# Dynamic Diagnosis of the Progress and Shortcomings of Student Learning using Machine Learning based on Cognitive, Social, and Emotional Features

**Authors:** Alex Doboli, Simona Doboli, Ryan Duke, Sangjin Hong, Wendy Tang  
**arXiv:** [2204.13989](https://arxiv.org/abs/2204.13989)  
**Date:** 2022-04-13  
**Summary page:** https://www.summarizepaper.com/en/paper/2204.13989v1/

## Key points

- The educational landscape is becoming increasingly diverse with students from different backgrounds, learning styles, career and life goals, ethnicity, age, social and emotional characteristics, course load and work schedule.
- This diversity offers unique opportunities for learning new skills but also poses challenges as it adds variability in the way in which students learn and progress over time.
- Traditional teaching methods may be ineffective as a single teaching approach cannot cater to the needs of all students.
- An automated support system based on data analytics and Machine Learning has been proposed to address these limitations of traditional teaching methods.
- The methodology groups learning difficulties into four categories: recall from memory, concept adjustment, concept modification, and problem decomposition into sub-goals (sub-problems) and concept combination.
- Data models are predicting the occurrence of each of the four challenge types as well as a student's learning trajectory.
- These models can be used to automatically create real-time student-specific interventions such as learning cues to address less understood concepts.
- The system enables new adaptive pedagogical approaches to unleash student learning potential through customization of the course material to the background, abilities, situation, and progress of each student; leveraging diversity-related learning experiences.
- The proposed methodology for automated diagnostic assessment and intervention creation is grounded in Bloom’s Taxonomy with connections to Jean Piaget’s theory of learning.

## Summary

The educational landscape is becoming increasingly diverse, with students from different backgrounds, learning styles, career and life goals, ethnicity, age, social and emotional characteristics, course load and work schedule. While this diversity offers unique opportunities for learning new skills, peer mentoring and example setting, it also poses challenges as it adds variability in the way in which students learn and progress over time. A single teaching approach is likely to be ineffective and result in students not meeting their potential. To address these limitations of traditional teaching methods, an automated support system based on data analytics and Machine Learning has been proposed. This system aims to continuously assess student learning and implement needed interventions by measuring and causally diagnosing the progress and shortcomings of student learning. The methodology groups learning difficulties into four categories: recall from memory, concept adjustment, concept modification, and problem decomposition into sub-goals (sub-problems) and concept combination. Data models are predicting the occurrence of each of the four challenge types as well as a student's learning trajectory. These models can be used to automatically create real-time student-specific interventions such as learning cues to address less understood concepts. The system enables new adaptive pedagogical approaches to unleash student learning potential through customization of the course material to the background, abilities, situation, and progress of each student; leveraging diversity-related learning experiences. The proposed methodology for automated diagnostic assessment and intervention creation is grounded in Bloom’s Taxonomy with connections to Jean Piaget’s theory of learning. It considers that human learning follows a sequence of successive cognitive stages: sensorimotor stage (when new concepts are learned through their physical features), symbolic stage (when symbols replace the physical facets), intuitive thought stage (when incipient reasoning starts utilizing new concepts), concrete operational stage (when logical reasoning uses learned concepts), formal operational stage (when abstract reasoning employs new knowledge).