• 인지과학
• /
• 제30권2호
• /
• pp.85-104
• /
• 2019

기존 연구들은 타인의 존재가 바람직한 행동을 유도하고 도덕적으로 엄격한 판단을 하게 한다는 것을 보여주었다. 즉, 타인의 존재 자체가 사람들을 더 도덕적인 존재로 만든다는 것이다. 반면 타인의 얼굴 표정에 따라 도덕적 판단이 어떻게 달라지는지에 대한 연구는 거의 존재하지 않는다. 본 연구에서는 타인의 얼굴표정이 드러내는 정서가 도덕적 판단에 미치는 영향을 검증하였다. 이를 위해 부도덕한 혹은 친사회적 행위를 묘사한 제시문과 함께 다양한 정서(특히, 혐오와 행복)를 표현하는 얼굴자극을 함께 제시한 뒤, 제시문에 묘사된 행동의 도덕성을 평가하도록 하였다. 실험 1에서는 타인의 얼굴표정이 도덕적 판단에는 영향을 미치지 않았으나, 제시문의 내용과 표정이 불일치할 때 도덕성 평정의 변산성이 높아지는 것을 확인하였다. 실험 1에서 효과가 나타나지 않은 잠재적 원인들을 수정하여 동일한 절차로 실험 2를 실시하였다. 그 결과 비도덕적 행동에 대해 참가자들은 행복표정보다 혐오표정에서 더 엄격한 판단을 했으나, 친사회적 행동에 대해서는 얼굴표정의 효과가 나타나지 않았다. 실험 3에서는 제시문의 행위자를 참가자 자신으로 여기도록 유도한 뒤 동일한 실험을 실시하였다. 그 결과 실험 2에서 나타난 결과들을 재검증할 수 있었으나 행위주체에 따른 차이는 발견할 수 없었다. 본 연구는 타인의 얼굴표정이 비도덕적 행위에 대한 판단에 특정적으로 영향을 미치며 친사회적 행위에 대한 판단에는 영향을 미치지 않는다는 것을 보여준다. 종합논의에서 본 실험의 결과를 논의하고 한계점을 제시하였다.

• 디자인융복합연구
• /
• 제14권4호
• /
• pp.1-16
• /
• 2015

본 연구는 영화 리뷰 값이 1000개 이상인 673개의 영화를 대상으로 영화 장르별로 관객들이 느끼는 감정 어휘의 분포를 탐색하고 영화 흥행도와 감정 어휘의 관계를 파악하는데 목적이 있다. 분석을 위해 네이버 영화 리뷰를 크롤링하고 감정 어휘 사전을 활용하여 7개의 대표 감정 어휘, 영화 티켓 판매액, 영화 관람 관객 수, 상영 스크린 수, 한 스크린 당 영화 관람 관객 수, 영화의 장르, 영화의 영문 이름으로 구성된 데이터를 생성하였다. 연구 목적을 위한 분석은 상관관계 분석 방법과 Parallel coordinates 시각화 분석 방법을 사용하였다. 연구 결과로는 첫째, 장르에 따른 영화 흥행도를 분석하여 영화 흥행도가 가장 높은 장르는 코미디이고 가장 낮은 장르는 호러라는 결과를 확인하였다. 둘째, 모든 장르에서 'Happy'와 'Surprise'의 값이 높게 나오지만 다른 장르들에 비해 판타지 장르의 영화는 지루한 감정이 많이 느껴지고, SF장르의 영화는 화나는 감정이 많이 느껴진다는 결과를 확인 하였다. 셋째, 모든 장르의 감정 어휘 별 상관관계를 분석하여 Disgust'의 값이 높아질 때 'Anger'의 값도 높아지고, 'Happy'의 값이 높아질 때 'Surprise'의 값은 낮아진다라는 결과를 확인하였다. 넷째, 영화 흥행도에 따른 감정 어휘를 분석하여 영화 흥행도와 'Happy'는 선형 관계이지만 영화 흥행도와 'Fear'는 비선형 관계인 것을 확인 하였다.

