Analysing learning behaviour: A data-driven approach to improve time management and active listening skills in students

Abstract

Learning behavior refers to the actions, attitudes, and strategies individuals employ when acquiring new knowledge. Time management is a perennial challenge in modern life, where individuals often juggle multiple responsibilities and commitments. Active listening is an indispensable skill in both educational and interpersonal contexts. Methodologically, the study began with comprehensive data collection through a survey, data preprocessing tasks and feature selection, followed by training and evaluating predictive models using various ML algorithms. With concerns rising over student failures, we conducted a survey with 350 participants, utilizing Google Forms. After testing multiple ML models with datasets, Random Forest was determined to be the most dependable model by emphasizing algorithms. It demonstrated remarkable durability (0.811012) and accuracy during cross-validation. The significance of addressing the effective abilities that students should absorb and the possibility of ML approaches in comprehending and reducing its negative impacts on academic success are both highlighted by these findings. By analyzing learning behavior, researchers and educators can gain insights into effective learning strategies, identify barriers to learning, and develop interventions to support learners in achieving their educational goals. The findings emphasize the pivotal role of non-cognitive skills like time management and active listening in fostering academic achievement.

• •
  Significance of Non-Cognitive Skills: The study underscores the critical role of non-cognitive skills, such as time management and active listening, in fostering academic success and overall learning effectiveness.
• •
  Survey and Dataset Analysis: The survey, conducted with 350 participants using Google Forms, provided valuable data for training models and highlighted challenges like student failures, which can be addressed through predictive analysis.
• •
  Impact on Academic Success: By analyzing learning behaviors and identifying barriers, the findings emphasize the potential of machine learning approaches in understanding and mitigating factors that negatively affect academic performance.