• Korean Journal of Cognitive Science
• /
• v.21 no.4
• /
• pp.459-480
• /
• 2010

A dialogue system includes various morphological analyses for recognizing a user's intention from the user's utterances. However, a user can represent various intentions via emotional states in addition to morphological expressions. Thus, a user's emotion recognition can analyze a user's intention in various manners. This paper presents a new method to automatically recognize a user's emotion for a dialogue system. For general emotions, we define nine categories using a psychological approach. For an optimal feature set, we organize a combination of sentential, a priori, and context features. Then, we employ a support vector machine (SVM) that has been widely used in various learning tasks to automatically classify a user's emotions. The experiment results show that our method has a 62.8% F-measure, 15% higher than the reference system.

• Design Convergence Study
• /
• v.15 no.1
• /
• pp.233-246
• /
• 2016

Mobile health industry has been combined with IT technology and is attracting attention. The health application has been developed to provide users a healthy life style. First of all, 5 mobile health applications were selected and reviewed in terms of their service trend. It turned out that none of those applications had any emotional data but physical one. Secondly, to extract users' emotion, technological researches were sorted into different categories. And the result implied that text-based emotion recognition technology is the most suitable for the mobile health service. To implement the service, the application was designed and developed the process of emotion recognition system based on the contents of the research. One-dimension emotion model, which is the standard of classifying emotional data and social network service, was set up as a source. In last, to suggest the usage of health application has been combined with persuasive technology. As a result, this paper prospered a overall service process, concrete service scheme and a guidelines containing 15 services in accordance with the five emotions and time. It is expected to become a direction for indicators considering a psychological individual context.

• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.25-30
• /
• 2021

In case of evaluating the similarity of the source code analysis material in the embedded system, the provided source code must be confirmed to be executable. However, it is currently being in which compilation and interface matching with hardware are provided in an unconfirmed materials. The complainant assumes that many parts of the source code are similar because the characteristics of the operation are similar and the expression of the function is similar. As for the analysis result, the analysis result may appear different than expected due to these unidentified objects. In this study, the improvement direction is sugested through the case study by the analysis process of the source code and the similarity of the unverified source code.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.161-162
• /
• 2017

외부환경을 인식하고 상황을 판단해 자율적으로 행동하는 지능형 서비스 로봇은 앞으로 새로운 시장을 열어줄 것으로 기대되며 이와 관련된 연구와 개발이 빠르게 확대되고 있다. 이러한 서비스 로봇에게 가장 중요한 기능은 인간과의 원활한 상호작용이다. 여기서 말하는 상호작용이란 단순히 인간이 원하는 것을 명령하고, 로봇이 이 명령을 수행하는 것에 그치는 것이 아니라, 로봇이 스스로 인간의 감정을 파악하고, 이에 대한 적절한 로봇 자신의 감정 표출이나 서비스, 행동을 제공함으로써 직접적인 소통이 이루어지는 것을 의미한다. 이렇게 로봇이 자연스럽게 인간과 함께 공존하기 위해서 감성 로봇(Emotional Robot) 분야에서 관련된 연구가 활발히 진행되고 있다 본 논문에서는 국내의 감성 로봇의 연구 현황과 발전 방향에 대해 서술한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.173-174
• /
• 2020

이 연구는 선행연구를 바탕으로 아파트경비원에 대한 감정노동에 대한 경비원들의 경험을 통하여 나타나는 문제점과 이에 대한 효율적인 발전방향을 제시하는데 있다. 심층면담 범주와 결과 크게 3가지로 나누었으며 첫째. 경비원들이 인식하는 감정노동인식은 높은 것으로 나타났다. 또한 주민들의 욕설 및 인격모독에 따른 스트레스 증가로 인해 의욕저하로 이어져 왔다. 둘째, 열악한 근무환경에 따른 휴게시간이 보장되지 않으며 경비업무 외적인 업무를 더 많이 수행하는걸로 나타났다. 셋째, 입주민들의 경비업무에 대한 이해도가 낮았으며 수평적 관계가 아닌 갑을관계로 인식하는 경향도 나타났으며. 또한 거기에 따른 부당한 업무지시로 인해 높은 노동강도를 보이고 있는 것으로 나타났다. 따라서 법 개정을 통하여 인권에 사각지대에 놓인 아파트경비원을 보호할 장치가 마련되어야 할 것으로 판단되며, 입주민들의 경비업무에 대한 이해도를 높이고 나아가 처우개선 및 근무환경개선이 필요하다고 사료된다.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.68-86
• /
• 2016

