DOI QR코드

DOI QR Code

Emoticon by Emotions: The Development of an Emoticon Recommendation System Based on Consumer Emotions

Emoticon by Emotions: 소비자 감성 기반 이모티콘 추천 시스템 개발

  • Kim, Keon-Woo (Graduate School of Business IT, Kookmin University) ;
  • Park, Do-Hyung (College of Business Administration / Graduate School of Business IT, Kookmin University)
  • 김건우 (국민대학교 비즈니스 IT 전문대학원) ;
  • 박도형 (국민대학교 경영대학 / 비즈니스 IT 전문대학원)
  • Received : 2017.10.31
  • Accepted : 2018.03.09
  • Published : 2018.03.31

Abstract

The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.

인터넷의 발달을 통해 지속적으로 인스턴트 커뮤니케이션이 발달해왔다. 인스턴트 커뮤니케이션에서 가장 대표적인 것이 메신저 애플리케이션이다. 메신저 애플리케이션에서 이모티콘은 송신자의 감정 전달을 보완하기 위해 활용됐다. 메신저 애플리케이션 송신자의 감정 전달에 약한 모습을 보이는데 그 이유는 면대면 커뮤니케이션이 아니기 때문이다. 이모티콘은 과거 화자의 기분 상태를 나타내는 기호로만 사용됐다. 그러나 현재는 이모티콘은 감정 전달 뿐만 아니라 개인의 특성과 개성을 나타내고 싶어 하는 소비자의 심리를 반영하는 형태로 발전해가고 있다. 이모티콘의 사용 환경이 개선되었고, 이모티콘 자체가 발전함으로써 이모티콘 자체에 대한 관심도는 증가하였다. 대표적인 예로 카카오톡, 라인, 애플 등에서 서비스를 진행하고 있으며, 관련 컨텐츠 상품의 매출도 지속적으로 증가할 것으로 전망하고 있다. 이모티콘 자체의 관심도 증가와 관련 사업의 성장세에도 불구하고 현재 적절한 이모티콘 추천 시스템이 부재하다. 국내 점유율 90% 이상의 메신저 애플리케이션인 카카오톡조차 단순히 인기 순이나 최근 순, 혹은 간략한 카테고리 별로 분류한 정도이다. 소비자들은 원하는 이모티콘을 찾기 위해서 스크롤을 계속해서 내려야 하는 불편함이 있으며, 본인이 원하는 감성의 이모티콘을 찾기 어렵다. 소비자들이 편의성 향상과 기업의 이모티콘 관련 사업의 판매 매출 증가를 위해 소비자가 원하는 이모티콘을 추천해줄 수 있는 이모티콘 추천 시스템이 필요하다. 적절한 이모티콘을 추천하기 위해서 소비자가 이모티콘을 보고 느낀 감성에 대해 정량화할 필요성이 있다. 정량화를 통해 소비자가 원하는 이모티콘 셋이 가진 특징과 감성에 대해 분석할 수 있으며, 분석 결과를 토대로 소비자에게 이모티콘을 추천할 수 있다. 이모티콘은 메타데이터화의 방법으로 정량화가 가능하다. 메타데이터화 방법은 빅데이터 시대에 비정형, 반정형 데이터에 대해서 의미를 추출하기 위해 데이터를 구조화 혹은 조직화하는 작업이다. 비정형 데이터인 이모티콘을 메타데이터화를 통해 구조화한다면, 쉽게 소비자가 원하는 감성 형태로 분류할 수 있을 것으로 생각한다. 