CC BY
10INTERNATIONAL SCIENTIFIC AND TECHNICAL CONFERENCE "DIGITAL TECHNOLOGIES: PROBLEMS AND SOLUTIONS OF PRACTICAL IMPLEMENTATION IN THE SPHERES" APRIL 27-28, 2023
USING AFFECTIVE COMPUTING SYSTEMS IN MODERN EDUCATION Kurbanov Abdurahmon Alishboyevich
Doctoral student of the Department of Computer Science and Programming of the Jizzakh branch of the National University of Uzbekistan named after Mirzo Uligbek https://doi.org/10.5281/zenodo.7856325
Abstract. It is becoming a trend to apply an emotional lens and to position emotions as central to educational interactions. Recently, affective computing has been one of the most actively research topics in education, attracting much attention from both academics and practitioners. However, despite the increasing number of papers published, there still are deficiencies and gaps in the comprehensive literature review in the specific area of affective computing in education. Affective measurement channels are classified into textual, visual, vocal, physiological, and multimodal channels, while the textual channel is recognized as the most widely-used affective measurement channel.
Keywords: Affective computing, Emotion Recognition Systems, Detecting boredom and disengagement, Personalizing learning experiences, Facial Recognition.
Affective computing is a field of study that focuses on developing technology that can recognize and respond to human emotions. In the context of education, affective computing has the potential to revolutionize the way we teach and learn by enabling personalized learning experiences that are tailored to each student's emotional state. In this article, we will discuss the benefits of affective computing in education and explore some of the ways it can be integrated into different educational settings.
Applied Affective Computing is a field that combines computer science, psychology, and other related disciplines to develop systems and applications that can detect, interpret, and respond to human emotions. It involves the use of various technologies such as machine learning, natural language processing, and computer vision to analyze and interpret human emotions in real-time.
Applications of applied affective computing include developing intelligent systems that can adapt to a user's emotional state, creating virtual assistants that can respond appropriately to emotional cues, and designing healthcare technologies that can monitor and respond to a patient's emotional state.
Some of the key research areas in applied affective computing include emotion recognition, affective sensing, affective computing interfaces, and affective computing applications. The ultimate goal of this field is to create more empathetic and intuitive technology that can understand and respond to human emotions in a more natural and human-like way.
Benefits of Emotion Recognition Systems in Education
Emotion recognition systems offer several benefits in education, including:
Personalized learning experiences: Emotion recognition systems can identify when a student is struggling, anxious, or bored and provide personalized resources and support to help them better engage with the learning experience. This can result in better learning outcomes, as students are more likely to stay motivated and focused when the learning experience is tailored to their needs.
Early intervention: Emotion recognition systems can help identify when students are struggling before it becomes a bigger problem. By detecting early signs of anxiety or
INTERNATIONAL SCIENTIFIC AND TECHNICAL CONFERENCE "DIGITAL TECHNOLOGIES: PROBLEMS AND SOLUTIONS OF PRACTICAL IMPLEMENTATION IN THE SPHERES" APRIL 27-28, 2023
disengagement, teachers can intervene and provide additional support to help students overcome their challenges.
Improved engagement: Emotion recognition systems can help teachers understand how students are feeling and adjust their teaching approaches accordingly. This can result in improved engagement, as teachers can use strategies that resonate with students' emotional states and keep them motivated and interested in the learning experience.
Better assessment: Emotion recognition systems can provide valuable data to help teachers assess students' learning progress and emotional states. This can help educators identify areas where students need more support and adjust their teaching strategies to better meet their needs.
Emotion recognition systems in Monitoring student engagement
Emotion recognition systems can play an important role in monitoring student engagement in educational settings. By using sensors and other technologies to detect students' emotional states, these systems can provide real-time feedback to teachers and help them adjust their teaching strategies to better engage and support students.
Here are some ways emotion recognition systems can be used to monitor student engagement:
Detecting boredom and disengagement: Emotion recognition systems can detect when students are bored, disengaged, or distracted, allowing teachers to intervene and adjust their teaching strategies accordingly. For example, the system may alert the teacher to change the pace of the lesson or provide more engaging activities to re-engage the student.
Monitoring emotional states: Emotion recognition systems can monitor students' emotional states, such as stress, anxiety, or frustration, which can negatively affect engagement and learning outcomes. By detecting these emotions, teachers can provide additional support or resources to help students manage their emotions and stay engaged.
Providing feedback on teaching effectiveness: Emotion recognition systems can also provide feedback on the teacher's effectiveness in engaging and supporting students. For example, the system may provide data on how often students are distracted or disengaged during a particular lesson or activity, allowing the teacher to adjust their teaching strategies accordingly.
Personalizing learning experiences: Emotion recognition systems can help personalize the learning experience for each student based on their emotional state and engagement levels. For example, the system may recommend different types of content or activities based on the student's emotional state or learning preferences.
An Emotion Recognition Model Based on Facial Recognition in Virtual Learning Environment can be used to enhance the student's engagement and learning experience in virtual learning environments. This model involves using facial recognition techniques to detect and classify emotions from students' facial expressions in real-time.
