Emotion, fiction and rationality : cognitivism vs. non-cognitivism

최진희 University of Wisconsin-Madison 1999 해외박사

The focus of this dissertation is on the rationality of emotion directed toward fiction. The launch of the cognitive theory of emotion in philosophy of mind and in psychology provides us with a way to show how emotion is not, by nature, opposed to reason and rationality. However, problems still remain with respect to emotion directed toward fiction, because we are emotionally involved with a story about people that do not exist and events that did not happen. This is called the paradox of fiction. The current debate in relation to emotion and fiction in aesthetics revolves around the paradox of fiction. I believe that the paradox of fiction consists of two different problems: an explicatory problem and a classificatory problem. The former concerns how we apprehend fiction if we do not believe that what is described in fiction happened, while the latter concerns the problem concerning if our emotional responses toward fiction do not require belief of the relevant sort, how should we classify them? examine four theories on the first issue: the make-believe theory, the simulation theory, the revisionist theory, and the thought theory. I believe that the revisionist theory and the thought theory provide us with the most plausible view on how we apprehend fiction. For the latter issue, I divide cognitivism in general into two different kinds: narrow cognitivism and broad cognitivism. I defend broad cognitivism anginst narrow cognitivism. However, I believe that cognitivism in general falls short of giving a full account of emotion directed toward fiction, since it neglects the role of non-representational features of fiction in arousing emotion in the reader. In this regard, I attempt to go beyond cognitivism. Last, I examine how we can attribute rationality to emotion directed toward fiction, gi that not all emotional responses are accompanied by cognition, strictly called. By discussing various warranting conditions, I try to show how emotions can be warranted not only in terms of their cognitive component, but also in terms of the perceptual element involved in emotion.

