在這個社群媒體平台發達的時代，虛擬角色已成為虛擬平台的重要識別，其中個人化設計更是不可或缺。色彩為角色外觀最直接的心理感受，而人們對於角色外觀或形象上多以一般口語化的語句描述，同樣地設計師在挑選色票時，也會先確定產品預期要給予的情緒感受，而後才來搭配適合的色彩，可見詞彙對應色彩是未來設計領域的趨勢。本研究將使用自然語言處理技術，搭配所收集的49個形象形容詞與描述句以及小林重順的色彩意象尺度上174個情感詞彙的描述句，開發形象分類器以及色彩意象分類器，使得輸入的描述句能自動分類到適當的類別，接著使用混和色彩意象主題生成方法生成特定的色彩主題，最終能生成出與各形象適配的色彩主題，並評估此方法與形象感知是否一致。
研究結果顯示，形象分類器的分類結果有良好的成效，而色彩意象分類器的分類結果大多也都可以分類到適當的類別，只有少部分的結果不適合。問卷結果顯示在16個形象中有8個形象和虛擬角色的衣著配色之間的感知相符，且具設計背景的受測者較能準確感知到形象與衣著配色間的關係。由此可見，本研究所建立的分類器與色彩主題生成方法有一定的可行性，有助於幫助設計師建立情感與詞彙間的關係，進而挑選到適合的顏色。

In this era of flourishing social media platforms, virtual characters have become crucial identities on virtual platforms, with personalized design being indispensable. Color, being the most direct psychological perception of a character's appearance, is often described in everyday language when discussing the visual aspects of a character. Similarly, when designers choose a color palette, they first determine the emotional impression the product is expected to convey before selecting suitable colors. It is evident that the correlation between vocabulary and color is a trend in the future of design.This study will utilize natural language processing techniques along with 49 image adjectives and descriptive sentences collected, as well as 174 emotional terms from Kobayashi Shigenobu's color image scale. The goal is to develop image and color image classifiers that automatically categorize input sentences into appropriate categories. Subsequently, a hybrid color image theme generation method will be employed to generate specific color themes, ensuring compatibility with various images. The final step involves evaluating the consistency of this approach with image perception.
The research results indicate that the image classifier performs well in classification, and the classification results of the color image classifier mostly fall into appropriate categories, with only a small portion of results being less suitable. Survey results show that out of 16 images, 8 images exhibit perceived congruence between clothing color schemes and virtual character representations. Moreover, participants with a design background demonstrate a more accurate perception of the relationship between images and clothing color schemes. This suggests that the classifier and color theme generation method established in this study have a certain feasibility, assisting designers in establishing connections between emotions and vocabulary, thereby aiding in the selection of suitable colors.

文化部（2022）。臺灣文化創意產業發展年報。臺北市：文化部。
田佩穎（2015）。動畫虛擬角色眨眼動作予人之意象探討（未出版碩士論文）。國立臺中科技大學，臺中市。
吳芳儀（2006）。心理因素影響影像色彩喜好之研究（未出版碩士論文）。國立雲林科技大學，雲林縣。
何宗諭（2022）。基於BERT的情緒分析應用於短句自動審查（未出版碩士論 文）。國立中興大學，臺中市。
李銘龍（2007）。色彩原理Color。新北市：龍騰文化。
周佩瑤（2019）。使用者對虛擬助理角色傾向之感性工學研究（未出版碩士論文）。國立臺北科技大學，臺北市。
邵婕芸（2023）。混和色彩意象主題生成之研究（未出版碩士論文）。國立臺灣師範大學，臺北市。
辜婷資（2013）。心理因素對環境色彩喜好之研究（未出版碩士論文）。中國文化大學，臺北市。
教育部重編國語辭典修訂本（2021）。取自https://dict.revised.moe.edu.tw/dictView.jsp?ID=110662&la=0&powerMode=0
黃毓雯（2013）。數位虛擬人物特徵之服裝色彩意象研究（未出版碩士論文）。 南華大學，嘉義縣。
賴思宇（2022）。以BERT 模型為基礎之情緒分析研究-以Amazon 評論為例（未出版碩士論文）。國立臺北大學，臺北市。
龔莉華（2007）。個性化角色造型之創作研究-以衝突性元素公仔造型為例（未 出版碩士論文）。國立高雄大學，高雄市。
Ameer, I., Bölücü, N., Siddiqui, M.H.F., Can, B., Sidorov, G., & Gelbukh, A. (2023). Multi-label emotion classification in texts using transfer learning. Expert Systems with Applications, 213, 118534.