The model typically involves the following steps:
Data collection: Images or videos of students' facial expressions are collected using a camera or webcam.
Preprocessing: The collected images are preprocessed to remove noise, distortions, and other artifacts that may affect the accuracy of emotion detection.
INTERNATIONAL SCIENTIFIC AND TECHNICAL CONFERENCE "DIGITAL TECHNOLOGIES: PROBLEMS AND SOLUTIONS OF PRACTICAL IMPLEMENTATION IN THE SPHERES" APRIL 27-28, 2023
Feature extraction: Facial features, such as eye movements, eyebrow movements, mouth movements, and head position, are extracted from the preprocessed images using computer vision techniques.
Emotion classification: Machine learning algorithms, such as support vector machines (SVM), artificial neural networks (ANN), or deep learning models, are used to classify the extracted features into different emotions, such as happiness, sadness, anger, or surprise.
Feedback generation: The detected emotions are used to provide real-time feedback to the student or teacher, such as adjusting the difficulty level of the content, providing additional support or resources, or adapting the teaching style to better suit the student's needs.
The advantages of using an emotion recognition model based on facial recognition in virtual learning environments include:
Improved student engagement: By providing personalized feedback and adapting the learning content to the student's emotional state, the model can enhance the student's engagement and motivation to learn.
Enhanced learning outcomes: By adapting the learning content and teaching style to the student's needs, the model can improve the student's learning outcomes and performance.
Real-time feedback: The model provides real-time feedback to the student or teacher, allowing for immediate intervention and support if necessary.
However, there are also some limitations and challenges associated with this model, such as privacy concerns, ethical issues, and potential biases in the data and algorithms used. Therefore, it is important to carefully consider these issues and ensure that the model is used in an ethical and responsible manner.
Emotion Recognition in E-learning Systems
Emotion recognition can be integrated into e-learning systems to enhance the student's learning experience and improve learning outcomes. Emotion recognition technology can help identify when a student is struggling or not engaged and provide personalized feedback and support to improve their learning experience.
Here are some ways emotion recognition can be used in e-learning systems:
Real-time feedback: Emotion recognition technology can provide real-time feedback to students and teachers on their emotional states and engagement levels. This feedback can be used to adjust the learning experience, such as providing additional resources or adjusting the difficulty level of the content.
Personalized learning: Emotion recognition technology can personalize the learning experience for each student based on their emotional state and engagement levels. For example, if a student is feeling frustrated or overwhelmed, the system can provide additional resources or break down the content into smaller, more manageable pieces.
Assessment: Emotion recognition technology can be used in assessments to help identify when students are struggling or need additional support. For example, if a student is feeling anxious or stressed during a test, the system can provide additional support or resources to help them manage their emotions and perform better.
Student engagement: Emotion recognition technology can help identify when a student is not engaged or distracted during the learning experience. This information can be used to adjust the learning experience and provide additional support to re-engage the student.
INTERNATIONAL SCIENTIFIC AND TECHNICAL CONFERENCE "DIGITAL TECHNOLOGIES: PROBLEMS AND SOLUTIONS OF PRACTICAL IMPLEMENTATION IN THE SPHERES" APRIL 27-28, 2023
Conclusion
Emotion recognition systems offer valuable insights into students' emotional states and can help educators personalize their teaching approaches, provide appropriate support, and improve learning outcomes. By integrating emotion recognition technology into educational settings, teachers can better understand how students are feeling and adjust their teaching strategies to better meet their needs. However, it is important to ensure that emotion recognition systems are used in an ethical and responsible manner, with appropriate safeguards in place to protect student privacy and prevent potential biases and inaccuracies in the technology.
REFERENCES
1. Yusupova, N.; Bogdanova, D.; Komendantova, N.; Hassani, H. Extracting Information on Affective Computing Research from Data Analysis of Known Digital Platforms: Research into Emotional Artificial Intelligence. Digital 2021, 1, 162-172. https://doi .org/10.3390/digital 1030012
2. Kratzwald, B.; Ili'c, S.; Kraus, M.; Feuerriegel, S.; Prendinger, H. Deep learning for affective computing: Text-based emotion recognition in decision support. Decis. Support Syst. 2018, 115, 24-35. [CrossRef]
3. Dai, W.; Han, D.; Dai, Y.; Xu, D. Emotion recognition and affective computing on vocal social media. Inf. Manag. 2015, 52, 777-788. [CrossRef]
4. Bozhkov, L.; Georgieva, P.; Santos, I.; Pereira, A.; Silva, C. EEG-based Subject Independent Affective Computing Models. Procedia Comput. Sci. 2015, 53, 375-382. [CrossRef]
5. Elaheh Yadegaridehkordi, Nurul Fazmidar Binti Mohd Noor, Mohamad Nizam Bin Ayub, Hannyzzura Binti Affal, Nornazlita Binti Hussin Affective computing in education: A systematic review and future research Department of Information Systems, Faculty of Computer Science & Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia. https://doi.org/10.10167j.compedu.2019.103649
