Paper Info
Title
An Automatic Matching Model for Chinese Test Questions and Knowledge Points Based on Text Classification
Abstract
Computer assisted instruction system is a hot topic in the field of smart education. In the current research, the knowledge point relationships to which the questions belong are mostly matched by labor. Due to the large workload and the influence of expert experience, the quality and efficiency of manually matching test questions with knowledge points is difficult to guarantee. In this paper, we propose a model named AMMTC based on text classification in order to automatically match the test questions to the knowledge points. According to the model, firstly, we use the TF-IDF algorithm to extract the test text features and transform the test text into a vector space model. Secondly, we use the test text features to select a classification model with the highest accuracy from multiple classification models. Finally, the selected classification model is utilized to match the test questions to the knowledge points. The experimental result show that the AMMTC model can automatically match the test questions to the knowledge points, which not only reduces labor consumption, but also has high accuracy.
Year
DOI
Venue
2018
10.1109/ISCID.2018.10181
2018 11th International Symposium on Computational Intelligence and Design (ISCID)
Keywords
Field
DocType
smart education,text classification,classification model,automatically match
Matching test,Computer-Assisted Instruction,Computer science,Workload,Artificial intelligence,Vector space model,Machine learning,Multiple classification
Conference
Volume
ISSN
ISBN
02
2165-1701
978-1-5386-8528-0
Citations 
PageRank 
References 
0
0.34
8
Authors
5
Name
Order
Citations
PageRank
Yancong Li100.68
Zengzhen Shao253.28
Hongxu Sun300.34
Xuechen Zhao421.40
Yanhui Guo532140.94