Download as PPTX, PDF, TXT or read online from Scribd
Download as pptx, pdf, or txt
You are on page 1/ 15
Mahatma Education Society's
Pillai HOC College of Engineering & Technology
Department of Computer Engineering Project Progress Review-I
STUDENT LEARNING STYLE PREDICTION USING MACHINE
LEARNING
Date: 20/09/2024
Group members : Under the guidance : Prof. Snehal Shinde Dnyaneshwari Pawar Shruti Jagtap Akanksha Gophane Presentation Outline
Introduction Expected Outcome
Motivation Gantt Chart
Literature Survey References
Research Gap
Problem Statement
Proposed architecture
Methodology
Tools and Dataset
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 2
Introduction
• Educational System : The educational system is a structured framework for teaching and learning that encompasses early childhood, primary, secondary, higher, and vocational education, focusing on skill development and knowledge acquisition
• Machine Learning : Machine learning is a subset of artificial intelligence that enables computers to learn from data and improve their performance on tasks without being explicitly programmed
• VARK Model : The VARK model is a learning style framework that categorizes individuals as Visual, Auditory ,Reading/Writing or Kinesthetic learner, highlighting how they prefer to prefer to absorb and process information
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no.3
Motivation
• Encourage learners to set specific, achievable goals
• Provide feedback and rewards to boost confidence
• Create opportunities for peer interactions and group learning
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 4
Literature Survey
Sr. No Paper Title / Year Methodology Limitations
1. Machine Learning Technique to Predict Learning Style in • In this paper the • Ethical & privacy concern E-Learning , Oluwaseyi Emmanual etal , 2024 • Data quality & availability
2. Automated learning style Prediction using machine • Fuzzy weighting • Overreliance on self Reported learning , Ahemad Zhicahao Zhang etal, • Deep learning Data doi.org/10.33.90/info1505027 , 2023 • Individual Differences
3. Predict student learning styles and suitable assessment • Learning prediction • Data complexity methods using click stream , Hesham A. Hefny Mohamed • Assessment mapping • Lack of Empirical Evidence etal , 2024 , 10.1016/j.eij.2024.100469
4. Learning style recommender system using VAK technique • Evaluation metrics • To increase accuracy using & machine learning , Adapa Mr Netaji Gandi etal, DOI: • Model performance deep learning 10.1007/978-981-15-5397-4_20 , 2022 • To increase dimensionality of data
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 5
Literature Survey
Sr. No Paper Title / Year Methodology Limitation
5. Analysing the learning style of an individual • Integration with learning
&suggesting field of study using Machine Learning • Study recommendations management system technique , Jijith Murali Lekshmi S Nair etal , 978-1- • Learning-based suggestions • Real time feedback 7281-1261-9, May 2022 • Algorithmic methods
6. Learning style detection in E-learning systems using • Feature extraction • Dyanamic Adaptation machine learning techniques , Fareeha Rasheed etal, vol • Learning metrics 174 , 2021
7. Personalized Adaptive Learning Technologies Based on • Adaptive technology • Static view of learning Machine Learning Techniques to Identify Learning • Platform integration • Limited generalization Styles , Essa Turgay Celik etal , 2021 , 10.1109/ACCESS.2023.3276439
8. Personalization of E-Learning Environment Using the • Kolb classification • Overreliance on memorization
Kolb's Learning Style Model , Gholam Ali Montazer • Learning styles • One size fits all approach etal , 2020, 10.1109/ICWR49608.2020.9122314
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING
Slide no. 6 Research gap
• Quality and Quantity of Data: Existing dataset are small and lack diversity ,falling to represent the broader student population
• Context-Aware Predictions: Models often overlook important contextual factors like emotions and social interactions, which can impact learning styles.
• Model Accuracy: Current models achieve moderate accuracy requiring improvements, model fail to generalize well to new unseen data
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 7
Problem statement
Personalized learning experience was not provided to the user. There is a lack of empirical evidence on whether adapting teaching strategies to align with the VARK learning styles significantly enhances student comprehension, retention, and engagement compared to traditional, non-tailored approaches.
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 8
Block Diagram
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 9
Methodology
• Upload Questionnaire for Module: An admin uploads a questionnaire related to a specific module or subject.
• Conduct Test: Students take the test based on the uploaded questionnaire.
• Evaluate Test: The system evaluates the student's performance on the test.
• Categorize as Slow/Fast Learner Using Random Forest: A machine learning algorithm, Random Forest, is used to classify students as either slow or fast learners based on their test performance and other relevant data (e.g., learning style).
• Recommend New Learning Technique for Slow/Fast Learner: Based on the categorization, the system recommends appropriate learning techniques tailored to the student's learning style and pace.
• Reconduct Test for Slow Learner (Optional): If a student is identified as a slow learner, the system may recommend retaking the test after implementing the recommended learning techniques to assess their progress.
• Evaluate Result: The final outcome of the process is an evaluation of the student's learning, including their initial performance, categorization, recommended techniques, and potential improvements.
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 10
Tools and dataset
Frontend Technology
• HTML • CSS • JavaScript
Backend Technology
• Python libraries • ML algorithm
Dataset :
• Survey data from participants - students,learners
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 11
Expected outcomes
User Interface of VARK model
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 12
Expected outcomes
Questionnaires to predict learning style
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 13
Gantt chart
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 14
References
[1] Godwin Oluwafemi Olaoye Joseph Oluwaseyi Emmanual , “Machine Learning Techniques to Predict Learning Style in E- Learning”, April 2024
[2] Wanying Suo Bello Ahemad Zhicahao Zhang “Automated learning style Prediction using machine learning” , doi.org/10.33.90/info15050277, January 2023
[3] Hesham A. Hefny Mohamed Khafagy’s Yasein Gouda, “Predict student learning styles and suitable assessment methods using click stream” , Egytian Informatics Journal , March 2024, 10.1016/j.eij.2024.100469
[4] Ananthu S Kuttattu Gokul G S Hari Prasad Jijith Murali Lekshmi S Nair , IEEE Xplore “Analysing the learning style of an individual and suggesting field of study using Machine Learning techniques” , 978-1-7281-1261-9, May 2022
[5] Srinivas Adapa Mr Netaji Gandi “Learning Style Recommender System Using VAK Technique and Machine Learning” 2022 DOI:10.1007/978-981-15-5397-4_20
[6] Saadia Gutta Essa Turgay Celik , “Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning” , IEEE Xplore , Vol 11 , May 2021 , 10.1109/ACCESS.2023.3276439
[7] Abdul Wahid Fareeha Rasheed “Learning style detection in E-learning systems using machine learning techniques” doi.org/10.1016/j.eswa.2121.114774 vol 174 2021
[8]Tahereh Sanjabi Gholam Ali Montazer “Personalization of E-Learning Environment Using the Kolb's Learning Style Model” 2020 10.1109/ICWR49608.2020.9122314
STUDENT LEARNING STYLE PREDICTION USING MACHINE LEARNING Slide no. 15
