• Proceedings of the Korean Society of Computer Information Conference
• /
• 2014.01a
• /
• pp.177-180
• /
• 2014

서비스 산업의 급격한 발전과 더불어 최상의 서비스를 제공하기 위한 기업 간의 서비스 경쟁 심화와 고객의 욕구변화에 의해 여러 직종에서 근로자들에게 감정노동을 요구하고 있다. 감정노동은 실제 자신이 느끼는 감정과는 상관없이 직무를 행해야 하는 감정적 노동으로 은행원, 승무원, 상담원 등이 대표적인 종사자로 알려져 있다. 감정노동은 이러한 서비스업에 국한되지 않고 교사 등 사람과 대면하는 모든 부류에 포함된다고 하여도 과언이 아니다. 감정노동은 지극히 주관적이고 개인적인 경험인 '감정'에 의해 행해지는 직무 활동으로 개개인의 특성에 따라 감정노동의 정도도 다를 것이다. 이에 본 연구에서는 고객센터 상담사들을 대상으로 인구통계적 특성에 따른 집단간에 감정노동의 차이가 있는지를 살펴보고자 한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.123-126
• /
• 2007

본 논문은 음성신호를 이용한 감정인식에 관한 연구이다. 감정인식에 관한 연구는 휴먼 인터페이스(Human Interface) 기술의 발전에서 인간과 기계의 상호작용을 위한 것이다. 본 연구에서는 음성신호를 이용하여 감정을 분석하고자 한다. 음성신호의 감정인식을 위해서 음성신호의 특정을 추출하여야한다. 본 논문에서는 개인에 따른 음성신호의 감정인식을 하고자하였다. 그래서 화자인식에 많이 사용되는 음성신호 분석기법인 Perceptual Linear Prediction(PLP) 분석을 이용하여 음성신호의 특정을 추출하였다. 본 연구에서는 PLP 분석을 통하여 개인화된 감정 패턴을 생성하여 간단하면서도 실시간으로 음성신호로부터 감정을 평가 할 수 있는 알고리즘을 만들었다.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.461-468
• /
• 2007

일상 생활에서의 대화 또는 컴퓨터를 매개로 이루어지는 대화에서 자기노출은 서로에 대한 개인적인 정보를 공유하여 친밀한 관계를 유지하기 위한 과정이다. 자기노출에서의 개인적인 정보는 생각 및 경험을 비롯하여 감정 등을 의미하는데, 감정은 특히 대화 분위기 형성 및 원활한 대화 진행을 위한 효과적인 의사소통수단으로 작용한다. 대화 시의 감정노출은 대화 상대방(노출 대상)과 감정표현의 대상(표현 대상)에 따라 표현의 실제강도와 노출의 정도가 달라지게 된다. 본 연구에서는 인터넷을 통해 대화를 주고 받거나 자료를 전송할 수 있는 인스턴트 메신저를 통하여 이루어진 대화에서 노출 대상과 표현 대상을 고려하여 대화참여자의 감정상태를 파악한다. 이를 위한 사전조사로 드라마 스크립트 상의 등장인물들의 감정표현 패턴을 분석하고 이를 활용하여 노출 대상이 각각 다른 대화문장에서 통사 및 의미 분석 과정을 거쳐 표현 대상에 따른 대화참여자의 감정상태를 파악하고, 대화참여자가 자신의 감정을 관찰할 수 있는 인터페이스를 제공한다.

• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.160-165
• /
• 2015

Traditional speech emotion recognition techniques recognize emotions using a general training model based on the voices of various people. These techniques can not consider personalized speech character exactly. Therefore, the recognized results are very different to each person. This paper proposes an adaptive speech emotion recognition framework made from user's' immediate feedback data using a prompted labeling technique for building a personal adaptive recognition model and applying it to each user in a mobile device environment. The proposed framework can recognize emotions from the building of a personalized recognition model. The proposed framework was evaluated to be better than the traditional research techniques from three comparative experiment. The proposed framework can be applied to healthcare, emotion monitoring and personalized service.

• The Journal of the Korea Contents Association
• /
• v.12 no.7
• /
• pp.147-155
• /
• 2012

This study is to analyze the difference of the post-viewing emotion and behavior of the audience at a dance performance by general characteristics of the audience. To attain the goal of the study described above paragraphs, the audience of dance performance located in Seoul and Kyoungki-Do was set as a collected group. Then, using the convenience sampling method, finally drew out and analyzed 280 people in total. statistic analysis techniques were used SPSS 18.0 program. Based on the statistical methods above, we had the result of data analysis as follows; First, among the general characteristics(job, viewing frequency, dance experience, and genre), had significantly effect on the post-viewing emotion(positive emotion, satisfaction) Second, among the general characteristics(job, viewing frequency, dance experience, and genre), all the factors had significantly effect on post-viewing behaviors(researching, respectating intention).

