Speech-balloon Shapes Estimation for Emotional Text Communication

  • Ryosuke Yamanishi Ritsumeikan University
  • Hideki Tanaka Ritsumeikan University
  • Yoko Nishihara Ritsumeikan University
  • Junichi Fukumoto Ritsumeikan University
Keywords: Comic computing, Speech-balloon, Visualization, Affective computing


The purpose of this study is to visualize speech nuance using speech-balloon shapes in textbased communication. Though speech nuance disappears in a text communication, comic readers can recognize speech nuance from the speech-balloon shape, which expresses nuances, emotions, and intentions. Through the subjective evaluation experiments, we confirmed that the shapes of speech-balloon changed the emotion towards the phrases. In this paper, we focus on the relationships between the linguistic features of speech and speechballoon shapes, and developed an estimation model for speech-balloon shapes with the linguistic features using Naive Bayes classifier. The effectiveness was confirmed especially in the estimation of “Explosion” and “Wave” shapes. The proposed method is expected to be used to visually represent a speech nuance that contains emotion in a text-based communication such as chat system and social networking service.

Author Biographies

Ryosuke Yamanishi, Ritsumeikan University
Assistant Professor at College of Information Science and Engineering
Yoko Nishihara, Ritsumeikan University
Associate Professor at College of Information Science and Engineering
Junichi Fukumoto, Ritsumeikan University
Professor at College of Information Science and Engineering


K. Nagatani, 漫画の構造学! (Structural study of comics). INDEX Press, 2000. (in Japanese).

O. Takeuchi, マンガ表現学入門 (A guide of expression studies of comics). Chikumashobo, 2005. (in Japanese).

W.-T. Chu and Y.-C. Chao, “Line-based drawing style description for manga classification,” in Proc. of the 22nd ACM international conference on Multimedia, pp. 781–784, 2014.

K. Hoashi, C. Ono, D. Ishii, and H. Watanabe, “Automatic preview generation of comic episodes for digitized comic search,” in Proc. of the 19th ACM international conference on Multimedia, pp. 1489–1492, 2011.

Y. Qu, T.-T. Wong, and P.-A. Heng, “Manga colorization,” ACM Transactions on Graphics (SIGGRAPH 2006 issue), vol. 25, no. 3, pp. 1214–1220, 2006.

Y. Qu, W.-M. Pang, T.-T. Wong, and P.-A. Heng, “Richness-preserving manga screening,” ACM Transactions on Graphics (SIGGRAPH Asia 2008 issue), vol. 27, no. 5, pp. 155:1–155:8, 2008.

K. Ito, Y. Matsui, T. Yamasaki, and K. Aizawa, “Separation of manga line drawings and screentones,” in EG 2015 - Short Papers, 2015.

H. Tobita, “Comic engine: interactive system for creating and browsing comic books with attention cuing,” in Proc. of the International Conference on Advanced Visual Interfaces, pp. 281–288, 2011.

H. Tobita, “Comic computing: creation and communication with comic,” in Proc. of the 29th ACM international conference on Design of communication, pp. 91–98, 2011.

H. Tanaka, R. Yamanishi, and J. Fukumoto, “Relation analysis between speech balloon shapes and their serif descriptions in comic,” in Proc. of 4th International Congress on Advanced Applied Informatics, pp. 229–233, 2015.

N. Kobayashi, K. Inui, Y. Matsumoto, and K. Tateishi, “Collecting evaluative expressions for opinion extraction,” Journal of Natural Language Processing, vol. 12, no. 3, pp. 203–222, 2005. (in Japanese).

A. Nakamura, 感情表現辞典 (Dictionary for expressions of emotion). Tokyodo, 1993. (in Japanese).

Technical Papers (Information and Communication Technology)