Smart AI Driven Adaptive Study Platform

“Mood Mentor”
Submitted By
Harshal Manohar More (33)
Sagar Ramdas Doddi (13)
Om Dinesh Patil (36)
Tejaswini Sunil Patil (37)

Under The Guidance Of

Prof. Ms. Aishwarya Sanap

Department of Information Technology

Matoshri Education Society’s
Matoshri Aasarabai Polytechnic, Eklahare,
Nashik
December 2024
Index
1. Introduction
2. Problem of statement / Why our Product...
3. Objectives and scope
4. Plan
5. Literature Survey
6. Proposed Project Concept
7. Functionalities. Requirements
8. Design / Methodology (Flowchart && Block diagram
&& ER Diagram
9. Advantages, disadvantages
10. Applications && Future Scope
11. Conclusion
12. References
Introduction
 Emotions play a critical role in the learning process, influencing
motivation, engagement, and overall academic performance. As
educational paradigms shift towards more personalized and adaptive
learning experiences, the integration of Artificial Intelligence (AI) in
learning environments has gained significant attention. One of the
emerging applications of AI is the ability to assess and respond to learners'
emotions, providing real-time feedback and support to enhance the
educational experience.
 AI-driven emotion recognition systems use various data inputs, including
facial expressions, speech patterns, physiological signals, and behavioral
data, to analyse and infer emotional states. These systems can adapt
learning materials, styles, and feedback mechanisms to meet the emotional
needs of learners, fostering a more engaging and supportive environment.
Problem of statement / Why our
Product...
 The problem of integrating artificial intelligence (AI) to assess emotions in
learning environments lies in the complexity of accurately detecting,
interpreting, and responding to the emotional states of students in real-time.
While emotions play a critical role in cognitive processes, motivation, and
overall learning outcomes, existing AI-driven systems often face challenges
such as limited contextual understanding, high variability in emotional
expressions across individuals, and potential biases in emotion recognition
models. Furthermore, there is a lack of standardized frameworks and
methodologies to guide the integration of AI into educational settings for
emotional assessment. A systematic literature review is needed to explore
current advancements, identify gaps, and propose strategies for effectively
leveraging AI to enhance adaptive learning environments by incorporating
emotional intelligence.
Objective/Scope
 To review the ethical implications of using AI to assess emotions, focusing
on privacy concerns, data protection, consent, and the potential for misuse
of emotional data.

 To identify the technical, ethical, and practical challenges associated with

integrating AI for emotion assessment, such as accuracy issues, context-
dependency, cultural variations, and user acceptance.
 To evaluate how AI-driven emotion assessment enables personalized
learning paths by adapting content, pace, and feedback based on the
learner's emotional state.
Plan
 Literature survey
Sr.No Paper Name Author Name Year Algorithm Database Observation

1 Integrating artificial Angel Olider Rojas 2024 federated facial This systematic literature
intelligence to assess Vistorte 1 2, Angel learning, (2) expression review showcases the
emotions in learning Deroncele-Acosta 3, convolutional databases significance of AI in
environments: a Juan Luis Martín Ay neural revolutionizing educational
systematic literature ala network practices through emotion
review (CNN), (3) assessment.
recurrent
neural
network
(RNN),
2 Student and educator Karen MacKinnon 1, 2015 Academic thematic For this review we will use
experiences of Lenora Marcellus, Databases synthesis, the definition of "simulation-
maternal-child Julie Rivers, meta- based learning experience"
simulation-based ethnography, or adopted by the International
learning: a systematic narrative Nursing Association for
review of qualitative synthesis Clinical Simulation and
evidence protocol Learning (INACSL

4 Influence of Stress an Alfredo Córdova 1, 2023 thematic Emotional instability and

d Emotions in the Lea Alberto Caballero-G synthesis, stress are the main
rning Process: The Ex arcía meta- disturbances that condition
ample of COVID-19 o 2, Franchek Drobnic
n University Students: 3 ethnography, or the learning process, affecting
A Narrative Review. , Enrique Roche ,
456
narrative S
David C Noriega synthesis