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.428-439
• /
• 2016

It becomes undeniable trends that offline shopping stores operate their own online shopping stores too. The multi-channel shopping stores like this allow consumers to have much choices to shop from either offline channel or online channel. This trend, however, also opens new research issues. Especially, we have found from literature survey that a new research model is necessary for more in-depth study of the consumer behavior analysis in the multi-channel trends like this, where those constructs such as offline trust, uncertainty, switching cost, and individual negative emotion are considered. It is noted, especially in the multi-channel environments, that uncertainty and switching cost need to be considered, and that individual tends to feel negative emotion much more. By relying on 406 valid questionnaires, we obtained empirical results such that switching cost and offline trust have a positive effect on continuance intention, and uncertainty tends to increase switching cost. Individual negative emotion also affects continuance intention significantly.

• Iberoamérica
• /
• v.22 no.1
• /
• pp.73-109
• /
• 2020

In the tourism industry, emotional labor-related problems are highly likely because workers cannot avoid frequent face-to-face contacts with customers. Emotional labor, however, is not always recognized in the same pattern by every worker in similar situations. As can be see in this research, emotional labor appears to vary depending on individual characteristics and sociocultural and economic conditions. In fact, there are so many factors affecting emotional labor, and the level of influence concerning these factors can vary depending on when and where they are. Psychological and mental pains and stress from emotional labor depend on a number of factors. The expression of emotional labor, depending on age, length of employment and gender, shows a clear difference. In particular, for those who are planning to participate in international labor migration to the United States in the future, emotional labor was often not recognized as a serious problem or rather a positive social and cultural experience. In fact, there are various types of tourism workers in Oaxaca, and their experiences vary greatly depending on individual and economic and sociocultural environments. The emotional labor of the workers in the tourism sector of Oaxaca also has various forms depending on various conditions. Positive or negative perceptions and consequences of emotional labor vary depending on the circumstances of the individual and working conditions. In other words, socioeconomic conditions, individual personality or experiences, sociocultural characteristics, and autonomy in the workplace, have a significant impact. As a result, the forms and effects of emotional labor expressed and understood by tourism workers vary considerably and may vary depending on the situations. Considering these problems, the way emotional labor emerges is greatly influenced by sociocultural or personal factors as well as economic factors. In addition, rather than considering the existence and seriousness of emotional labor as given depending on the nature of a particular industry or work, it should also be recognized that the expression of emotional labor differ considerably from individual to individual. Also, the seriousness of problems caused by emotional labor can be diversified. In this sense, it is necessary to clearly understand the meanings of the dynamism, diversity and multidimensionality of emotional labor from a new perspective.

• Journal of Distribution Research
• /
• v.16 no.4
• /
• pp.95-127
• /
• 2011

Developing our understanding of retail employee job satisfaction is important, especially given its impact in reducing employee turnover intentions and increasing employee job performance. While developing our understanding of job satisfaction is important, the vast majority of studies examine job satisfaction as a global or single-faceted construct. However, extant research provides evidence that to properly measure job satisfaction, multi-faceted scales are required (e.g. Churchill et al., 1974; Boles et al., 2007; Rutherford et al., 2009). Using the literature on multi-faceted job satisfaction, this study examines retail employees' satisfaction with supervision, job, company policy, promotion, pay, fellow workers, and customers. Specifically, emotional exhaustion, need for emotion, and personal traits (strong, independent, and warm) are examined as antecedents. This study finds that emotional exhaustion is negatively related to all seven facets of job satisfaction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.323-324
• /
• 2012

최근 스마트폰 환경에서 제공되는 수많은 서비스들은 일률적으로 소비자에게 단방향으로 제공되던 예전과 달리 사용자마다 개인화된 서비스 제공을 통해, 더욱 효율적으로 서비스를 제공하려는 시도들이 이루어지고 있다. 그 중에서 감정인식을 이용한 연구는 사용자에게 최적화된 개인화 서비스 제공을 위해 사용자의 감정을 인식하여 사용자가 느끼는 감정에 맞는 서비스를 제공함으로써 보다 몰입감을 느낄 수 있도록 하여 결과적으로 특정 서비스의 이용을 유도하도록 할 수 있다. 본 논문에서는 사용자 선호도와 컨텍스트 정보를 활용하여 사용자의 감정을 추출하고 이를 음성기반 감정인식과 융합하여 그 정확도를 높이고 실제서비스에서 활용할 수 있는 시스템 설계를 제안한다. 제안하는 시스템은 사용자 선호도와 컨텍스트 인식으로 감정을 판단했을 경우의 오류를 음성을 통한 감정인식으로 보완하며, 사용자가 감정인식 시스템을 활용하기 위한 비용을 최소화한다. 제안하는 시스템은 스마트폰에서 사용자 감정을 이용한 애플리케이션이나 추천서비스 등에서 활용이 가능하다.

• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.104-116
• /
• 2011

A recommender system is a personalized decision support tool to suggest suitable products in proper manners for the benefits of both suppliers and consumers, with the assumption of full understating of consumers' needs and preferences. However, a substantial number of studies have focused on making recommender systems more accurate and efficient. Whereas, there have been a few studies on consumers' needs and preferences under their own contexts to accept recommender systems. To this end, this study attempted to find out the impact of personal sentiments and contexts on the willingness to accept music recommender systems based on the simplified "Technology Acceptance Model" and some verified variables from the precedent studies. For the study, we conducted an empirical study using surveys and High-Order Structural Equation Model (SEM). The outcomes of the research was affirmative to the research hypothesis that the personal sentiments and contexts positively affect the acceptance of the music recommender systems.