Learning analytics based intelligent simulator for personalised learning slide
0 likes195 views
The document discusses the development of an intelligent simulator for personalized learning (ISPeRL) that leverages learning analytics to enhance learner engagement and outcomes. It emphasizes the importance of optimizing instructional approaches, understanding learner profiles, and adapting materials based on individual needs. The simulator includes features like predictive analytics, personalized lesson planning, and the functionality of two chatbots for academic support and customer service.
Learning analytics based intelligent simulator for personalised learning slide
- 1. Learning-Analytics based Intelligent Simulator for Personalised Learning Assoc. Prof. Dr. Nurfadhlina Mohd Sharef Universiti Putra Malaysia nurfadhlina@upm.edu.my
- 3. Personalised learning through meaningful experiential learning analytic 1. Instructor must determine suitable pedagogies that could optimize meaningful learning experience. 2. The choice and preparation of learning materials should be optimized as well. 3. Instructor has good competencies and familiarity with the course. 4. The instructor should also be informed on the learners’ profile and able to identify the students’ learning needs. 1. Instruction in which the pace of learning and the instructional approach are optimized for the needs of each learner where the learning objectives, instructional approaches, and instructional content (and its sequencing) may all vary based on learner needs. 2. Learning activities are made available that are meaningful and relevant to learners, driven by their interests and often self-initiated. Characteristics Actions
- 4. Objectives
- 5. Why is it important to conduct Learning Analytics?
- 6. Intelligent Simulator for Personalised Learning (ISPerL) Benefits and purpose of ISPerL for meaningful learning analytic can be further described as follows: a. Plan a personalized lesson i. Plan upcoming lesson and get prediction on the satisfaction score ii. View current course summary and past lesson information b. Conduct adaptive teaching i. View students heart rate ii. View participation and engagement score c. Learning scaffolding i. Analyse students’ achievement by assessment types ii. Analyse students’ achievement by program outcomes iii. Analyse students’ participation and engagement iv. Analyse students’ satisfaction There are two chatbots developed in ISPerL. The purpose of the first chatbot is to provide alternative to learning materials and interaction modality with the instructor. The chatbot is designed in Bahasa Melayu, which is the national language in Malaysia. The target user of the chatbot ranges from secondary school learners to lifelong learners. The second chatbot aims to provide customer service related to academic program’s admission enquiries.
- 7. Which algorithms and features best predict the end of term academic performance of students by comparing different classificationalgorithms and pre-processing techniques and whether or not academicperformance can be predicted in the earlier weeks using these features and theselected algorithm 7
- 8. 8
- 10. Features Students Really Expect from Learning Analytics ● time spent online ● collaborative learning with friends and colleagues ● learning recommendation for successful course completion ● prefer self/independent learning rather than conventional classroom setting ● timeline showing current status and goal ● time needed to complete a task or read a text ● prompts for self-assessments ● further learning recommendations ● comparison with fellow students ● considering the students personal calendar for appropriate learning recommendations ● newsfeed with relevant news matching the learning content ● revision of former learning content ● feedback for assignments ● reminder for deadlines ● term scheduler, recommending relevant courses
- 11. Descriptive Learning Analytic Diagnostic Learning Analytic Personalised Learning Facilitation through Meaningful Learning Experience Analysis Predictive Learning Analytic Prescriptive Learning Analytic ● Lesson records visualization and alert on low attendance ● Assessments record visualization and alert on low assessment achievements ● PO achievements records visualization and alert on low PO achievements ● Statistics on learning materials, learning activities, satisfaction records and reaction in each lesson ● Correlate assessment achievement with demographic profile, attendance, participation, engagement and satisfaction ● Correlate PO achievement with demographic profile, attendance, participation, engagement and satisfaction ● Predict grade based on attendance, participation, engagement and satisfaction ● Predict satisfaction based on materials, activities and student demography ● Prescribe remedial actions based on gap in students attendance participation, engagement, satisfaction and achievements ● Prescribe remedial actions based on predicted grade performance
