Knowledge map oriented network learning behavior and efficiency analysis method

Abstract

The invention discloses a knowledge map oriented network learning behavior and efficiency analysis method. According to the method, the difference between the traditional courseware oriented network learning and knowledge map oriented network learning is comparatively analyzed from the aspects of teaching resource organization, teaching activity design, user learning behavior characteristics and the like, and indexes, namely a knowledge element coverage rate F and effective click time length T calculation method, for embodying learning behaviors of learners in a knowledge map mode are given; analysis is carried out by combining the time length characteristic that users submit homework online on a network learning platform, a k-means clustering algorithm is adopted, and the learners are divided into three types, namely an active type, a general type and a dilatory type. The method has the advantages that network learning behavior characteristic extraction in a knowledge map oriented learning mode and the quantitative analysis of a relationship between a network learning behavior mode and learning efficiency are achieved, and basis and foundation for the personalized recommendation of network learning resources can be provided.

Description

Technical field [0001] The invention relates to a network learning behavior and effectiveness analysis method, in particular to a knowledge map-oriented network user behavior analysis method. Background technique [0002] In E-learning, the separation of time and space between teaching and learning makes it more difficult for teachers to monitor the learning process. Understanding the intrinsic style and preferences of online learners is the key to grasping the daily learning behavior of online learners. Learning style is composed of learners' unique cognition, emotions and physiological behaviors. It is a relatively stable learning method that reflects how learners perceive information, how to interact with the learning environment, and respond to it. Domestic and foreign scholars have carried out research on the classification of online learning styles, learning behavior monitoring, learning behavior feature extraction, behavior model construction and learning effect evaluation...

AI Technical Summary

Problems solved by technology

[0004] Although the perspectives are different, there are few studies on whether users' learning styles and behaviors are affected by factors such as network platforms and course resource presentation forms.

Images