• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1215-1217
• /
• 2012

기계가 인간의 감정을 인식하기 위해서는 인간의 감정을 정량적으로 측정할 수 있는 모델이 있어야 한다. 하지만, 인간의 감정은 그 사람이 살아온 환경과 그 사람의 기질에 따라서 같은 자극에 노출되어도 사람마다 느끼는 것이 다르다. 따라서 기계가 인간의 감정을 사람의 기질을 포함하는 개인성향 기반의 감정 모델이 필요하다. 본 논문에서는 감정 모델링을 위해 BAS/BIS 가 제안한 개인 성향을 EEG 기반으로 측정 해보고 각 감정 유발 자극 별로 전두엽에서 발생하는 전위를 분석한 결과 각 성향 별로 대뇌 반응이 다르게 나왔다. 이는 인지적 감정이 전이될 때, 성향별로 대뇌에서 다르게 반응 한다는 것을 의미한다.

• Management & Information Systems Review
• /
• v.30 no.4
• /
• pp.195-227
• /
• 2011

There is no doubt that distribution channels and services greatly satisfy consumers' desires. Lots of products and services, stimulate consumers to purchase products to relieve their depressed feeling/stress temporarily, leading them gradually to a shopping addiction. Shopping addiction generates lots of problems, damaging not only consumers themselves but also other consumers and the entire society. Therefore, the purposes of this study were 1) to examine psychological factors that affected addictive shopping orientation of consumers, 2) to explore the effects addictive shopping orientation on the post-purchase emotions(positive emotion/negative emotion), 3) to examine the effect of post-purchase emotions on post-purchase behaviors (repurchasing/refund and exchange/negative word of mouth). 4) the study explored the differences in terms of effects of addictive shopping orientations on post-purchase emotions and behaviors, depending on the retailing channel (online and off line). The study performed a questionnaire survey for female adults older than 18 years old, living Seoul and Pusan areas. By using 404 copies for questionnaires, factor analysis, reliability analysis, and Amos 7.0 were used for the data analysis. It was found that psychological variables, self-esteem, compensatory buying and impulsiveness, had significant effects on addictive shopping orientations. Addictive shopping orientations affect both positive and negative post-purchase emotions in case of off-line shopping. Negative post-purchase emotions have higher impact on the postpurchase behaviors than positive post-purchase emotions.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.31-32
• /
• 2013

본 논문에서는 영화의 등장인물의 성향을 파악하기 위해 시나리오의 대사로부터 감정어를 추출하고, 등장인물의 감정어들을 긍정, 부정, 중립의 3개로 단순화하여 등장인물의 성향을 가시화 시켜주는 방법을 제안한다. 대사로부터 감정어를 추출하기 위해 WordNet 기반의 감정어 추출 방법을 제안한다. WordNet은 단어 간에 상위어와 하위어, 유사어 등의 관계로 연결된 네트워크 구조의 사전이다. 이 네트워크 구조에서 최상위의 감정 항목과의 거리를 계산하여 단어별 감정량을 계산하여 대사를 30 차원의 감정 벡터로 표현한다. 등장인물별로 추출된 감정 벡터를 긍정, 부정, 중립의 3개의 차원으로 단순화 하여 등장인물의 성향을 표현한다.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.131-138
• /
• 2013

In this paper, I propose and evaluate the method that classifies emotional type of characters with their emotional words. Emotional types are classified as three types such as positive, negative and neutral. They are selected by classification of emotional words that characters speak. I propose the method to extract emotional words based on WordNet, and to represent as emotional vector. WordNet is thesaurus of network structure connected by hypernym, hyponym, synonym, antonym, and so on. Emotion word is extracted by calculating its emotional distance to each emotional category. The number of emotional category is 30. Therefore, emotional vector has 30 levels. When all emotional vectors of some character are accumulated, her/his emotion of a movie can be represented as a emotional vector. Also, thirty emotional categories can be classified as three elements of positive, negative, and neutral. As a result, emotion of some character can be represented by values of three elements. The proposed method was evaluated for 12 characters of four movies. Result of evaluation showed the accuracy of 75%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.12
• /
• pp.3788-3796
• /
• 2009

The aim of the study is to look at the relationships among emotional dimensions, commitment to environment, consumer typology, and quality of life. For this study, 303 students completed the questionnaires and SPSS and Amos 4 were employed. The findings are: First, positive emotion increases commitment to environment. Second, commitment to environment encourages green consumer behaviors and quasi-green consumer behaviors while it reduces non-green consumer behaviors. Third, green consumer behaviors increase quality of life while quasi-green consumer behaviors and non-green consumer behaviors do not have any influence on quality of life. Some practical implications are included.