Bahng, H., Yoo, S., Cho, W., Park, D.K., Wu, Z., Ma, X., & Choo, J. (2018). Coloring with words: Guiding image colorization through text-based palette generation. In Proceedings of the European Conference on Computer Vision (ECCV), 431-447.
Bélisle, J.F., & Bodur, H.O. (2010). Avatars as information: Perception of consumers based on their avatars in virtual worlds. Psychology & Marketing, 27(8), 741-765.
Bem, S.L. (1974). The measurement of psychological androgyny. Journal of Consulting and Clinical Psychology, 42(2), 155-162.
Chen, Y., Yang, J., Pan, Q., Vazirian, M., & Westland, S. (2019). A method for exploring word‐colour associations. Color Research & Application, 45(1), 85-94.
Chen, Y., Yang, J., Yu, L., Westland, S., & Wang, H. (2022). The multiple characteristics of specific associations from words to colors. Color Research & Application, 48(1), 139-150.
Devlin, J., Chang, M.W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
Ding, Z., Qi, Y., & Lin, D. (2021). Albert-based sentiment analysis of movie review. In 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), 1243-1246.
Fong, K., & Mar, R.A. (2015). What does my avatar say about me? Inferring personality from avatars. Personality and Social Psychology Bulletin, 41(2), 237-249.
Gao, Z., Feng, A., Song, X., & Wu, X. (2019). Target-dependent sentiment classification with BERT. IEEE Access, 7, 154290-154299.
Giri, N., & Stolterman, E. (2020). Pixel perfect: Fashion styling in virtual character design process. In HCI in Games: Second International Conference, 76-87. Springer International Publishing.
Gong, S.M., & Lee, W.Y. (2019). Colour harmony of two‐colour combinations using a 3D colour configuration. Coloration Technology, 135(4), 292-304.
Greco, G., Guzzo, A., & Nardiello, G. (2020). FD-VAE: A feature drivenVAE architecture for flexible synthetic data generation. In International Conference on Database and Expert Systems Applications, 188-197. Cham: Springer International Publishing.
Guo, F., Li, F., Nagamachi, M., Hu, M., & Li, M. (2020). Research on color optimization of tricolor product considering color harmony and users' emotion. Color Research & Application, 45(1), 156-171.
Hinton, G.E., & Salakhutdinov, R.R. (2006). Reducing the dimensionality of data with neural networks. science, 313(5786), 504-507.
Horiguchi, S., & Iwamatsu, K. (2018). From Munsell color system to a new color psychology system. Color Research & Application, 43(6), 827-839.
Hsu, S.H., Kao, C.H., & Wu, M.C. (2006). Factors influencing player preferences for heroic roles in role-playing games. CyberPsychology & Behavior, 10(2), 293-295.
Hu, G., Liu, Z., Wang, Y., & Sheng, A. (2020). Calculative modeling for quantified semantics‐color mapping. Color Research & Application, 45(3), 465-476.
Ibrahiem, S.S., Ismail, S.S., Bahnasy, K.A., & Aref, M.M. (2019). Multi-emotion classification evaluation via Twitter. In 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS), 60-67.
Jabreel, M., & Moreno, A. (2019). A deep learning-based approach for multi-label emotion classification in tweets. Applied Sciences, 9(6), 1123.
Kao, D., & Harrell, D.F. (2016). Exploring the impact of avatar color on game experience in educational games. In Proceedings of the 2016 CHI Conference Extended Abstracts on Human Factors in Computing Systems, 1896-1905.
Kao, C., & Fan, I. (2015). A study of image for heroic characters in video games. Asian J. Soc. Sci. Humanit, 4(1), 118-125.
Kingma, D.P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.
Kobayashi, S. (1981). The aim and method of the color image scale. Color Research & Application, 6(2), 93-107.
Kobayashi, S. (1991). Color Image Scale. Kodansha.
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., & Soricut, R. (2019). Albert: A lite bert for self-supervised learning of language representations. arXiv preprint arXiv:1909.11942.