• 문화기술의 융합
• /
• 제9권4호
• /
• pp.687-692
• /
• 2023

본 연구는 자연어 처리 딥러닝 모델의 감정분석 정확성을 확인해보고 이를 감성 콘텐츠 개발에 활용하도록 제안한다. GPT-3모델의 개요를 살펴본 후 Aihub에서 제공하는 희곡 대사 데이터 약 6000개를 입력하고 '기쁨', '슬픔', '공포', '분노', '혐오', '놀람', '흥미', '지루함', '통증' 총 9가지 감정 범주로 분류하였다. 이후 자연어 처리 모델 평가 방법인 정확도, 정밀도, 재현율, F1-score 의 평가지표를 활용하여 성능평가를 진행하였다. 감정분석 결과 91% 이상의 정확도를 보였으며 정밀도의 경우 '공포','통증'이 낮은 수치를 보였다. 재현도의 경우 '슬픔', '분노', '혐오'와 같은 부정적인 감정에서 낮은 수치가 나타났고 특히 '혐오'의 경우 데이터 양의 부족으로 인해 오차가 나타난 것으로 확인된다. 기존 연구의 경우 감정분석을 긍정, 부정, 중립으로 나누는 극성분석에만 주로 사용되어 그 특성상 피드백 단계에서만 사용되는 한계가 있었다. 본 연구는 감정분석을 9가지 범주로 확장하여 기획 단계에서부터 이를 고려한 개발을 통해 게임, 전시, 공연, 관광, 디자인, 에듀테크, 미디어 등에서 감성 콘텐츠 개발에 활용될 수 있음을 제안한다. 후속 연구를 통하여 더욱 다양한 일상 대화들을 추가로 수집하여 감정분석을 진행한다면 더욱 정확한 결과를 얻을 수 있을 것으로 기대된다.

• 대한인간공학회지
• /
• 제31권5호
• /
• pp.617-627
• /
• 2012

Objective: The aim of the study was to develop a most widely used Korean dictionary of emotion expressing idioms. This is anticipated to assist the development of software technology that recognizes and responds to verbally expressed human emotions. Method: Through rigorous and strategic classification processes, idiomatic expressions included in this dictionary have been rated in terms of nine different emotions (i.e., happiness, sadness, fear, anger, surprise, disgust, interest, boredom, and pain) for meaning and intensity associated with each expression. Result: The Korean dictionary of emotion expression idioms included 427 expressions, with approximately two thirds classified as 'happiness'(n=96), 'sadness'(n=96), and 'anger'(n=90) emotions. Conclusion: The significance of this study primarily rests in the development of a practical language tool that contains Korean idiomatic expressions of emotions, provision of information on meaning and strength, and identification of idioms connoting two or more emotions. Application: Study findings can be utilized in emotion recognition research, particularly in identifying primary and secondary emotions as well as understanding intensity associated with various idioms used in emotion expressions. In clinical settings, information provided from this research may also enhance helping professionals' competence in verbally communicating patients' emotional needs.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1229-1234
• /
• 2004

Face robots capable of expressing their emotional status, can be adopted as an e cient tool for friendly communication between the human and the machine. In this paper, we present a face robot actuated with arti cial muscle based on dielectric elastomer. By exploiting the properties of polymers, it is possible to actuate the covering skin, and provide human-like expressivity without employing complicated mechanisms. The robot is driven by seven types of actuator modules such as eye, eyebrow, eyelid, brow, cheek, jaw and neck module corresponding to movements of facial muscles. Although they are only part of the whole set of facial motions, our approach is su cient to generate six fundamental facial expressions such as surprise, fear, angry, disgust, sadness, and happiness. Each module communicates with the others via CAN communication protocol and according to the desired emotional expressions, the facial motions are generated by combining the motions of each actuator module. A prototype of the robot has been developed and several experiments have been conducted to validate its feasibility.

• 로봇학회논문지
• /
• 제5권1호
• /
• pp.7-13
• /
• 2010

This paper presents the sound-based emotion estimation method and the growing HRI (human-robot interaction) system for a Mon-E robot. The method of emotion estimation uses the musical element based on the law of harmony and counterpoint. The emotion is estimated from sound using the information of musical elements which include chord, tempo, volume, harmonic and compass. In this paper, the estimated emotions display the standard 12 emotions including Eckman's 6 emotions (anger, disgust, fear, happiness, sadness, surprise) and the opposite 6 emotions (calmness, love, confidence, unhappiness, gladness, comfortableness) of those. The growing HRI system analyzes sensing information, estimated emotion and service log in an edutainment robot. So, it commands the behavior of the robot. The growing HRI system consists of the emotion client and the emotion server. The emotion client estimates the emotion from sound. This client not only transmits the estimated emotion and sensing information to the emotion server but also delivers response coming from the emotion server to the main program of the robot. The emotion server not only updates the rule table of HRI using information transmitted from the emotion client and but also transmits the response of the HRI to the emotion client. The proposed system was applied to a Mon-E robot and can supply friendly HRI service to users.

