Computer-Assisted Collaborative Learning for Enhancing Students Intellectual Ability Using Machine Learning Techniques

Computer-assisted Collaborative Learning (CCL) is a good teaching technique to enhance students' learning and intellectual performance consistency. Several studies have been undertaken to recognize variables that affect student intellectual ability. Observation obtained from the studies helped students in the right way and improved their habits and personal condition in learning and intellectual performance. In this paper, the proposed method has a multi-level multi-class classification algorithm. The dataset is transformed into various problem syntheses, and adaptive methods such as Binary Significance (BS), Label Powerset (LP), Classifier Series (CS), K-Nearest Neighbor (KNN), and Machine Learning integrated K-Nearest Neighbor (MLiKNN) adaptive classifier algorithm. Finally, the variables that significantly impact the student's success are identified, and recommendations for enhancing those factors are suggested to enhance the student's intellectual ability. The outcomes observed from the proposed classifier framework provide more recommended strategies to enhance students' learning environment and intellectual ability.