遊戲音樂設計與玩家情感反應之研究

A Study of Players' Affective Response on Video Game Music Design

林佩儒(Pei-Ju Lin)；楊智傑(Chih-Chieh Yang)

情感反應 ； 遊戲音樂作曲 ； 因素分析 ； 支援向量機 ； 支援向量機遞迴特徵消去 ； Affective Responses ； Video Game ； Music Composition ； Factor Analysis ； Support Vector Machine ； Support Vector Machine Recursive Feature Elimination

商業設計學報

21期（2017 / 12 / 01）

154 - 173

繁體中文

在電玩遊戲設計產業中，其音樂部分的設計影響力可以讓玩家融入並沉浸於遊戲角色與情境當中，因此如何設計一款有效影響，並滿足玩家玩遊戲時的音樂情感反應模式，是相當重要的遊戲設計課題。本研究以感性工學為基礎，以八位元時代的電玩遊戲音樂做為樣本，針對100首遊戲音樂，以因素分析方法找出五種代表性情感形容詞共15首音樂樣本作為研究，以支援向量機(support vector machine)分類模型用來建立玩家情感反應與遊戲音樂特徵之間的關聯性，並進一步使用支援向量機遞迴特徵消去(support vector machine recursive feature elimination)，挑選出最具關鍵性之音樂並展示出每個特徵對於八位元遊戲音樂之重要性。研究結果顯示，情感反應尺度結果歸類出五組代表形容詞，分別是平靜的、冰冷的、奇異的、幽默的以及熱情的，並針對形容詞的音樂樣本進行音訊分析，可看出與三項音樂特徵的情感反應關係，最後透過支援向量機所獲得的預測模型準確率為94%，證明本研究所選用特徵以及特徵分析方式是可行的，而分析結果也提供具體而明確的音樂設計建議。透過本研究所提出的方法，遊戲音樂設計師可以考慮音樂特徵的優先排列順序，針對特定遊戲情感內容或情境，設計出符合玩家需求的遊戲產品。

In the video game industry, it is the game music that enables players to immerse themselves in their roles within the context of the game. It is, therefore, how to collecting affective responses from game player is of crucial importance to music composers wishing to create an appealing game music track. However, the problems inherent in producing game music works have not yet been intensively and systematically investigated. Hence, based on Kansei engineering, this study proposes a novel methodology for get insight and better understanding the players' emotion in playing game that integrates several methods. Factor analysis (FA) identifies representative adjectives for music samples. Three musical features, including tonality, interval, and rhythm, were extracted for analysis. A support vector machine (SVM) classification model established the connection between the musical features and the affective responses of players. Finally, support vector machine recursive feature elimination (SVM-RFE) was employed to identify critical musical features and determine their importance to game music. The emotional response scale results generalized five representative adjectives: calming, cold, fantastic, humorous, and passionate. A signal analysis of the music samples for each adjective revealed their emotional response relationship with the three music features. Finally, the accuracy rate of the prediction model obtained using the support vector machine was 94%, which demonstrates that the features and the feature analysis approach used in this study are feasible. The analysis results also provide clear and specific suggestions regarding music design. Using the proposed approach, game music designers can consider the priority of music features before designing game products that meet game player needs with certain emotional content or scenarios.

