Special lssues
Table of Content

Humanized Computing and Reasoning in Teaching and Learning

Submission Deadline: 15 April 2022 (closed)

Guest Editors

Prof. Xinguo Yu, Central China Normal University, China
Dr. Jun Shen, University of Wollongong, Australia
Dr. Yuan Sun, National Institute of informatics, Japan
Dr. Yalin Zheng, The University of Liverpool, United Kingdom 


Traditional digital education is indifferent and rigid as it mainly is the outcome of technology applying into education, which is far from the humanized digital education. Humanized computing and reasoning technology includes the methods and algorithms that can conduct computing and reasoning tasks as people do. Some studies have shown that humanized computing and reasoning technology, such as knowledge transform based problem solving, knowledge network based diagnosis, knowledge network based education evaluation can be applied to many scenarios of educational artificial intelligence and make the teaching and learning interaction more humanized and personalized. It is more and more evident that humanized computing and reasoning technology has great research potential and application value in the future digital education. For example, automatic problem solving can generate the humanoid solution and humanoid teaching video for exercise problems based knowledge extraction and knowledge inference; diagnosis system can report the learning outcome of an individual student in terms of knowledge points by mining learning data; AI teaching support system can provide smart teaching help to teachers based on modelling educational situations. Since the great potential of humanized computing and reasoning technology, many teams from many countries work on it. This special issue will also receive a good batch of submissions from TALE 2021: http://tale2021.org/index.html


AI Education, Modelling Education, Educational Computing, Humanized Computing, Humanized Reasoning

Published Papers

  • Open Access


    Solving Geometry Problems via Feature Learning and Contrastive Learning of Multimodal Data

    Pengpeng Jian, Fucheng Guo, Yanli Wang, Yang Li
    CMES-Computer Modeling in Engineering & Sciences, Vol.136, No.2, pp. 1707-1728, 2023, DOI:10.32604/cmes.2023.023243
    (This article belongs to this Special Issue: Humanized Computing and Reasoning in Teaching and Learning)
    Abstract This paper presents an end-to-end deep learning method to solve geometry problems via feature learning and contrastive learning of multimodal data. A key challenge in solving geometry problems using deep learning is to automatically adapt to the task of understanding single-modal and multimodal problems. Existing methods either focus on single-modal or multimodal problems, and they cannot fit each other. A general geometry problem solver should obviously be able to process various modal problems at the same time. In this paper, a shared feature-learning model of multimodal data is adopted to learn the unified feature representation of text and image, which… More >

  • Open Access


    Qualia Role-Based Quantity Relation Extraction for Solving Algebra Story Problems

    Bin He, Hao Meng, Zhejin Zhang, Rui Liu, Ting Zhang
    CMES-Computer Modeling in Engineering & Sciences, Vol.136, No.1, pp. 403-419, 2023, DOI:10.32604/cmes.2023.023242
    (This article belongs to this Special Issue: Humanized Computing and Reasoning in Teaching and Learning)
    Abstract A qualia role-based entity-dependency graph (EDG) is proposed to represent and extract quantity relations for solving algebra story problems stated in Chinese. Traditional neural solvers use end-to-end models to translate problem texts into math expressions, which lack quantity relation acquisition in sophisticated scenarios. To address the problem, the proposed method leverages EDG to represent quantity relations hidden in qualia roles of math objects. Algorithms were designed for EDG generation and quantity relation extraction for solving algebra story problems. Experimental result shows that the proposed method achieved an average accuracy of 82.2% on quantity relation extraction compared to 74.5% of baseline… More >

  • Open Access


    MDNN: Predicting Student Engagement via Gaze Direction and Facial Expression in Collaborative Learning

    Yi Chen, Jin Zhou, Qianting Gao, Jing Gao, Wei Zhang
    CMES-Computer Modeling in Engineering & Sciences, Vol.136, No.1, pp. 381-401, 2023, DOI:10.32604/cmes.2023.023234
    (This article belongs to this Special Issue: Humanized Computing and Reasoning in Teaching and Learning)
    Abstract Prediction of students’ engagement in a Collaborative Learning setting is essential to improve the quality of learning. Collaborative learning is a strategy of learning through groups or teams. When cooperative learning behavior occurs, each student in the group should participate in teaching activities. Researchers showed that students who are actively involved in a class gain more. Gaze behavior and facial expression are important nonverbal indicators to reveal engagement in collaborative learning environments. Previous studies require the wearing of sensor devices or eye tracker devices, which have cost barriers and technical interference for daily teaching practice. In this paper, student engagement… More >

  • Open Access


    An Auto-Grading Oriented Approach for Off-Line Handwritten Organic Cyclic Compound Structure Formulas Recognition

    Ting Zhang, Yifei Wang, Xinxin Jin, Zhiwen Gu, Xiaoliang Zhang, Bin He
    CMES-Computer Modeling in Engineering & Sciences, Vol.135, No.3, pp. 2267-2285, 2023, DOI:10.32604/cmes.2023.023229
    (This article belongs to this Special Issue: Humanized Computing and Reasoning in Teaching and Learning)
    Abstract Auto-grading, as an instruction tool, could reduce teachers’ workload, provide students with instant feedback and support highly personalized learning. Therefore, this topic attracts considerable attentions from researchers recently. To realize the automatic grading of handwritten chemistry assignments, the problem of chemical notations recognition should be solved first. The recent handwritten chemical notations recognition solutions belonging to the end-to-end trainable category suffered from the problem of lacking the accurate alignment information between the input and output. They serve the aim of reading notations into electrical devices to better prepare relevant e-documents instead of auto-grading handwritten assignments. To tackle this limitation to… More >

Share Link