라디오 청취자 문자 사연을 활용한 KoBERT 기반 한국어 다중 감정 분석 연구

이재아 서울과학기술대학교 2023 국내석사

최근 딥러닝 기술 연구의 발전으로 감정 분석에 관한 다양한 연구가 진행되고 있다. 초기 자연어처리 분야에서는 인공지능이 인간의 감정 또는 감성을 단순 극성인 긍/부정으로 분류하는 연구가 다수 존재하였다. 그러나 최근에는 긍/부정으로 감정 극성을 분류하는 이진 감성 분석을 넘어서 더 복잡하고 어려운 태스크인 다중 감정 분석에 관한 연구로 발전하고 있다. 이러한 다중 감정 분석 기술은 방송 분야와 융합하여 새로운 결과 창출을 기대할 수 있다. 그러나 방송 분야에서의 감정 분석 연구는 높은 관심에도 불구하고 아직 부족한 실정이다. 특히, 방송 매체 중 라디오에서 청취자 문자 사연은 실제 인간이 가질 수 있는 다양한 감정이 담겨 있는 텍스트 데이터임에도 불구하고 관련 연구는 미흡할 뿐만 아니라 실제 사람들이 사용하는 문장에 대한 한국어 다중 감정 분석에 관한 연구는 부족하다. 이에 실제 환경에서 수집한 라디오 청취자 문자 사연을 활용하여 감정 분석을 수행하는 시스템을 제안하고, 이를 통해 한국어 다중 감정 분석에 관하여 연구를 진행하였다. 본 논문에서는 실제 환경에서 수집한 라디오 청취자 문자 사연을 활용하여 한국어 다중 감정 분석 성능을 향상하는 방안을 연구하였다. 기존의 감정 분석 연구에서 보편적으로 이용한 개방 데이터셋이 아닌 실제 라디오 방송의 청취자 문자 사연을 직접 수집하여 감정 분석을 위한 한국어 데이터셋으로 활용했다는 점에서 차별성이 있다. 실제 환경에서 수집한 라디오 청취자 문자 사연을 분석함으로써 한국어 감정 분석이 어려운 언어학적 특성에 대하여 고찰해보았다. 또한, 한국어 다중 감정 분석의 정확도를 높일 수 있는 데이터셋 구성에 관한 고찰과 분석을 위해 설문조사와 실험을 수행하였다. 실험을 진행하기에 앞서, 실험을 위한 한국어 말뭉치를 구축하기 위해 감정 레이블링의 보편적인 기준을 정의하기 위하여 설문조사를 진행하였다. 또한, 한국어 및 문어체에 특화된 KoBERT 언어 모델로 한국어 다중 감정 분석 시스템을 구축하여 두 가지 실험을 진행하였다. 정제된 데이터와 정제되지 않은 데이터를 감정 분석 모델에 각각 테스트 데이터로서 주입하여 비교함으로써 비문법적인 요소들이 KoBERT 기반 한국어 다중 감정 분석 시스템 성능에 어떤 영향을 끼치는지 고찰해보았으며, 개방 데이터셋과 직접 구축한 한국어 말뭉치를 비교 분석하여 한국어 다중 감정 분석 시스템의 정확도 향상을 위한 전이학습용 데이터셋 구성 방안을 제안하였다. 본 연구에서는 한국어 감정 분석 정확도가 높다고 검증된 KoBERT 언어모델을 이용한 다중 감정 분석 시스템을 구축하여 감정 분석이 수행되는 과정에서 한국어 다중 감정 분석이 어떠한 이유로 어려운지 분석하고 데이터셋 조성에 대한 방향성을 제시하였다. 이를 통하여 한국어 텍스트 감정 분석의 정확도를 향상할 자료로 쓰이는 데에 의미가 있으며, 방송 분야에서의 감정 분석 기술 활용에 도움이 되고자 한다. With the recent development of Deep Learning technology research, various studies on Emotion Analysis are being conducted. In the early Natural Language Processing field, there were many studies in which Artificial Intelligence classified into various human emotions or into positive/negative emotion. However, recently, beyond Binary Sentiment Analysis, which classifies emotional polarity as positive/negative, it has evolved into a study on Multi-class Emotion Analysis, a more complex and difficult task. Such Multi-class Emotion Analysis technology can be expected to generate new results by converging with the broadcasting field. However, despite high interest in the field of broadcasting, research on Multi-class Emotion Analysis is still insufficient. In particular, although the Radio listeners' text messages are textual data that contains various emotions that humans can have, related studies are insufficient and studies of Korean Multi-class Emotion Analysis on sentences used by real people are insufficient. Accordingly, a system for performing Emotion Analysis using radio listeners’ text messages collected in the actual environment was proposed and through this, a study on Korean Multi-class Emotion Analysis was conducted. In this paper, a method of improving the performance of Korean Multi-class Emotion Analysis was studied by using radio listeners’ text messages collected in a real environment. It is differentiated in that it directly collects listeners’ text messages of actual radio broadcasts and uses them as a Korean dataset for Emotion Analysis, rather than an open dataset commonly used in existing Emotion Analysis studies. By analyzing the radio listeners' text messages collected in the actual environment, the linguistic characteristics that are difficult to analyze Korean emotions were examined. In addition, a survey and experiment were conducted to consider and analyze the composition of a dataset that can increase the accuracy of Korean Multi-class Emotion Analysis. Prior to conducting the experiment, a survey was conducted to define a universal standard for emotional labeling in order to build a Korean corpus for the experiment. In addition, two experiments were conducted by establishing a Korean Multi-class Emotion Analysis system with a KoBERT Language Model specialized in Korean and literary styles. We investigated how non-grammatical factors affect the performance of the KoBERT-based Korean Multi-class Emotion Analysis system by injecting refined data and unrefined data each into the Emotion Analysis model as test data, and proposed a method of constructing a dataset for Fine-tuning to improve the accuracy of the Korean Multi-class Emotion Analysis system. In this study, a Multi-class Emotion Analysis system using the KoBERT Language Model, which was proven to have high accuracy in Korean Emotion Analysis, was established to analyze Korean emotion in the process of Emotion Analysis, and to present the direction for creating a dataset. Through this, it is meaningful to be used as a material to improve the accuracy of Korean Text Emotion Analysis, and it is intended to help apply Emotion Analysis technology in the broadcasting field.

