An improved classification algorithm on teaching evaluation
Juanli Hu, Jiabin Deng, Chang Hu · 2009
Teaching evaluation is a difficult task because of the difficulty of transforming teaching behavior into a quantitative problem. In this paper, an improved classification algorithm is proposed into the field of teaching evaluation by contrast with the traditional methods. Firstly, the key concepts of algorithms using in teaching evaluation are introduced, including the actual process of mining knowledge. Secondly, an improved decision tree algorithm is presented to analyze the data by fuzzy clustering. Thirdly, after the analysis by this new way, the potential rules are found and can be as the objective basis for teaching evaluation. The improved method can overcome the shortage of traditional methods on data integration and aggregation. The results show that this method for decision-making on teaching evaluation is feasible and effective.