• International Area Studies Review
• /
• v.15 no.2
• /
• pp.225-245
• /
• 2011

This study investigates the effects of justice dimensions on negative emotion, consumer satisfaction after service recovery, repurchase intention and word-of-mouth intention in a context of service recovery. Behavioral intentions(repurchase intention and word-of-mouth intention) are critical to the discount store sellers' survival and success. The research model is an extension of previous studies, especially considering more recent developments in the service recovery literature. A survey using 458 customers in China was conducted, confirmatory factor analysis was conducted to test the validity of the measurement model, and AMOS analysis approach was used to gain important insights into how customer retention in the discount store business can be ensured. The results suggest that all three dimensions of justice had negative effects on negative emotion, had positive effects on satisfaction after service recovery. Negative emotion had negative effects on recovery satisfaction. Recovery satisfaction had positive effects on repurchase intention and word-of-mouth intention. Finally, this study suggests the implications of these findings and offers directions for future research.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.499-517
• /
• 2008

In this paper, we propose an effective emotion feature extraction method for Korean and evaluate their availability in sentiment classification. Korean emotion features are expanded from several representative emotion words and they play an important role in building in an effective sentiment classification system. Firstly, synonym information of English word thesaurus is used to extract effective emotion features and then the extracted English emotion features are translated into Korean. To evaluate the extracted Korean emotion features, we represent each document using the extracted features and classify it using SVM(Support Vector Machine). In experimental results, the sentiment classification system using the extracted Korean emotion features obtained more improved performance(14.1%) than the system using content-words based features which have generally used in common text classification systems.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.225-226
• /
• 2019

오피니언 마이닝은 온라인 문서의 감성을 추출하여 분석하는 기법이다. 별도의 여론조사 없이 감성을 분석 가능하므로, 최근 활발한 연구 분야이다. 그러나 소셜미디어에는 신조어 등이 많이 포함되어 있어 기존 감성분석 시스템으로는 정확한 분석이 어려울 뿐만 아니라, 복합적인 감성에 대한 분석을 내리기에 불리하다. 이에 본 연구에서는 직관적인 감성모델을 제안하고 SNS에서 주목받는 다양한 신조어를 수용한 감성단어사전을 구축한 후, 이를 적용하여 소셜미디어에 나타나는 복합적인 감성을 분석하는 감성분석시스템을 설계한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1137-1142
• /
• 2010

This paper studied the speech parameters less affected by the human emotion for the development of the robust speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient and frequency warped mel-cepstral coefficient were used as feature parameters. And CMS (Cepstral Mean Subtraction) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using vocal tract length normalized mel-cepstral coefficient, its derivatives and CMS as a signal bias removal showed the best performance of 0.78% word error rate. This corresponds to about a 50% word error reduction as compare to the performance of baseline system using mel-cepstral coefficient, its derivatives and CMS.

• Journal of Fashion Business
• /
• v.17 no.2
• /
• pp.136-150
• /
• 2013

This study investigates the effect of customer emotions on customer evaluation and behavior intention. The subjects used in this study were customers of a fashion shop in Sunchon South Korea. The questionnaires were conveniently sampled from July 2010 to August, 2010. Questionnaire data from 335 customers of a national brand were analyzed through a reliability analysis, factor analysis, and multiple regression analysis. The results of this study are as follows. First, emotions of customer were divided into 2 patterns, positive emotion and negative emotion. Second positive emotion have significant (+) influences on the trust and negative emotion have significant (-) influences on the trust. Third positive emotion have significant (+) influences on the customer orientation and negative emotion have significant (-) influences on the customer orientation. Forth, the emotions of customer have a considerable impact on the interaction intention. And the positive emotion have significant (+) influences on the word-of-mouth intention and negative emotion have not a considerable impact on it. Fifth the positive emotion have significant (+) influences on the attitude toward store and repurchase intention, and negative emotion have significant (-) influences on the attitude toward store and repurchase intention.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.281-291
• /
• 2017

Emotional interaction in virtual reality is necessary of social communication. However, social emotion has been tried to be less recognized quantitatively. This study was to determined social gaze of emotion in business domain. 417 emotion words were collected and 16 emotion words were selected to Goodness of Fit. Emotion word were mapped into 2 dimensional space through multidimensional scaling analysis. Then, X axis defined dimensions of cooperation, competition, and Y axis of low focus and high focus through the FGD. 52 subjects were presented to stimuli for emotion and gaze movement data were collected. Independent t-test results showed that the gaze factor increased in the face, eye, and nose areas at cooperation, and the gaze factor increased in the right face and nose areas at the low focus. It is expected that this will be used as a basic research to evaluate emotions needed in business environment in virtual space.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.21-27
• /
• 2021