This study confirmed structural causal relations among concepts such as characteristics of store, store image, affective satisfaction, affective commitment, and loyalty and surveyed mediating roles of affective commitment in grocery retailing. Analysis of structural equation modeling with SPSS18.0 and AMOS18.0 were performed to test the research hypothesis. The results are as follows. First, Perceived quality, product assortment and product price influenced satisfaction. Second, Store image influenced affective satisfaction, affective commitment and loyalty. Affective satisfaction influenced affective commitment but not loyalty directly. Third, affective commitment influenced loyalty through the powerful mediating role. The store characteristics was seen to have a positive impact on affective satisfaction through store image, and in turn related to affective commitment, ultimately leading to loyalty. Especially, It is meaningful result in this study which is confirmed affective commitment have a strong mediating role in between store image, affective satisfaction and loyalty. Finally, we discussed the role of affective commitment and the strategies of affective commitment development, and suggested future studies.

• Construction Engineering and Management
• /
• v.22 no.2
• /
• pp.9-12
• /
• 2021

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.6
• /
• pp.119-133
• /
• 2021

Research has been conducted in many fields to identify research trends using text mining, but in the field of emotional labor, no research has been conducted using text mining to identify research trends. This study uses text mining to deeply analyze 1,465 papers at the Korea Citation Index (KCI) from 2004 to 2019 containing the subject word 'emotional labor' to understand the trend of emotional labor researches. Topics were extracted by LDA analysis, and IDM analysis was performed to confirm the proportion and similarity of the topics. Through these methods, an integrated analysis of topics was conducted considering the usefulness of topics with high similarity. The research topics are divided into 11 categories in descending order: stress of emotional labor (12.2%), emotional labor and social support (12.0%), customer service workers' emotional labor (10.9%), emotional labor and resilience (10.2%), emotional labor strategy (9.2%), call center counselor's emotional labor (9.1%), results of emotional labor (9.0%), emotional labor and job exhaustion (7.9%), emotional intelligence (7.1%), preliminary care service workers' emotional labor (6.6%), emotional labor and organizational culture (5.9%). Through topic modeling and trend analysis, the research trend of emotional labor and the academic progress are analyzed to present the direction of emotional labor research, and it is expected that a practical strategy for emotional labor can be established.

• The Journal of the Korea Contents Association
• /
• v.10 no.1
• /
• pp.192-201
• /
• 2010

This research deals with expressive definition of visual contents by using the distance between a subject and a screen resolution, and what changes affect the emotion of those looking at the expressive definition. A visual image captured from a HDTV screen was shown to the 61 students attending a university in the Busan area and SAM evaluation method was used to measure 3 different emotions such as pleasant, arousal, and dominance. While comparing different resolution, looking at high resolution contents rather than low resolution resulted in a direction of pleasant, arousal, and dominance. Also showing a different resolution than consistently showing the same resolution had a more volatile emotional effect. Aftermath multiple comparison resulted in a tendency for emotions to become unpleasant and un-arousal when high resolution contents were shown and then switched to a low resolution contents. There was no result of any significance in the control variables. Also on the aftermath multiple comparison on short, medium and long distance between the subject and the screen resolution, short distance had a bigger pleasant, arousal, and dominance emotional numbers than the rest. In a multiple variable verification result, a resolution and the distance of happiness and excitement showed a positive correlation.

• Journal of Digital Convergence
• /
• v.20 no.2
• /
• pp.57-62
• /
• 2022

This study was conducted with the purpose of listening to the explanations of artworks in the non-face-to-face class and confirming the learner's feelings as a result of the class. The proposed system listens to the explanation of the artwork, inputs the learner's emotions with a dedicated key, and expresses the result in music. To this end, the direction of the non-face-to-face art appreciation class model using the emotion key was set, and based on this, a system for non-face-to-face art appreciation was constructed. The learner will use the 'smart device using the emotion key' proposed in this study to listen to the explanation of the artwork and to input the emotion for the question presented. Through the proposed system, learners can express their emotional state in online art classes, and instructors receive the results of class participation and use them in various ways for educational analysis.