5 An AI Powered Faraz Hasan, July 2024 Naive Bayes, MYSQL Imagine a digital world where
Emotion Recognition Lakshay Arora Support your computer understands
System Anshul Tickoo Vector how you feel. This project is
 Machines all about making that a reality
(SVM), by bringing together the
Recurrent magic of technology and
Neural human emotions.
Networks
 Proposed Project Concept
 Mood Mentor is an AI-powered adaptive study platform designed to optimize
learning outcomes by catering to students’ emotional and cognitive states.
Through intelligent analysis of a user's mood, focus level, and study behavior,
the platform personalizes study plans, provides motivational support, and
enhances overall learning efficiency. The project aims to create a more
supportive, engaging, and effective educational experience by blending
emotional intelligence with adaptive learning techniques.
Functionalities,
Requirement
SOFTWARE REQUIREMENTS:
Sr. Software Description Operation
No
1 Operatin Windows 11 To run development app.
g and above
System
2 Language To develop the application.
Python

HARDWARE REQUIREMENTS:
Sr.no. Hardware Specification

1 Processor Intel Core-i5 or above

2 RAM 4 GB & Above

3 HDD 256 GB
Design/Methodology

Fig: Block diagram

Fig: DFD0
diagram
Fig: DFD 1 diagram
Fig: Class diagram
Fig: Deployment diagram
Fig: Package diagram
Fig: Activity diagram
Fig: Sequence diagram
 advantages
 Optimized Learning: Tailored study sessions based on mood and focus.
 Higher Motivation: Real-time encouragement and mental well-being
support.
 Reduced Fatigue: Session adjustments prevent burnout.
 Better Performance: Personalized plans improve retention and
understanding.
 Insightful Feedback: Mood and focus data help students refine study
habits.
 Disadvantages
 Privacy Risks: Sensitive data monitoring may pose privacy concerns.
 Dependency: Over-reliance on AI could hinder self-regulation skills.
 Algorithm Bias: Inaccurate mood interpretation risks misleading
recommendations.
 High Setup Costs: Advanced technology implementation can be costly.
 Distraction Potential: Frequent adjustments may overwhelm students.
 Applications
 Personalized Learning Paths
 Emotion Recognition and Feedback
 Intelligent Tutoring Systems
 Support for Affective Learning
 Enhanced Engagement and Motivation
 Research and Development in Education
 Future Scope
 “Mood Mentor” encompasses several exciting advancements aimed at enhancing
personalized learning experiences through emotion-driven methodologies. As
artificial intelligence and machine learning technologies evolve, the platform can
integrate more sophisticated multimodal emotion detection techniques, combining
facial recognition, voice analysis, and biometric data to improve accuracy in
understanding learners’ emotional states. Future developments may also include the
incorporation of gamified elements and social-emotional learning (SEL) strategies
to further engage students and enhance their emotional well-being. Additionally,
the platform could leverage explainable AI (XAI) principles to ensure transparency
in AI decision-making processes, fostering trust among users. By expanding its
capabilities to support collaborative learning environments and integrating adaptive
content creation tools, the platform can become a comprehensive educational
ecosystem that not only adapts to individual learner needs but also promotes a
holistic approach to emotional intelligence and academic success.
Conclusion
 So hereby taking all the references and apply the necessary methodologies ,
We have started to design an SMART AI-Driven Adaptive Study Platform
named as ‘Mood Mentor ‘ . The mood mentor application enhances the user
experience towards online learning . This Application will adapt According
to the users need and give them proper guidance . It will make proper
schedule of the particular students according to their ease . We will also
make some significant changes if needed further for the betterment of this
Application .
 References
1. Zhao, G., & Zhang, J. (2013). "Facial Expression Recognition Based on Fusing
Multiple Feature Representations." International Journal of Advanced Computer
Science and Applications, 4(3), 73-78.

2. M. R. M. Ali, Z. A. D. (2020). "Adaptive Learning System: A Systematic

Review." IEEE Access, 8, 34489-34501.

3. Luckin, R., Holmes, W., Griffiths, M. D., & Forcier, L. B. (2016). "Intelligence
Unleashed: An Argument for AI in Education." Pearson Education.

4. Kappas, A., & Brennan, J. (2014). "Emotion in Communication: The Role of

Emotion in Language and Communication." Emotion Review, 6(2), 100-107.

5. Hamari, J., Koivisto, J., & Sarsa, H. (2014). "Does Gamification Work?--A
Literature Review of Empirical Studies on Gamification." 2014 47th Hawaii
International Conference on System Sciences (pp. 3025-3034). IEEE
THANK YOU…!