A Self-Relevant CNN-SVM Model for Problem Classification in K-12 Question-Driven Learning

• Main Authors: Eric Hsiao-Kuang Wu, Sung-En Chen, Jhao-Jhong Liu, Yu-Yen Ou, Min-Te Sun
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Classification; convolutional neural network; support vector machine; Word2Vec; question-driven learning
• Online Access: https://ieeexplore.ieee.org/document/9265190/

With the development and progress of science and technology, the learning patterns also evolve. In Question-Driven learning, students clarify and validate what they learn by answering questions. Such a large number of questions needs good management. A well-performed management can avoid the situation that learning materials with the same knowledge set are defined into different sections due to ambiguous expressions. In this work, we propose a hybrid classification model using the CNN-SVM that focuses on K-12 learning materials. We combine the Word2Vec feature and the hidden layer feature of CNN. In response to a current question that contains text and image, we also introduce a multi-modal preprocessing approach. The experiment results validate that the preprocessing method and the hybrid model can outperform the the state-of-the-art method and baseline methods.