• 한국생활과학회지
• /
• 제23권6호
• /
• pp.1155-1170
• /
• 2014

This study was performed to understand the structure of family experiences of adolescent behavior problems by analyzing and integrating family experiences in the family relationships. This study intends to discover in-depth family experience by analyzing the individual meaning of family experiences from client's wording. This study was performed in phenomenological method through analyzing the actual counselling cases. The results indicated that 9 units of meaning were derived on family relationships. In the family relationship domain, desire to die or kill others, guilt and resentment, not receiving the respect, mother's ignorance and verbal abuse to father were derived as primary components. Parents-children relationships-Not understanding about his father's drunkenness and disgust, getting exhausted, untrusted parents, unidirectional attitude without communication. Sibling Relationships-younger brother or sister to work off frustration.

• 여성건강간호학회지
• /
• 제5권2호
• /
• pp.288-299
• /
• 1999

The purpose of this research was to understand the dysmenorrhea experience of women. To do this work, we asked 9 women a lot of questions about dysmenorrhea. The interviews were carried out from JUL 1, 1998 through JUL 30, 1998. They were audio-recorded and analyzed using Van kaam's Phenomenological method. Results were as follows. One hundreds forty two descriptive expression were found and they were grouped under twenty common factors. twenty common factors were grouped under six higher categories. Two common factors, "Physical pain", "Physical Discomfort" were grouped under . Three common factors, "Receptively of Femininity", "Women's Persecution", "Mystery of Femininity" were grouped under . Three common factors, "Emotional Anxiety", "Disgust of Pain", "Solitude" were grouped under . Two common factors, "Coping with Pain Relief", "Fear of Pain relief method" were grouped under . One common factors "Beauty" were grouped under , One common factors, "Singularity" were grouped under . As Dysmenorrhea Experience of Women's authors recommend further studies on Women's Dysmenorrhea Experience and go into details nursing intervention of Dysmenorrhea relief method.

• 로봇학회논문지
• /
• 제8권4호
• /
• pp.266-272
• /
• 2013

Facial feature extraction and tracking are essential steps in human-robot-interaction (HRI) field such as face recognition, gaze estimation, and emotion recognition. Active shape model (ASM) is one of the successful generative models that extract the facial features. However, applying only ASM is not adequate for modeling a face in actual applications, because positions of facial features are unstably extracted due to limitation of the number of iterations in the ASM fitting algorithm. The unaccurate positions of facial features decrease the performance of the emotion recognition. In this paper, we propose real-time facial feature extraction and tracking framework using ASM and LK optical flow for emotion recognition. LK optical flow is desirable to estimate time-varying geometric parameters in sequential face images. In addition, we introduce a straightforward method to avoid tracking failure caused by partial occlusions that can be a serious problem for tracking based algorithm. Emotion recognition experiments with k-NN and SVM classifier shows over 95% classification accuracy for three emotions: "joy", "anger", and "disgust".

• 제어로봇시스템학회논문지
• /
• 제19권4호
• /
• pp.364-371
• /
• 2013

Emotion Recognition is one of the important part to develop in human-human and human computer interaction. In this paper, we have focused on the performance of multi-class SVM (Support Vector Machine) with Gaussian RFB (Radial Basis function) kernel, which has been used to solve the problem of emotion recognition from physiological signals and to improve the accuracy of emotion recognition. The experimental paradigm for data acquisition, visual-stimuli of IAPS (International Affective Picture System) are used to induce emotional states, such as fear, disgust, joy, and neutral for each subject. The raw signals of acquisited data are splitted in the trial from each session to pre-process the data. The mean value and standard deviation are employed to extract the data for feature extraction and preparing in the next step of classification. The experimental results are proving that the proposed approach of multi-class SVM with Gaussian RBF kernel with OVO (One-Versus-One) method provided the successful performance, accuracies of classification, which has been performed over these four emotions.