1. 林佩儒、楊智傑(2015)。八位元遊戲音樂與情感反應關聯性之初探。商業設計學報，19，81-93。
   連結：
2. Alpert, J.I.,Alpert, M.I.(1990).Music influences on mood and purchase intention.Psychology and Marketing,7,109-33.
3. Bruner, J.(1990).Acts of meaning.Cambridge, MA:Harvard University Press.
4. Budd, M.(1985).Music and the emotions: The philosophical theories.London:Routledge.
5. Collins, K.(2008).Game Sound: An Introduction to the History, Theory, and Practice of Video Game Music and Sound Design.The MIT Press.
6. Collins, K.(2008).In the loop creativity and constraint in 8-bit video game audio.Twentieth-century Music,4,209-227.
7. Cook, N. D.(2002).Tone of Voice and Mind: The Connections Between Intonation, Emotion, Cognition, and Consciousness.John Benjamins Pub Co.
8. Cooke, D.(1990).The Language of Music.USA:Oxford University Press.
9. David, W. B.,Thaut, M. H.,Gfeller, K. E.(1998).An Introduction to music therapy: theory and practice.USA:McGraw-Hill.
10. Davies, S.(1994).Musical meaning and expression.Ithaca, NY:Cornell University Press.
11. Ekman, P.(1992).An argument for basic emotions.Cognition & Emotion,6,169-200.
12. Eladhari, M.,Nieuwdorp, R.,Fridenfalk, M.(2004).The soundtrack of your mind: mind music-adaptive audio for game characters.Advances in Computer Entertainment' 06,Hollywood, CA, USA:
13. Guieford, J. P.(1965).Fundamental Statistics in Psychology and Education.New York:McGram Hill.
14. Han, S. H.,Kim, K.J.,Yun, M. H.(2004).Identifying mobile phone design features critical to user satisfaction.Human Factors and Ergonomics in Manufacturing,14(1),15-29.
15. Han, S.H.,Hong, S. W.(2003).A systematic approach for coupling user satisfaction with product design.Ergonomics,46(13/14),1441-1461.
16. Hargreaves, D. J.(ed.),North, A. C.(ed.)(1997).The social psychology of music.New York, NY:Oxford university press.
17. Hsiao, S. W.,Huang, H. C.(2002).A neural network based approach for product form design.Design Studies,23,67-84.
18. Hunt, M.,Lennig, M.,Mermelstein, P.(1980).Experiments in syllable-based recognition of continuous speech.Acoustics, Speech, and Signal Processing, IEEE International Conferenceon ICASSP '80.
19. Izard, C. E.(2007).Basic emotions, natural kinds, emotion schemas, and a new paradigm.Perspectives on Psychological Science,2,260-280.
20. Jindo, T.,Hirasago, K.,Nagamachi, M.(1995).Development of a design support system for office chairs using 3-D graphics.International Journal of Industrial Ergonomics,15,49-62.
21. Juslin, P. N.,Zentner, M.(2002).Current trends in the study of music and emotion: Overture.Musicae Scientiae,Special Issue , 2001-2002,3-21.
22. Kim, J. O.,Mueller, C. W.(1978).Factor Analysis: Statistical Methods and Practical Issues.Newbury Park:Sage Publication.
23. Lartillot, O, Toiviainen, P.,Eerola, T.(2008).A Matlab Toolbox for Music Information Retrieval.Finland:University of Jyvaskyla.
24. LeCun, Y.,Denker, J.,Solla, S.,Howard, R.,Jackel, L. D.(1990).Optimal brain damages.Advances in neural information processing systems,Mateo, CA:
25. Li, D.,Sethi, I. K.,Dimitrova, N.,McGee, T.(2001).Classification of general audio data for content-based retrieval.Pattern Recognition Letters,22,533-544.
26. Livingstone, S. R.,Brown, A. R.(2005).Dynamic Response: Real-Time Adaptation for Music Emotion.Proceedings of the Second Australasian conference on Interactive Entertainment,Sydney:
27. MacKay, D.(2006).Chemometrics, econometrics, psychometrics-How best to handle hedonics?.Food Quality and Preference,17,529-535.
28. Miller, H. M.,Taylor, P.,Williams, E.(1991).Introduction to Music.Flagtown, New Jersey, USA:
29. Nagamachi, M.(1995).Kansei Engineering: a new ergonomic consumer-oriented technology for product development.International Journal of Industrial Ergonomics,15(1),311-346.
30. Nunnally, J. C.(1967).Psychometric Theory.USA:McGraw-Hill.
31. Park, J.,Han, S. H.(2004).A fuzzy rule-based approach to modeling affective user satisfaction towards office chair design.International Journal of Industrial Ergonomics,34,31-47.
32. Quinlan, J. R.(1993).C4.5: Programs for machine learning.San Mateo, California:Morgan Kaufmann.
33. Radocy, R. E.,Boyle, J. D.(2003).Psychological Foundations of Musical Behavior.Springfield, IL:Charles C. Thomas.
34. Robinson, J.(2005).Deeper than Reason: Emotion and its Role in Literature, Music, and Art.Oxford:Oxford University Press.
35. Russell, J. A.(2003).Core affect and the psychological construction of emotion.Psychological Review,110,145-172.
36. Sadie, Stanley(ed.),Tyrrell, John(ed.)(2001).The New Grove Dictionary of Music and Musicians.London:Macmillan Publishers.
37. Scherer, K. R.,Zentner, M. R.(2001).Emotional effect of music: Production rules. Music and emotion: Theory and research.New York, NY:Oxford University Press.
38. Schneck, D. J.,Berger, D. S.(2006).The Music Effect: Music Physiology and Clinical Applications.Jessica Kingsley Publisher.
39. Schölkopf, B.(Ed.),Burges, C.J.C.(Ed.),Smola, A. J.(Ed.)(1999).Advances in Kernel Methods-Support Vector Learning.Cambridge, MA:MIT Press.
40. Sexton, J.(2007).Music, sound and multimedia: From the live to the virtual. Music and the moving image.Edinburgh:Edinburgh University Press.
41. Shieh, M. D.,Yang, C. C.(2008).Classification model for product form design using fuzzy support vector machines.Computers and Industrial Engineering,55(1),150-164.
42. Shieh, M. D.,Yang, C. C.(2008).Multiclass SVM-RFE for product form feature selection.Expert Systems with Applications,35(1-2),531-541.
43. Sloboda, J.(Ed.)(2001).Music and emotion.Oxford:Oxford University Press.
44. Tzanetakis, G.,Cook, P.(2002).Musical genre classification of audio signals.IEEE Transactions on Speech and Audio Processing,10(5)
45. Unehara, M.,Onisawa, T.(2003).Music composition system with human evaluation as human centered system.Soft Computing,7,167-178.
46. Vapnik, V. N.(1982).Estimate of dependencies based on empirical data.New York:Springer.
47. Wallis, I.,Ingalls, T.,Campana, E.(2008).Computer-generating emotional music: the design of an affective music algorithm.Proceedings of the 11th International Conference on Digital Audio Effects,Espoo, Finland:
48. Watson, D.,Wiese, D.,Vaidya, J.,Tellegen, A.(1999).The two general activation systems of affect: Structural findings, evolutionary considerations, and psychobiological evidence.Journal of Personality and Social Psychology,76,820-838.
49. Whalen, Z.(2004).Play along - an approach to videogame music.Game Studies,4(1)
50. Wold, E.,Blum, T.,Keislar, D.,Wheaton, J.(1996).Content-based classification, search, and retrieval of audio.IEEE Multimedia,3,27-36.
51. Zentner, M.,Grandjean, D.,Scherer, K. R.(2008).Emotions evoked by the sound of music: characterization, classification, and measurement.Emotion,8(4),494-521.
52. 林明穎(2009)。碩士論文(碩士論文)。台北，國立台灣師範大學。
53. 林俊男(2001)。碩士論文(碩士論文)。雲林，國立雲林科技大學。
54. 莊雅量(2001)。碩士論文(碩士論文)。新竹，國立交通大學。
55. 黃靜芳、吳舜文(2007)。大學生音樂選曲與情緒反應之相關研究。國際藝術教育學刊，5(1)，54-70。