Decision Making for E-learners based on Learning Style, Personality, and Knowledge Level

With the increase of internet usage, most of the learners go for e-learning systems for all kinds of learning activities. E-learning has been able to provide support to all learners through a wide range of materials for every topic. But the availability of large materials and resources has caused difficulty in selecting the optimized material. The learners find it difficult to select the right resource based on their criteria for learning. Going through many resources on same topics lead to learners losing his interest or dropping the idea of learning online. Thus, a recommender system that will provide the users right and optimized path of learning is essential. The idea is to recommend a learner the material that will suit his/her style and will help him/her learn quickly in an optimized manner. This paper estimates the learning style, personality and the knowledge level of a learner in order to recommend the next topics he/she should learn. The results from all of these three questionnaires are put into an algorithm named as aggregation using intuitionistic fuzzy genetic algorithm. This gave us the aggregated values for each student and the next task of classifying a student is done using the KNN classifier. The classes to which a student could belong are termed as low, low-medium, medium, medium-high and high. These classes will group together students having nearly same aggregate values and with similar learning, personality and knowledge levels. This will in turn help us to provide the learners with the material that would suit them and help them to progress at a much better pace.