[ISEA2024] Paper: Tiancheng Liu, Anqi Wang, Xinda Chen, Jing Yan, Yin Li, Pan Hui & Kang Zhang — PoEmotion: Can AI Utilize Chinese Calligraphy to Express Emotion from Poems?

Abstract

Keywords: Poem, emotion, visualization, Chinese Calligraphy, NLP, generative art

This paper presents PoEmotion, an approach to visualizing emotions in poetry with Chinese calligraphy strokes. Traditional textual emotion analysis often lacks emotional resonance due to its mechanical nature. PoEmotion combines natural language processing with deep learning generative algorithms to create Chinese calligraphy that effectively conveys the emotions in poetry. The created calligraphy represents four fundamental emotions: excitement, anger, sadness, and relaxation, making the visual representation of emotions intuitive and concise. Furthermore, the approach delves into the relationship between time, emotion, and cultural communication. Its goal is to provide a more natural means of communicating emotions through non-verbal mediums to enhance human emotional expression.

  • Tiancheng Liu, The Hong Kong University of Science and Technology (Guangzhou) (Guangzhou, China)
  • Anqi Wang, The Hong Kong University of Science and Technology (Hong Kong)
  • Xinda Chen, China Academy of Art (Hangzhou, China)
  • Jing Yan, The Hong Kong University of Science and Technology (Guangzhou) (Guangzhou, China)
  • Yin Li, China Academy of Art (Hangzhou, China) and The Hong Kong University of Science and Technology (Hong Kong)
  • Pan Hui, The Hong Kong University of Science and Technology (Guangzhou) (Guangzhou, China) and The Hong Kong University of Science and Technology (Hong Kong)
  • Kang Zhang, The Hong Kong University of Science and Technology (Guangzhou) (Guangzhou, China)