International Journal of Emerging Technologies in Learning (iJET), Год журнала: 2023, Номер 18(14), С. 200 - 214
Опубликована: Июль 31, 2023
A diversified academic assessment mechanism can effectively improve students’ learning motivation, make up for the possible blind spots of a single method, and better guide teachers’ teaching. Using data mining methods to process evaluation mechanisms in colleges universities discover patterns learning, find key factors affecting performance, provide basis teaching reform. Most current focus on hard skills, such as performance classroom participation, but it is difficult evaluate soft skills critical thinking teamwork. To this end, paper studies universities. It constructs an indicator system universities, gives quantitative method indicators, performs fuzzy comprehensive based AHP-entropy weight method. For text-based consistency training introduced train correlation model using large amount unlabeled examples, which solves problems lack labeled data, high labeling cost, changes distribution, improves availability model. The experimental results verify effectiveness proposed
Язык: Английский