软件重点实验室(桂林电子科技大学) 广西桂林 541004);2(暨南大学信息科学技术学院/网络空间安全学院 广州 510632) (
  • 出版日期: 2021-02-01
  • 基金资助: 

Ethical Behavior Discrimination Based on Social News Dataset

Gu Tianlong1, Feng Xuan1, Li Long1,2, Bao Xuguang1, Li Yunhui1   

  1. 1(Guangxi Key Laboratory of Trusted Software (Guilin University of Electronic Technology), Guilin, Guangxi 541004);2(College of Information Science and Technology/College of Cyber Security, Jinan University, Guangzhou 510632)
  • Online: 2021-02-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (U1711263, U1811264, 61966009, 61961007, 61862016, 62006057), the Natural Science Foundation of Guangxi Province (2019GXNSFBA245049, 2019GXNSFBA245059, 2018GXNSFDA281045), and the Science and Technology Base and Talents Program of Guangxi Province (AD19245011).

摘要: 人工智能(artificial intelligence, AI)应用的伦理风险和挑战引起了人们的普遍关注,如何从技术实现角度开发出遵守人类价值观和伦理规范的AI系统,即,符合伦理的AI设计,是亟需解决的重要问题之一.基于机器学习的伦理与道德判别是此方面的有益探索.社会新闻数据具有丰富的伦理和道德的内容及知识,为机器学习的训练数据开发提供了可能.鉴于此,本文构建了具有人类行为伦理和道德属性的社会新闻数据集,附之以法律与行为规范数据集,用以机器学习的训练和测试;建立了基于使用信息实体的增强语言表示(enhanced language representation of information entities, ERNIE)和卷积神经网络(convolutional neural network, CNN)的伦理行为判别模型ERNIE-CNN,通过词的向量表示计算语义相似度来提取关于行为的伦理判断.实验结果表明,提出的模型具有比基准模型更好的性能,验证了方法和模型的有效性.

关键词: 社会新闻数据集, 符合伦理的设计, 深度学习, ERNIE, CNN

Abstract: With the broader applications of artificial intelligence (AI), their ethical and moral issues have attracted more and more concerns. How to develop an AI system that complies with human values and ethical norms from the perspective of technology realization, namely, ethical aligned AI design, is one of the important issues that need to be solved urgently. The ethical and moral discrimination based on machine learning is a beneficial exploration in this aspect. Social news data has rich content and knowledge of ethics and morality, which provides the possibility for the training data development of machine learning. Because of this, this paper constructs a social news dataset with ethics and morality of human behavior, which is attached to law and code of conduct dataset for machine learning training and testing. The ethical behavior discrimination model ERNIE-CNN based on enhanced language representation of information entities (ERNIE) and convolutional neural network (CNN), is developed to extract ethical discriminations about behavior by calculating semantic similarity based on the vector representation of words. The experimental results show that the proposed model has better performance than the baseline models.

Key words: social news dataset, ethically aligned design, deep learning, ERNIE, CNN