정서 조절 관련 fMRI 연구의 메타분석

왕동평 전북대학교 일반대학원 2022 국내박사

Emotion regulation can promote academic engagement, cognitive functions, and learning abilities among students. The use of habitual emotion regulation strategies may affect real-time emotion regulation. Moreover, emotion regulation strategies are more prone to recruit appropriate brain regions in situations that need to regulate emotions. Different emotion regulation strategies might engage different neural networks, and these networks might be recruited to a different extent depending on the emotion regulation goal. Therefore, the purpose of this study is to explore the brain regions and networks correlated to emotion regulation, emotion regulation strategies, and emotion regulation goals through a meta-analysis of fMRI neuroimaging studies, and to derive educational implications. In order to collect fMRI data on emotion regulation, emotion regulation strategies, and emotion regulation goals electronic journals were used to search for literature reporting Talairach or MNI standard coordinates of healthy subjects from the year 2000 to 2021. Finally, 106 studies and 132 experiments were included. The coordinate-based meta-analysis of Activation Likelihood Estimation(ALE) was used to detect the significant activation regions related to emotion regulation, emotion regulation strategies, and emotion regulation goals. MACM(Meta-Analytic Connectivity Modeling) analysis was also performed to measure functional connectivity in activated regions related to the overall emotion regulation. Data analysis by using GingerALE 3.0.2, and the activated brain regions and connectivity networks were visualized by Mango 4.0.1 and BrainNet Viewer 1.7. The results are summarized as follows. First, the brain regions related to the overall emotion regulation showed a distribution pattern of the frontoparietal network (FPN) and the prefrontal cortex-limbic system network (PFC-limbic system network). They were mainly concentrated in the left medial frontal gyrus (BA6), left inferior frontal gyrus (BA45), left parahippocampal gyrus, right inferior parietal lobule (BA40), left inferior parietal lobule (BA40), and right middle frontal gyrus (BA9). The brain network of emotion regulation was interconnected with other cognitive functions (e. g. perception, attention, memory, learning, decision making, and language abilities) brain networks. Second, emotion regulation strategies reflect the diversity of emotion regulation in specific brain regions. The distraction was single activated in the left inferior frontal gyrus (BA45), left medial frontal gyrus (BA32), left medial frontal gyrus (BA6), and right middle frontal gyrus (BA9). The reappraisal was single activated in the left medial frontal gyrus (BA6), left inferior frontal gyrus (BA7), and right precentral gyrus (BA9). The suppression was single activated in the left middle frontal gyrus (BA6) and left superior frontal gyrus (BA8). The concepts of distraction, reappraisal, and suppression were likely to include specific cognitive processes. The distraction, reappraisal, and suppression co-activation areas are the left medial frontal gyrus (BA6). This result indicated that the left medial frontal gyrus (BA6) plays an important role in emotion regulation strategies. Third, emotion regulation goals reflect the diversity of emotion regulation in specific brain regions. The down-regulation was single activated in the left medial frontal gyrus (BA6), left inferior frontal gyrus (BA45), and right precentral gyrus (BA9). The maintenance was single activated in the left inferior frontal gyrus (BA47), left middle frontal gyrus (BA6), left inferior frontal gyrus (BA6), and right middle frontal gyrus (BA47). The up-regulation was single activation in the left medial frontal gyrus (BA6) and left inferior frontal gyrus (BA47). The concepts of down-regulation, maintenance, and up-regulation were likely to include specific cognitive processes. The down-regulation, maintenance, and