정확한 감성을 추출하기 위해 감정과 관련된 선행 연구를 통해 7개의 공통 감성 형용사와 한국어에서만 나타나는 은유 혹은 표현적 특징들을 반영하기 위해 하위 세부 표현들까지 고려했다. 이모티콘의 가장 큰 특징인 캐릭터를 기반으로 "표상", "형상", "색상"의 범주에서 세부 하위 감성들을 수집했다. 정확도 높은 추천 시스템을 설계하기 위해 감성 지표만이 아니라 객관적 지표도 고려하였다. 메타데이터화 방법을 통해 이모티콘이 갖고 있는 캐릭터의 특징을 객관적 지표로 14개, 감성 지표로 활용하기 위해 감성 형용사를 36개를 추출하였다. 추출된 감성 형용사는 대비되는 형용사로 구성하여 총 18개로 줄였으며, 18개의 감성 형용사는 카카오톡의 이모티콘을 인기 순으로 임의의 40개 셋을 대상으로 측정하였다. 측정을 위해 이모티콘을 평가할 조사 대상자 온라인으로 모집하였고, 277명의 20~30대의 이모티콘을 구매한 경험이 있는 소비자를 대상으로 설문을 진행하였다. 설문응답자에게 서로 다른 5개의 이모티콘 셋을 평가하도록 하였다. 평가 결과 수집된 18개의 감정 형용사는 요인분석을 통해 감성 지표 요인으로 추출하였다. 추출된 소비자 감성 지표의 요인은 "코믹", "부드러움", "모던함", "투명함"이었다. 이모티콘의 객관적 지표와 감성 지표 요인을 활용하여 소비자 만족과의 관계를 분석하였고, 객관적 지표와 감성 지표 간의 관계도 분석하였다. 이 과정에서 객관적 지표가 소비자 태도에 바로 영향을 주는 것이 아니라 감성 지표 요인을 통해 소비자 태도에 영향을 주는 매개 효과가 있음을 확인하였다. 분석 결과는 소비자의 감성 평가 메커니즘을 밝혀냈고, 소비자의 이모티콘 감성 평가 메커니즘은 객관적 지표가 감성 지표 요인에 영향을 미치며, 감성 지표 요인은 소비자 만족에 영향을 미치는 관계였다. 따라서 감성 지표 요인의 네 가지만으로 이모티콘 추천 시스템을 설계하였고, 추천 방법은 각 감성과의 거리를 유클리디안 거리로 측정하여 거리의 차가 0에 가까울수록 비슷한 감성으로 정의하였다. 본 연구에서 제안한 이모티콘 시스템의 검증을 위해 각 감성 지표 요인과 소비자 만족의 평균을 지표 값으로 활용하여 각 이모티콘 셋의 감성 패턴을 그래프로 비교하였고, 추천된 이모티콘들과 선택된 이모티콘이 대체로 비슷한 패턴을 그리는 것을 확인하였다. 정확한 검증을 위해 사전 조사하였던 소비자를 대상으로 이모티콘 추천 시스템이 제시한 결과와 유사하게 평가하였는지 유사 순위를 세 구간으로 나누어 비교하였고, 순위별 예측 정확도는 결과 1순위 81.02%, 2순위 76.64%, 3순위 81.63%였다. 본 연구의 결과는 학문적, 실무적으로 다양한 분야에서 활용 가능한 방법론을 제시하였으며, 기존에 없던 이모티콘 추천 시스템의 설계를 통해 소비자에게는 편의와 이모티콘을 서비스하는 기업에는 매출증대의 효과를 가져올 것으로 예상한다. 그리고 본 연구를 통해 지능형 이모티콘 시스템으로 발전할 수 있는 단초를 제공했다는 점에서 의미가 있다. 본 연구에서 제안한 감성 요인들을 활용하여 감성 라이브러리로 사용함으로써, 새로운 이모티콘 출시 시 감성 평가의 지표로 활용할 수 있다. 축적된 감성 라이브러리와 기업의 판매 데이터, 매출 정보, 소비자 데이터를 결합하여 본 연구에서 제안한 추천 시스템을 복합형 추천 시스템으로 발전시켜 단순 소비자의 편의성이나 매출 증가뿐만 아니라 기업에서 전략적으로 활용 가능한 지적 자산으로 활용할 수 있을 것으로 판단한다.

