Emotions play an important role in the learning process. With intelligent technology support, identification and intervention of learners’ cognition have made great achievement, but the care of emotion has been in the absence for a long time. In recent years, the use of affective computing technology to solve affective loss in online education has become a key research topic. To date, a growing number of studies have investigated automated emotion recognition (AER) in online environments. However, AER has been mainly studied from the perspective of computer science focusing on technical characteristics of developing AI technology while its pedagogical value and educational application has been overlooked. Therefore, this systematic literature review aimed to bring together educational and technical aspects of AER. Following PRISMA methodology, a comprehensive search of AER research from 2010 to 2024 in three databases (Web of Science, Science Direct and IEEE Xplore) identified 117 studies that met inclusion criteria. The articles were coded for report characteristics, educational characteristics (tech platform, pedagogy, assessment, content), technical characteristics (emotion model, emotion category, emotion measurement channel, database, algorithm model) and outcome characteristics (technical result, educational application). We found that the primary purpose of these studies was to develop and evaluate systems for AER, rather than implementing these systems in real online learning environments. Furthermore, our findings indicated a lack of integration between computer science and educational science in the realm of AER. Despite the fact that most algorithm models demonstrated high accuracy in AER, the interpretability of the results was significantly constrained by the quality of the databases used, along with the scarcity of studies focusing on the effective and real-time application of AER results. These findings provide essential guidance for shaping future research and development pathways in this field.

中文翻译：

---

连接计算机和教育科学：在线学习环境中自动情绪识别的系统回顾


情绪在学习过程中起着重要作用。在智能技术的支持下，学习者认知的识别和干预取得了巨大的成就，但情感的关怀却长期缺乏。近年来，利用情感计算技术解决在线教育中的情感损失已成为重点研究课题。迄今为止，越来越多的研究调查了在线环境中的自动情绪识别（AER）。然而，人们主要从计算机科学的角度对AER进行研究，侧重于开发人工智能技术的技术特征，而忽视了其教学价值和教育应用。因此，本系统文献综述旨在将 AER 的教育和技术方面结合起来。按照 PRISMA 方法，对三个数据库（Web of Science、Science Direct 和 IEEE Xplore）中 2010 年至 2024 年的 AER 研究进行了全面检索，确定了 117 项符合纳入标准的研究。文章按报告特征、教育特征（技术平台、教学法、评估、内容）、技术特征（情感模型、情感类别、情感测量通道、数据库、算法模型）和成果特征（技术成果、教育应用）进行编码。我们发现这些研究的主要目的是开发和评估 AER 系统，而不是在真实的在线学习环境中实施这些系统。此外，我们的研究结果表明，在 AER 领域，计算机科学和教育科学之间缺乏整合。 尽管大多数算法模型在 AER 方面表现出较高的准确性，但结果的可解释性受到所用数据库质量的严重限制，而且缺乏关注 AER 结果有效和实时应用的研究。这些发现为塑造该领域未来的研究和开发路径提供了重要指导。