This systematic literature review explores the use of artificial intelligence (AI) in assessing emotions within educational environments. The study aims to provide a comprehensive overview of current research, focusing on advancements, challenges, and opportunities in AI-driven emotional assessment in education. The review analyzed 41 articles from databases such as Pubmed, Web of Science, PsycINFO, and Scopus, identifying key insights related to AI and emotional assessment in educational contexts. The findings reveal various AI-driven approaches for capturing and analyzing students' emotional states during learning activities. These include emotion recognition, technology integration and learning outcomes, special education and assistive technology, and affective computing. Key AI techniques used are machine learning and facial recognition, which show promise in enhancing pedagogical strategies and creating adaptive learning environments that cater to individual emotional needs. Emerging factors such as federated learning, convolutional neural networks (CNN), recurrent neural networks (RNN), facial expression databases, and ethics in intelligent systems require further investigation. The review highlights the significance of AI in revolutionizing educational practices through emotion assessment. While advancements are evident, challenges related to accuracy, privacy, and cross-cultural validity were also identified. The synthesis of existing research emphasizes the need for further research into refining AI models for emotion recognition and the importance of ethical considerations in implementing AI technologies within educational contexts. AI has the potential to recognize and predict emotions, enabling systems like virtual assistants and Intelligent Tutoring Systems (ITS) to adapt and respond more effectively to students' emotional needs, thus enhancing the learning experience. AI also impacts social emotions such as empathy, compassion, and interpersonal phenomena like justice and cooperation, which are crucial for learning. AI can analyze empathic behavior in dynamic social contexts like educational settings and foster emotional intelligence through deep learning models that process multimodal emotional signals to generate appropriate empathic responses. Intelligent Tutoring Systems (ITS) are closely related to students' emotions, as learning and emotions are an inseparable binomial. ITS are evolving to address not only the cognitive aspect of learning but also the emotional needs of students to improve their educational experience and performance. The review highlights the importance of emotion recognition in education, technology integration and learning outcomes, special education and assistive technology, and affective computing in enhancing the educational experience. AI-based educational models, such as "MAPLE," are poised to positively influence student motivation and engagement in e-learning environments by catering to their emotional needs. The integration of AI into educational design influences learning outcomes directly, increasing motivation, self-efficacy, and the effectiveness of cognitive learning strategies within learning communities. AI's role in detecting students' emotions not only enhances productivity and academic performance but also streamlines teaching practices by allowing educators to monitor emotional states and provide targeted feedback that positively affects learning outcomes. AI applications in education are diverse, including profiling, assessment, adaptive systems, personalization, and intelligent tutoring systems. The integration of AI can support classroom interaction and discussion, as AI techniques can effectively identify significant contributions and patternsThis systematic literature review explores the use of artificial intelligence (AI) in assessing emotions within educational environments. The study aims to provide a comprehensive overview of current research, focusing on advancements, challenges, and opportunities in AI-driven emotional assessment in education. The review analyzed 41 articles from databases such as Pubmed, Web of Science, PsycINFO, and Scopus, identifying key insights related to AI and emotional assessment in educational contexts. The findings reveal various AI-driven approaches for capturing and analyzing students' emotional states during learning activities. These include emotion recognition, technology integration and learning outcomes, special education and assistive technology, and affective computing. Key AI techniques used are machine learning and facial recognition, which show promise in enhancing pedagogical strategies and creating adaptive learning environments that cater to individual emotional needs. Emerging factors such as federated learning, convolutional neural networks (CNN), recurrent neural networks (RNN), facial expression databases, and ethics in intelligent systems require further investigation. The review highlights the significance of AI in revolutionizing educational practices through emotion assessment. While advancements are evident, challenges related to accuracy, privacy, and cross-cultural validity were also identified. The synthesis of existing research emphasizes the need for further research into refining AI models for emotion recognition and the importance of ethical considerations in implementing AI technologies within educational contexts. AI has the potential to recognize and predict emotions, enabling systems like virtual assistants and Intelligent Tutoring Systems (ITS) to adapt and respond more effectively to students' emotional needs, thus enhancing the learning experience. AI also impacts social emotions such as empathy, compassion, and interpersonal phenomena like justice and cooperation, which are crucial for learning. AI can analyze empathic behavior in dynamic social contexts like educational settings and foster emotional intelligence through deep learning models that process multimodal emotional signals to generate appropriate empathic responses. Intelligent Tutoring Systems (ITS) are closely related to students' emotions, as learning and emotions are an inseparable binomial. ITS are evolving to address not only the cognitive aspect of learning but also the emotional needs of students to improve their educational experience and performance. The review highlights the importance of emotion recognition in education, technology integration and learning outcomes, special education and assistive technology, and affective computing in enhancing the educational experience. AI-based educational models, such as "MAPLE," are poised to positively influence student motivation and engagement in e-learning environments by catering to their emotional needs. The integration of AI into educational design influences learning outcomes directly, increasing motivation, self-efficacy, and the effectiveness of cognitive learning strategies within learning communities. AI's role in detecting students' emotions not only enhances productivity and academic performance but also streamlines teaching practices by allowing educators to monitor emotional states and provide targeted feedback that positively affects learning outcomes. AI applications in education are diverse, including profiling, assessment, adaptive systems, personalization, and intelligent tutoring systems. The integration of AI can support classroom interaction and discussion, as AI techniques can effectively identify significant contributions and patterns