Keywords

References

  1. Balabanovic, M., and Y. Shoham, "Content-based, collaborative recommendation," Communications of the ACM, Vol. 40, No. 3 (1997), 66-72. https://doi.org/10.1145/245108.245124
  2. Beyer, M., Gartner says solving big data challenge involves more than just managing volumes of data, Gartner, 2011. Available at: http://www.gartner.com/it/page.jsp?id=1731916.
  3. Cho, K., and K. Kim, "Study of emoticon as an emotional sign under the digital communication environment," Journal of Korean Society of Design Science, Vol. 55 (2004), 319-328.
  4. Choi, H., J., Lee, M. Kim, J. Kim, H. Cho, H. Lee and K. Yoon, "Music recommendation system based on user emotion and music mood," Summer Conference of Korea Society Broadcast Engineers Magazine, (2011), 142-145.
  5. Choi, Y., and D.-H. Park, "Development of Youke mining system with Youke's travel demand and insight based on web search traffic information," Journal of Intelligence and Information Systems, Vol. 23, No. 3 (2017), 155-175. https://doi.org/10.13088/JIIS.2017.23.3.155
  6. Coyle, K., "Understanding metadata and its Purpose," The Journal of Academic Librarianship, Vol. 31, No. 2 (2005), 160-163. https://doi.org/10.1016/j.acalib.2004.12.010
  7. Crystal, D., Language and the internet, 45, Cambridge University Press, 2001.
  8. Halvorsen, A., "Patterns of emoticon usage in ESL students' Discussion Forum Writing," CALICO Journal, Vol. 29, No. 4 (2012), 694-717 https://doi.org/10.11139/cj.29.4.694-717
  9. Hong, J., and J. Lee, "A study on KakaoTalk emoticons through self-representation and symbol characteristic,", Journal of Basic Design & Art, Vol. 15, No. 4 (2014), 495-505.
  10. Jack, R. E., O. G. Garrod, H. Yu, R. Caldara, and P. G. Schyns, "Facial expressions of emotion are not culturally universal,". Proceedings of the National Academy of Sciences, Vol. 109, No. 19 (2012), 7241-7244. https://doi.org/10.1073/pnas.1200155109
  11. Jeon, K., "Analysis of the feature of the emotion expressional communication derived from comical texts: Focusing on cartooncon and character emoticon in MIM," Journal of Digital Design, Vol. 15, No. 4 (2015), 173-182.
  12. Johnston, F. E., V. B. Van Hasselt and M. Hersen, "Rapport, empathy, and reflection," Basic interviewing: A practical guide for counselors and clinicians, 1998, 41-55.
  13. Kang, H., "An analysis on synonymic relations of psychological adjectives," Korean Semantics, Vol. 17 (2005), 43-64.
  14. Kang, T., D.-H. Park, and I. Han, "Beyond the numbers: The effect of 10-K tone on firms' performance predictions using text analytics," Telematics and Informatics, Vol. 35, No. 2 (2018), 370-381. https://doi.org/10.1016/j.tele.2017.12.014
  15. Kim, K.-W., and D.-H. Park, "Design evaluation model based on consumer values: Three-step approach from product attributes, perceived attributes, to consumer values," Journal of Intelligence and Information Systems, Vol. 23, No. 4 (2017), 57-76. https://doi.org/10.13088/JIIS.2017.23.4.057
  16. Kim, S., "The comparative study on the characteristics of emoticons used in mobile messengers - mainly on Korean and foreign mobile messengers," Journal of Digital Design, Vol. 14, No. 1 (2014), 87-96. https://doi.org/10.17280/jdd.2014.14.1.009
  17. Kim, S., "A Study on the expression aspect in emoticon," Korean Semantics, Vo. 38(2012), 1-25.
  18. Kim, Y., "Typography media (emoticon) for the public service and communication," The Journal of the Korea Contents Association, Vol. 11, No. 6 (2011), 197-204. https://doi.org/10.5392/JKCA.2011.11.6.197
  19. Kim, Y., and D.-H. Park, "A study on the consumers' knowledge structure of innovative products through product category concept map: Focusing on 3D and smart TV," Entrue Journal of Information Technology, Vol. 12, No. 3 (2013), 181-197.
  20. Kim, W., "Descartes, the origin of cognitivist theory of emotions and its limit," CHEOLHAK: Korean Journal of Philosophy, Vol. 114 (2013), 1-25.
  21. Laney, D., 3D data management: Controlling data volume, velocity and variety, META Group Research Note, 6, 2001, Available at : http://blogs.gartner.com/doug-laney/files/2012/01/ad949-3D-Data-Management-Controlling-Data-Volume-Velocity-and-Variety.pdf
  22. Lee, D., T. Kang, and D.-H. Park, "The research on pc-based versus mobile device-based shopping behavior depending on consumer purchase decision process: Focusing on task-technology fit theory," Entrue Journal of Information Technology, Vol. 13, No. 3 (2014), 107-122.
  23. Lee, E., "Motivations for the using emoticon: Exploring the effect of motivations and intimacies between users on the attitude and behaviors of using emoticon," Journal of the HCI Society of Korea, Vol. 12, No. 2 (2017), 5-12.
