Mutual evaluation method for homework of students during online course

Abstract

The invention relates to a mutual evaluation method for the homework of students during the online course and belongs to the field of computer application. The method comprises the steps of extracting the features of the learning records of students, calculating the similarity between a homework grading student and a to-be-graded student, assigning the homework through the bipartite graph matching process, solving out an optimal solution for the bipartite graph matching process, and figuring out an optimal homework assignment scheme for the mutual evaluation of the homework. According to the technical scheme of the invention, the homework assignment problem is converted into the graph theory problem. Meanwhile, the problem is solved out based on the related algorithms of the graph theory. The obtained outcome of the solution fully considers the similarity between the homework grading student and the to-be-graded student from a global perspective. Therefore, students most similar in learning habit and learning level are matched to the greatest extent. At the same time, two parties that participate the mutual evaluation process are similar in learning level and learning habit as much as possible.

Description

technical field [0001] The invention belongs to the field of computer applications, in particular to a method for grading students' homework in online learning. technical background [0002] In recent years, Massive Open Online Courses (MOOC) have developed rapidly around the world, providing high-quality and convenient learning resources for learners around the world. At the same time, the MOOC platform has also brought some challenges. [0003] In the teaching process, it is a very important link to consolidate the learning content by completing homework. In the traditional homework form, it can be divided into two types: objective questions and subjective questions. Among them, objective questions only need to set standard answers Correcting and grading can be done efficiently by computer, but for subjective homework, there are generally three grading methods: manual grading, machine grading, and peer evaluation. The three methods have their own advantages and disadvanta...

AI Technical Summary

Problems solved by technology

The three methods have their own advantages and disadvantages, and the accuracy of manual grading is the highest. However, since the number of course participants on the MOOC platform is usually large, and the number of students enrolled in a course is usually thousands or even tens of thousands, the workload of manual grading is very heavy for teachers. It is too large to be feasible; machine scoring usually uses machine learning methods, and when there is a suitable training set (usually part of the homework judged by the teacher as the training set), it can automatically perform text-type questions. Grading, the disadvantage is that it is difficult to guarantee the accuracy of the current technical level, and the applicable question types are relatively single (only text questions); on the premise of setting reasonable rules, allowing students to conduct mutual evaluation can reduce the workload of teachers. Under the premise, the grading can also get higher accuracy. The existing major MOOC platforms edx and coursera also use mutual evaluation to complete the grading of subjective questions.

These phenomena will affect the reliability of the mutual evaluation results

Images