As social media platforms are evolving from text-based forums into multi-modal environments, the nature of misinformation in social media is also changing accordingly. Taking advantage of the fact that visual modalities such as images and videos are more favorable and attractive to the users, and textual contents are sometimes skimmed carelessly, misinformation spreaders have recently targeted contextual correlations between modalities e.g., text and image. Thus, many research efforts have been put into development of automatic techniques for detecting possible cross-modal discordances in web-based media. In this work, we aim to analyze, categorize and identify existing approaches in addition to challenges and shortcomings they face in order to unearth new opportunities in furthering the research in the field of multi-modal misinformation detection.
翻译:由于社交媒体平台正在从基于文字的论坛演变为多种模式的环境,社交媒体中错误信息的性质也在相应改变,利用图像和视频等视觉模式对用户更为有利和更具吸引力,而且文字内容有时被轻描淡写,错误信息传播者最近针对文字和图像等模式之间的背景关联,因此,许多研究工作已投入开发自动技术,以发现网络媒体中可能的跨模式差异。在这项工作中,我们的目标是分析、分类和确定现有方法,并找出它们面临的挑战和缺点,以发现新的机会,推进多模式错误检测领域的研究。