Presentation 2021-01-27
Coloration of Emotional Expressions in Texts Based on Hue Circle
Kuniaki Yuba, Tsunenori Mine,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When having a conversation using only text, there is sometimes a discrepancy in emotions when using only the written word. Therefore, we tried to solve this problem by visualizing the emotions. To solve this problem, we used the method of coloring emotions by RGB values, assuming that it will be used as an internal emotion value for Chatbot in the future. As a start, we created a color-emotion model by assigning emotions to each of the seven colors except for white, which can be represented by RGB values of [0,255]. We then combined bidirectional GRU with MLP and Attention to learn and measure accuracy. As a result, although the overall accuracy was not as good as the conventional method, we were able to create a model with local superiority.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) RGB / Emotion Learning / GRU / MLP
Paper # AI2020-16
Date of Issue 2021-01-20 (AI)

Conference Information
Committee AI
Conference Date 2021/1/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Naoki Fukuta(Shizuoka Univ.)
Vice Chair Yuichi Sei(Univ. of Electro-Comm.) / Yuko Sakurai(AIST)
Secretary Yuichi Sei(Nagoya Inst. of Tech.) / Yuko Sakurai(Tokyo Univ. of Agriculture and Technology)
Assistant

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Coloration of Emotional Expressions in Texts Based on Hue Circle
Sub Title (in English)
Keyword(1) RGB
Keyword(2) Emotion Learning
Keyword(3) GRU
Keyword(4) MLP
1st Author's Name Kuniaki Yuba
1st Author's Affiliation Kyushu University(Kyushu Univ)
2nd Author's Name Tsunenori Mine
2nd Author's Affiliation Kyushu University(Kyushu Univ)
Date 2021-01-27
Paper # AI2020-16
Volume (vol) vol.120
Number (no) AI-344
Page pp.pp.13-18(AI),
#Pages 6
Date of Issue 2021-01-20 (AI)