Proceedings of the 2nd International Conference on Internet Technology and Educational Informatization, ITEI 2022, December 23-25, 2022, Harbin, China

Research Article

Pre-Recommend or Post-Recommend? A Study on the Design of the Recommender System for Aesthetic Education

Download153 downloads
  • @INPROCEEDINGS{10.4108/eai.23-12-2022.2329083,
        author={Baoqing  Song and Yilin  Dai and Hanchao  Zhang and Gongxin  Jiang and Junyan  Chen and Yunji  Cai and Jun  Wu},
        title={Pre-Recommend or Post-Recommend? A Study on the Design of the Recommender System for Aesthetic Education},
        proceedings={Proceedings of the 2nd International Conference on Internet Technology and Educational Informatization, ITEI 2022, December 23-25, 2022, Harbin, China},
        publisher={EAI},
        proceedings_a={ITEI},
        year={2023},
        month={6},
        keywords={ml recommender system ers aesthetic education higher education sor},
        doi={10.4108/eai.23-12-2022.2329083}
    }
    
  • Baoqing Song
    Yilin Dai
    Hanchao Zhang
    Gongxin Jiang
    Junyan Chen
    Yunji Cai
    Jun Wu
    Year: 2023
    Pre-Recommend or Post-Recommend? A Study on the Design of the Recommender System for Aesthetic Education
    ITEI
    EAI
    DOI: 10.4108/eai.23-12-2022.2329083
Baoqing Song1, Yilin Dai1, Hanchao Zhang2, Gongxin Jiang1, Junyan Chen1, Yunji Cai1, Jun Wu1,*
  • 1: Beijing Institute of Technology Zhuhai
  • 2: Beijing Normal University
*Contact email: wu_j@bitzh.edu.cn

Abstract

This paper describes a user's feature found during the design of the aesthetic education recommendation system, namely, Changes in students' (N=873) needs for art education information after a short time (1 hour) in an online art appreciation course offered by the authors. The change indicates that an increase in user demand for the knowledge of the art being recommended. At the same time, the correlation between users' satisfaction with artworks and their demand for recommended art information increase, including art history (0.22), performance information (0.22), famous artists and artworks (0.2), and information about similar art disciplines (0.18). Based on this phenomenon, conclusion points out that the educational recommender system should take into account the rapid changes of students' demand for recommended content.