Recently, the importance of counseling is increasing due to the Corona Blue caused by COVID-19. Also, with the increase of non-face-to-face services, researches on chatbots that have changed the counseling media are being actively conducted. In non-face-to-face counseling through chatbot, it is most important to accurately understand the client's emotions. However, since there is a limit to recognizing emotions only in sentences written by the client, it is necessary to recognize the dimensional emotions embedded in the sentences for more accurate emotion recognition. Therefore, in this paper, the vector and sentence VAD (Valence, Arousal, Dominance) generated by learning the Word2Vec model after correcting the original data according to the characteristics of the data are learned using a deep learning algorithm to learn the multi-dimensional We propose an emotion recognition model. As a result of comparing three deep learning models as a method to verify the usefulness of the proposed model, R-squared showed the best performance with 0.8484 when the attention model is used.

• Journal of Distribution Science
• /
• v.10 no.2
• /
• pp.19-28
• /
• 2012

Rapidly growing sales amount and the number of discount stores caused many side effects and sensitive issues in Korea. Because these severe competition due to more expensive cost just like excessive increase in advertising and location selection, and these caused completely ruined small merchants as well as passed on to the consumer. This Study focused on competitiveness of discount store in Korea to the perspective of college students, as explored the relationships between marketing communication and store loyalty. And, examined for two moderating effect, 1) consumers' value separated by hedonic value and utilitarian value between marketing communication and store loyalty, and 2) consumers' value separated by hedonic value and utilitarian value between marketing communication and consumption emotion. Finally, this study examined for mediating effect of consumption emotion between marketing communication and store loyalty. In order to verify the relationship, moderating and mediating effects, data were collected from 130 college students in Whasung, Gyeonggi Province to test theoretical model and its hypotheses. Findings are as followed : First, analysis showed that factors such as advertisement(β =.221, p<.05), publicity(β =.513, p<.01), sales promotion(β =.234, p<.01), word of mouth(β =.627, p<.01) and physical environment(β =.339, p<.01) for marketing communication in the discount store have statistically significant positive effect on store loyalty. But the result of regression analysis for which factors are more impact in marketing communication between store loyalty showed that word of mouth(β =.53, p<.01) is only statistically significant. Second, publicity(β =-.895, p<.05), the sub-dimension of marketing communication shows only statistically significant negative moderating effect on store loyalty. But, the results of the moderating effect of value between marketing communication and consumption emotion verified that utilitarian value show statistically significant, specifically advertisement(β =.294, p<.01), physical environment(β =.418, p<.01), sales promotion(β =.245, p<.01), word of mouth(β =.414, p<.01) and publicity(β =1.137, p<.05), respectively. And hedonic value show statistically significant, specifically advertisement(β =.286, p<.01), physical environment (β =.418, p<.01), sales promotion(β =.236, p<.01) and word of mouth(β =.420, p<.01), respectively. But publicity(β =.145, p=.119) is not statistically significant. Finally, the results verified mediating effect for consumption emotion between all factors for marketing communication and store loyalty showed that factors such as advertisement, publicity, word of mouth and physical environment for marketing communication except sales promotion were statistically significant fully mediated in advertisement, and partially mediated in publicity, word of mouth and physical environment. This testified that the consumption emotion had the most important factor to enhance store loyalty to the perspective of College students. These results can provide important implications and invaluable tips for planning marketing strategies and gaining access to new potential customers. Implications and future research directions are also discussed.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.05a
• /
• pp.55-58
• /
• 2009

본 연구는 주관적인 사용자의 감성을 객관적으로 정의하여 2차원 감성 모델에 의한 터치폰의 GUI 디자인 요소에 대한 디자인 가이드라인을 제시하고자 한다. 본 연구는 다음과 같은 단계로 연구를 진행하였다. 첫 번째 단계로 그루밍(Grooming) 사용자들의 라이프 스타일을 조사하여 Norman(2002)에 의거한 감각적, 행태적, 그리고 심볼적 세 가지 레벨의 감성요소를 추출하였다. 두 번째 단계로 Russell(1980)의 28개 감성 어휘와 세 단계 감성과의 관계성을 설문하여 감성모델을 구현하였다. 마지막으로 요인분석을 이용하여 대표 감성 어휘를 도출한 후 감성적 터치폰의 GUI(Graphic User Interaction) 디자인 요소를 제시함으로써 사용자의 감성이 반영된 인간 중심적인 제품 디자인을 위한 가이드라인을 제안한다.