Title: Research on classification method of answering questions in network classroom based on natural language processing technology
Authors: Lanlan Liu; Qiang Yu
Addresses: School of Geography and Tourism, Harbin University, Harbin 150086, China ' School of Geography and Tourism, Harbin University, Harbin 150086, China
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.
Keywords: natural language processing; online classroom; question answering classification; rules; support vector machine.
International Journal of Continuing Engineering Education and Life-Long Learning, 2021 Vol.31 No.2, pp.152 - 169
Received: 27 Jun 2019
Accepted: 17 Sep 2019
Published online: 20 Apr 2021 *