Research on classification method of answering questions in network classroom based on natural language processing technology
by Lanlan Liu; Qiang Yu
International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL), Vol. 31, No. 2, 2021

Abstract: In order to overcome the inaccuracy of the current research results of online classroom question-answering classification, a method of online classroom question-answering classification based on natural language processing technology is proposed. The entity relationship model of the network classroom question answering system is constructed, and the model is transformed into the relational data model, the network classroom question answering database is constructed. TF-IDF technology is used to extract curriculum keywords, construct attribute word set, use natural language processing technology to segment students' questions reasonably in the network classroom, convert the words into vectors, calculate the question similarity according to cosine theorem, and then return the answers with the highest degree of similarity to students in the same type of questions. Experimental results show that the classification accuracy of the proposed method is always above 96%, and the user satisfaction is above 94%, with high classification accuracy and user satisfaction.

Online publication date: Tue, 20-Apr-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Continuing Engineering Education and Life-Long Learning (IJCEELL):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com