Lee, W.Y., & Gong, S.M. (2022). The relationship between colour harmony and colour emotions—using two‐colour combinations applied on 3D colour configuration. Coloration Technology, 138(4), 397-406.
Lindner, A.J., & Süsstrunk, S. (2013). Automatic color palette creation from words. In Proceedings of the IS&T; 21st Color and Imaging Conference, 69-74.
Lokman, A.M., Mustafa, A.M., & Fathir, M.F.M. (2014). Avatar warrior: A Kansei analysis. In 2014 3rd International Conference on User Science and Engineering (i-USEr), 24-29.
Lupyan, G., Rahman, R.A., Boroditsky, L., & Clark, A. (2020). Effects of language on visual perception. Trends in Cognitive Sciences, 24(11), 930-944.
Moussa, A., & Watanabe, H. (2022). Generation and Extraction of Color Palettes with Adversarial Variational Auto-Encoders. In Proceedings of Sixth International Congress on Information and Communication Technology(ICICT), 2, 889-897.
Münchow, H., Mengelkamp, C., & Bannert, M. (2017). The better you feel the better you learn: do warm colours and rounded shapes enhance learning outcome in multimedia learning?. Education Research International, 2017.
Nandwani, P., & Verma, R. (2021). A review on sentiment analysis and emotion detection from text. Social Network Analysis and Mining, 11(1), 81.
Osgood, C.E., Suci, G.J., & Tannenbaum, P.H. (1957). The measurement of meaning (No. 47). University of Illinois press.
Ou, L.C., Luo, M.R., Woodcock, A., & Wright, A. (2004). A study of colour emotion and colour preference. Part I: Colour emotions for single colours. Color Research & Application, 29(3), 232-240.
Ou, L.C., Luo, M.R., Woodcock, A., & Wright, A. (2004). A study of colour emotion and colour preference. part II: colour emotions for two‐colour combinations. Color Research & Application, 29(4), 292-298.
Plass, J.L., Heidig, S., Hayward, E.O., Homer, B.D., & Um, E. (2014). Emotional design in multimedia learning: Effects of shape and color on affect and learning. Learning and Instruction, 29, 128-140.
Przybylski, A.K., Weinstein, N., Murayama, K., Lynch, M.F., & Ryan, R.M. (2012). The ideal self at play: The appeal of video games that let you be all you can be. Psychological science, 23(1), 69-76.
Sailunaz, K., & Alhajj, R. (2019). Emotion and sentiment analysis from Twitter text. Journal of Computational Science, 36, 101003.
Salur, M.U., & Aydin, I. (2020). A novel hybrid deep learning model for sentiment classification. IEEE Access, 8, 58080-58093.
Sridhar, B.N., Mrinalini, K., & Vijayalakshmi, P. (2020). Data Annotation and Multi-Emotion Classification for Social Media Text. In 2020 International Conference on Communication and Signal Processing (ICCSP), 1011-1015.
Tang, M.T., Zhu, V.L., & Popescu, V. (2021). Alterecho: Loose avatar-streamer coupling for expressive vtubing. In 2021 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 128-137.
Wang, X., Li, X., Liu, X., & Cheng, H. (2022). Using ALBERT and Multi-modal Circulant Fusion for Fake News Detection. In 2022 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2936-2942.
Williams, J.E., & Bennett, S.M. (1975). The definition of sex stereotypes via the adjective check list. Sex roles, 1, 327-337.
Williams, J.E., & Best, D.L. (1977). Sex stereotypes and trait favorability on the Adjective Check List. Educational and Psychological Measurement, 37(1), 101-110.
Wu, Z., & Lin, T. (2016). Investigating the personality associations evoked by single colors: An exploratory study. Color Research & Application, 42(3), 388-396.
Wu, Z., Lin, T., & Li, M. (2018). A computer-aided coloring method for virtual agents based on personality impression, color harmony, and designer preference. International Journal of Industrial Ergonomics, 68, 327-336.
Xu, L., Park, S.J., & Lee, S. (2022). Color2Vec: Web-Based Modeling of Word-Color Association with Sociocultural Contexts. ACM Transactions on Computer-Human Interaction, 30(4), 1-29.
Ye, Z., Zuo, T., Chen, W., Li, Y., & Lu, Z. (2023). Textual emotion recognition method based on ALBERT-BiLSTM model and SVM-NB classification. Soft Computing, 27(8), 5063-5075.