Personalized Learning in Science Recommendation System based on Learners' Preferences

Along with the massive internet digital dataset, it gives the reform motivation and amiabilities to change traditional college teaching and learning in science. How to find the appropriate information that the students are interested, valuable, and easy to be understood in the vast amount of information, and bring their creative ability, needs a personalized full path. A Recommender System (RS) based on learners' preferences is a powerful tool, which can guarantee the quality and efficiency of the teaching and learning in science and provide one of science research directions with great research value. This paper presents the overall framework design of a wisdom RS in science, which analysis models are based on the students' preferences, especially, Science Knowledge (SK), using a big data software platform. The research sample is made of totally 708 first year undergraduate students who take the subject of an introductory in Science Concepts (SC) in Computer Studies of Program (CSP), Macao Polytechnic Institution, from 2007 to 2022 academic year. According to the students' SK, their Conceptual Learning (CL) methods have been classified into six types of thinking modes, which have three different corresponding understanding levels for each mode. The appropriate recommended materials to the students who are interested in the information provided, such as text-based teaching materials on science discussion forums, simulation tools and game activities, can increase the motivations of the students to learn, considered their different characteristics and understanding. The performances of this RS have been tracked over a period of 15 years, which can effectively improve the personalized teaching quality in the area of computer science, since it may be useful in heightening students' motivation and interest in CL in science.