- 12. Lesson Satisfaction Learning AnalyticReaction to Lesson Learning Materials Assessment Records Descriptive Diagnostic Predictive Prescriptive Chatbot Student Lecturer and Administrator Intelligent Simulator for Personalised Learning (ISPerL) model) Version 1
- 13. ProfilingLearning preferences Learning competency Learning behavior - System participation log - Heart rate Learning satisfaction Learning Personalization Analytics Descriptive (preferences, satisfaction, competency, achievement) Diagnostic-learning plan adaptability (preferences-behavior, satisfaction-achievement) Predictive-learning plan recommendation (performance, satisfaction) Prescriptive-Adaptive learning plan (performance, satisfaction) Assessment records Learning Materials Learning dashboard Learning engagement Learning achievement Satisfaction prediction Performance prediction Learning competency Customization Model of Intelligent Simulator for Personalised Learning (ISPerL) Version 2
- 14. For Learners For Instructors - Pre-lesson execution - Planning of lesson - Prediction of satisfaction score - Prediction of grade - During lesson execution - Average heart rate of class - View heart rate of each student - Participation and engagement by each students - Participation and engagement alert of class - Post-lesson execution - Analysis of participation, engagement, heart rate, satisfaction rating and achievement ISPerL Features For Instructors and Administrators - Descriptive analytic of course, lesson and student info - Diagnostic analytic on course performance by gender, PO and assessment type - Comparative analytic on course performance across gender, PO and assessment type, groups and semesters - Predictive analytic on students and course performance (assessment , PO for current and cross group , semester) - View course info - View lesson plan - View graph of heart beat vs ideal heart beat - Assign rating for content, delivery, engagement - View self-standing vs average participation in the course - View self-standing vs average achievement in the course - Execute chatbot
- 15. Features: 1. View - Course Info - Course Assessment - Course PO - Comparison between semesters - Analysis of heart rate 1. Plan a new lesson & view lessons for current semester 2. Get prediction of content, delivery and engagement satisfaction Intelligent Simulator for Personalised Learning (ISPerL)
- 16. Descriptive Learning Analytic of Learning Outcome distribution - Comparing grade distribution across groups within the same semester - Comparing marks distribution by PO across groups within the same semester - Comparing marks distribution by PO across gender and groups within the same semester - Comparing marks distribution by PO across gender, groups and semester - Comparing marks distribution by PO across gender, groups and semester of each grade Showcase: https://public.tableau.com/profile/nurfadhlina.mohd.sharef#!/vizhome/LearningAnalytic-Course1/Story- LearningAnalytic?publish=yes
- 19. Descriptive and predictive analytics Pilot 1
- 20. POWERPOINT TEMPLATEWhirlWind | Email : example@example.com | Web : www.example.com This is a sample text, Insert your desired text here this is a sample text. Pilot 2
- 21. Pilot 3
- 22. Guru AI Bot- teaches the basics of artificial intelligence, in Malay language. Modifying current chatbot based on input from pilot study - 50% Development of questionnaires - 100% User study setup - 50% FSKTMBot - customer service chatbot that entertains admission inquiries. Development of chatbot - 100% Development of questionnaires - 100% User study setup - 40% 1. What? A virtual assistant for the Artificial Intelligence (AI) subject 2. Scope? Basic information on AI 3. Who? Anyone who likes to learn about the basic of AI 4. Language? Malay 1. What? A virtual assistant for ADMISSION inquiries into Faculty of Computer Science and Information Technology, UPM. 2. Scope? Information (Programme, Requirement, Fees, Contact Us) 3. Who? Future and current students that seeking for basic information of the FCSIT 4. Language? English
- 24. A customer service chatbot that entertains admission inquiries. FSKTMBot 1. What? A virtual assistant for ADMISSION inquiries into Faculty of Computer Science and Information Technology, UPM. 2. Scope? Information (Programme, Requirement, Fees, Contact Us) 3. Who? Future and current students that seeking for basic information of the FCSIT 4. How? Rule-based Natural Language Processing using DialogFlow framework 5. Language? English
- 25. Thank you from us.. To cite: Sharef, N. M., et. al (2020), “Learning-Analytics based Intelligent Simulator for Personalised Learning”, International Conference of Advancements in Data Science, e-Learning and Information Systems (ICADEIS’20) Please visit our website https://qrgo.page.link/7EEdp