Allein Liesbeth, Moens Marie-Francine, Perrotta Domenico
European Commission, Joint Research Centre (JRC), Italy.
Department of Computer Science, KU Leuven, Belgium.
Inf Process Manag. 2023 Mar;60(2):None. doi: 10.1016/j.ipm.2022.103206.
A news article's online audience provides useful insights about the article's identity. However, fake news classifiers using such information risk relying on profiling. In response to the rising demand for ethical AI, we present a profiling-avoiding algorithm that leverages Twitter users during model optimisation while excluding them when an article's veracity is evaluated. For this, we take inspiration from the social sciences and introduce two objective functions that maximise correlation between the article and its spreaders, and among those spreaders. We applied our profiling-avoiding algorithm to three popular neural classifiers and obtained results on fake news data discussing a variety of news topics. The positive impact on prediction performance demonstrates the soundness of the proposed objective functions to integrate social context in text-based classifiers. Moreover, statistical visualisation and dimension reduction techniques show that the user-inspired classifiers better discriminate between unseen fake and true news in their latent spaces. Our study serves as a stepping stone to resolve the underexplored issue of profiling-dependent decision-making in user-informed fake news detection.
一篇新闻文章的在线受众能提供有关该文章特征的有用见解。然而，使用此类信息的假新闻分类器有依赖用户画像的风险。为响应人们对符合伦理的人工智能日益增长的需求，我们提出一种避免用户画像的算法，该算法在模型优化期间利用推特用户，但在评估文章真实性时将他们排除在外。为此，我们从社会科学中汲取灵感，引入两个目标函数，使文章与其传播者之间以及这些传播者之间的相关性最大化。我们将我们的避免用户画像算法应用于三种流行的神经分类器，并在讨论各种新闻主题的假新闻数据上获得了结果。对预测性能的积极影响证明了所提出的目标函数在基于文本的分类器中整合社会背景的合理性。此外，统计可视化和降维技术表明，受用户启发的分类器在其潜在空间中能更好地区分未见过的假新闻和真实新闻。我们的研究是解决在用户信息辅助的假新闻检测中尚未充分探索的依赖用户画像进行决策这一问题的垫脚石。