• Proceedings of the KAIS Fall Conference
• /
• 2009.12a
• /
• pp.245-248
• /
• 2009

The aim of the study is to look at the relationships among emotional dimensions, commitment to environment, consumer typology, and quality of life. For this study, 303 students completed the questionnaires and SPSS and Amos 4 were employed. The findings are: First, positive emotion increases commitment to environment. Second, commitment to environment encourages green consumer behaviors and quasi-green consumer behaviors while it reduces non-green consumer behaviors. Third, green consumer behaviors increase quality of life while quasi-green consumer behaviors and non-green consumer behaviors do not have any influence on quality of life. Some practical implications are included.

• Journal of Digital Convergence
• /
• v.20 no.1
• /
• pp.141-153
• /
• 2022

This study tried to understand the structural relationship of consumer characteristics on consumer emotions and satisfaction in online shopping. First, consumer characteristics derived various tendencies through previous studies. Next, consumer emotion was defined as positive and negative emotions in the six purchasing processes from information search to use, and satisfaction was defined as the overall satisfaction of the purchasing experience. To this end, this study measured consumer satisfaction and positive/negative emotions in the six consumption processes in their 20s and 40s with online clothing shopping experience within the last month. Finally, structural equation modeling(SEM) was conducted. As a result, the model fit was good, and impulse purchase tendency, conspicuous consumption tendency, innovation tendency, and trendy shopping tendency only affected negative emotions. On the other hand, it was confirmed that information search tendency, hedonic shopping tendency, and economic shopping tendency directly affect positive emotions and indirectly affect consumer satisfaction. Through this, implications for improving the consumer experience in online shopping were presented by identifying consumer characteristics and enhancing consumer emotions.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.6
• /
• pp.980-990
• /
• 2008

This study tested how impulse buying behavior for apparel was related to hedonic consumption and impulse buying tendencies and emotion in the context of shopping. A total of 290 self-administered questionnaires were obtained from college students during scheduled classes. A structural equation model using a correlation matrix with maximum likelihood was estimated for examining the relationships among consumer tendencies of hedonic consumption and impulse buying, positive emotion, and impulse buying behaviors by LISREL 8.53. Findings showed that impulse buying behaviors for apparel could be classified into planned, reminded, and fashion-oriented impulse buying typologies. Hedonic consumption and impulse buying tendencies had significant effects on positive emotion. Positive emotion had a significant effect on planned, reminded, and fashion-oriented impulse buying for apparel. This study suggests that positive emotion plays an important role in determining impulse buying behaviors relevant to hedonic and impulse buying tendencies. Managerial implications for apparel retailers are discussed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.343-350
• /
• 2008

사람들은 다양한 매체를 통하여 음악을 청취하고 있으며, 느낌별, 장르별, 연령별, 날씨별, 시간별, 장소별, 상황별, 직업별, 악기별, 템포별 등으로 다양한 분류 방법으로 음악을 제공받고 있다. 이는 음악을 분류하는 방법들이 음악 자체에 대한 분석이나 음악을 듣는 환경에 대한 분류로만 제공되고 있기 때문이다. 같은 상황, 환경이라도 개인에 따라서 같은 음악을 듣더라도 다른 감정의 상태를 나타내기 때문에, 개인을 고려한 분류 방법이 요구된다. 본 논문에서는 인간의 성격을 통해 감정의 표현 방식에 차이가 있다는 면을 초점으로 접근하였다. 감정이 미치는 심전도에 미치는 영향과 음악이 신체와 감정에 미치는 영향들을 통해 심전도를 이용하여 개인의 성향에 따른 음원자극에 대한 반응 차이를 통해 개인의 성향이 반영된 분류 방법을 제시하고자 했다.

• Science of Emotion and Sensibility
• /
• v.17 no.1
• /
• pp.53-62
• /
• 2014

Despite the huge potential of the practical application of emotion recognition technologies, the enhancement of the technologies still remains a challenge mainly due to the difficulty of recognizing emotion. Although not perfect, human emotions can be recognized through human images and sounds. Emotion recognition technologies have been researched by extensive studies that include image-based recognition studies, sound-based studies, and both image and sound-based studies. Studies on emotion recognition through facial expression detection are especially effective as emotions are primarily expressed in human face. However, differences in user environment and their familiarity with the technologies may cause significant disparities and errors. In order to enhance the accuracy of real-time emotion recognition, it is crucial to note a mechanism of understanding and analyzing users' personality traits that contribute to the improvement of emotion recognition. This study focuses on analyzing users' personality traits and its application in the emotion recognition system to reduce errors in emotion recognition through facial expression detection and improve the accuracy of the results. In particular, the study offers a practical solution to users with subtle facial expressions or low degree of emotion expression by providing an enhanced emotion recognition function.