  24. Lee, K., M. Choi, and C. Kim, "Study on laughter-arousing factors of character designs of KakaoTalk emoticons," Journal of Multimedia Society, Vol. 18, No. 2 (2015), 253-259. https://doi.org/10.9717/kmms.2015.18.2.253
  25. Lee, J., Mobile media and mobile society, 33, Communication Books, 2004.
  26. Lee, M., and H. Lee, "The structural analysis of adjective meanings: Related to affective vocabulary," Korean Journal of Cognitive and Biological Psychology, Vol. 2 (1990), 118-138.
  27. Lee, S., "The study of emoticon as a nonverbal symbolic representation of CMC," Journal of the Korean Society of Design Culture, Vol. 7, No. 2 (2001), 99-111.
  28. Lim, J., "Linguistically encoding aspects of physiological effects of emotions," Discourse and cognition, Vol. 6, No. 2 (1999), 89-117.
  29. Lim, J., "A study on the metaphorical aspects of basic emotional expressions in Korean," Korean Linguistics, Vol. 17 (2002), 135-162.
  30. Na, J., H. Jun., Y. Chen., H. Choi., and D.-H. Park, "The Development and practice of design thinking methodology based on gamification: Focusing on university loyalty program," Journal of Information Technology Services, Vol. 15, No. 2 (2016), 65-80.
  31. Park, D.-H., "The process of user experience quality evaluation and product improvement based on consumer needs: focusing on mobile phone camera experience," Entrue Journal of Information Technology, Vol. 12, No. 1 (2013), 165-175.
  32. Park, D.-H., "A study on the success factors and strategy of information technology investment based on intelligent economic simulation modeling," Journal of Intelligence and Information Systems, Vol. 19, No. 1 (2013), 35-55. https://doi.org/10.13088/jiis.2013.19.1.035
  33. Park, D.-H., "The development of travel demand nowcasting model based on travelers' attention: focusing on web search traffic information," The Journal of Information Systems, Vol. 26, No. 3 (2017a), 171-185. https://doi.org/10.5859/KAIS.2017.26.1.171
  34. Park, D.-H., "Virtuality as a psychological distance: The strategy for advertisement message appeal depending on virtuality," Journal of Information Technology Applications & Management, Vol. 24, No. 2 (2017b), 39-54.
  35. Park, D.-H., "Virtuality as a psychological distance and temporal distance: Focusing on the effect of product information type on product attitude," Knowledge Management Research, Vol. 18, No. 3 (2017c), 163-178.
  36. Park, D.-H., and J. Chung, "The effect of regulatory fit on consumer product attitude: advertisement fit vs. consumer reviews fit," The e-Business Studies, Vol. 15, No. 4 (2014), 127-148. https://doi.org/10.15719/geba.15.4.201408.127
  37. Park, H., "Relationship between emoticons and nonverbal behaviors in online chatting system: Emoticons as relational control mechanism," Journal of Communication Science, Vol. 5, No. 3 (2005), 273-302.
  38. Park, J., V. Barash, C. Fink and M. Cha, "Emoticon style: Interpreting differences in emoticons across cultures". In Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2013, 466-475.
  39. Park, Y., and D.-H. Park, "S/W developer's IT project participation: Focusing on the moderating role of regulatory focus on the effect of technology recency on participation intention," Knowledge Management Research, Vol. 18, No. 2 (2017), 45-63.
  40. Pazzani, M. J., "A framework for collaborative, content-based and demographic filtering," Artificial intelligence review, Vol. 13, No. 5 (1999), 393-408. https://doi.org/10.1023/A:1006544522159
  41. Sarwar, B., G. Karypis, J. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms," In Proceedings of the 10th international conference on World Wide Web, 2001, 285-295.
  42. Semeraro, G., P. Lops, P. Basile, and M. de Gemmis, "Knowledge infusion into content-based recommender systems," In Proceedings of the third ACM conference on Recommender systems, 2009, 301-304.
  43. Wolf, A., "Emotional expression online: Gender differences in emoticon use," Cyber Psychology & Behavior, Vol. 3, No. 5 (2000), 827-833. https://doi.org/10.1089/10949310050191809
  44. Yang, K., N. Kim, and E. Jung, "A study on the user evaluation for design of game characters about traditional culture: Focused on preference of domestic and foreign game character design," Journal of the Korean Society of Design Culture, Vol. 20, No. 3 (2014), 333-342.

Cited by

  1. 발신자의 감정 깊이 및 수신자와의 관계에 따른 이모티콘 표현유형과 선호도에 관한 연구 vol.17, pp.1, 2018, https://doi.org/10.18852/bdak.2019.17.1.223
  2. 웹툰 콘텐츠 추천을 위한 소비자 감성 패턴 맵 개발 vol.25, pp.4, 2018, https://doi.org/10.13088/jiis.2019.25.4.067
  3. 시선추적장치를 활용한 모바일 메신저 이모티콘의 시각적 주의집중 분석 vol.23, pp.3, 2018, https://doi.org/10.9717/kmms.2020.23.3.508
  4. 온라인 메신저 서비스에서의 이모티콘 사용 동기: 조절초점 성향을 중심으로 vol.21, pp.2, 2020, https://doi.org/10.15813/kmr.2020.21.2.006