up-regulation co-activation areas are the left medial frontal gyrus (BA6), left inferior frontal gyrus (BA45), and left supramarginal gyrus (BA40), left parahippocampal gyrus. Fourth, During the distraction, conjunction analysis for down-regulation showed that the left medial frontal gyrus (BA6), left middle frontal gyrus (BA6), left parahippocampal gyrus, right middle frontal gyrus (BA6), right inferior parietal lobule (BA40), and right parahippocampal gyrus were activated, conjunction analysis for maintenance showed that the left medial frontal gyrus (BA6) and right inferior parietal lobule (BA40) were activated, and conjunction analysis for up-regulation showed that the left medial frontal gyrus (BA6) was activated. During the reappraisal, conjunction analysis for down-regulation showed that the left medial frontal gyrus (BA6), left inferior frontal gyrus (BA45), left inferior temporal gyrus (BA20), and right inferior parietal lobule (BA40) were activated, conjunction analysis for maintenance showed that the left inferior frontal gyrus (BA45) was activated, and conjunction analysis for up-regulation showed that the right inferior parietal lobule (BA40) was activated. During the suppression, conjunction analysis for down-regulation showed that the left supramarginal gyrus (BA40) was activated, conjunction analysis for maintenance showed that the left superior frontal gyrus (BA6) was activated, conjunction analysis for up-regulation showed that the left medial frontal gyrus (BA6) and left middle frontal gyrus (BA6) were activated. Fifth, a relatively fixed brain network was formed between brain regions that activate overall emotion regulation. The left medial frontal gyrus (BA6), left inferior frontal gyrus (BA45), left parahippocampal gyrus, right inferior parietal lobule (BA40), left inferior parietal lobule (BA40), and right middle frontal gyrus (BA9) were the 6 important nodes represent the main concentrated areas of the brain where emotion regulation is activated. By combining the results of this study, we proposed an educational strategy considering corresponding functions of brain regions associated with emotion regulation, emotion regulation strategies, and emotion regulation goals. 정서 조절은 학생의 학습 참여, 인지기능, 학습 능력을 촉진시킬 수 있다. 정서 조절의 정서 조절의 목표 및 전략에 따라 다른 양상으로 나타난다. 이는 신경망 차원에서도 유사할 수 있다. 즉, 정서 조절의 목표 및 전략에 따라 활성화되는 뇌 부위가 다르게 나타날 수 있다. 이에 따라 본 연구에서는 fMRI 신경영상 연구 메타분석을 통하여 정서조절, 정서조절 전략, 정서조절 목표와 관련된 대뇌 영역과 신경망을 탐색하고 교육적 의미를 도출하 고자 하였다. 정서조절, 정서조절 전략, 정서조절 목표에 대한 fMRI 데이터를 수집하기 위하여 2000년부터 2021년까지 건강한 피험자를 대상으로 연구한 후, 뇌 영역 좌표를 보고한 문헌을 검색하였다. 최종적으로 106개의 연구와 132개의 실험 자료를 수집하였다. ALE(약자 포함)를 통해 정서 조절 전략, 목표 별로 활성화되는 뇌 영역을 확인하였으며, 이후 과 MACM (Meta-analytic connectivity modeling) 을 통해 정서 조절과 관련된 활성화 영역의 기능적 연결을 분석하였다.. 분석에는 GingerALE 3.0.2, Mango 4.0.1, BrainNet Viewer 1.7을 사용하였다. 주요 결과를 요약하면 다음과 같다. 첫째, 전반적인 정서 조절과 관련해서는 전두·두정 네트워크와 전전두엽피질-변연계 네트워크의 활성화가 나타났다. 이는 주로 좌측 내측 전두회 (left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA45), 좌측 해마회 (left parahippocampal gyrus), 우측 하두정소엽 (right inferior parietal lobule, BA40), 좌측 하두정소엽 (left inferior parietal lobule, BA40) 과 우측 중전두회 (right middle frontal gyrus, BA9) 에 집중되어 있었다. 둘째, 정서 조절 전략에 따른 활성화 뇌 부위를 분석한 결과, 정서 조절 전략 별로 다양한 뇌 부위가 활성화됨을 확인할 수 있었다. 주의 전환 전략의 경우 좌측 하전두 회 (left inferior frontal gyrus, BA45), 좌측 내측 전두회 (left medial frontal gyrus, BA32), 좌측 내측 전두회 (left medial frontal gyrus, BA6), 우측 중전두회 (right middle frontal gyrus, BA9)가 활성화되었고, 재평가 전략과 관련해서는 좌측 내측 전두회(left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA7), 과 우측 중심전회 (right precentral gyrus, BA9)이 활성화되었다. 억제 전략의 경우 좌측 중전두회 (left middle frontal gyrus, BA6) 과 좌측 위 이마회 (left superior frontal gyrus, BA8) 영역의 활성화되었다. 이를 통해 주의 전환, 재평가, 억제 전략 각각이 고유한 인지 과정과 관련 있음을 확인하였다. 세 전락 모두 활성화된 뇌 영역은 좌측 내측 전두회 (left medial frontal gyrus, BA6)로, 이는 좌측 내측 전두회 (left medial frontal gyrus, BA6) 영역이 정서 조절 전략에 있어 중요한 역할을 담당함을 뜻한다. 셋째, 정서 조절 목표별로 활성화되는 뇌 영역이 달랐다. 하향 조절의 경우 좌측 내측 전두회(left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA45), 과 우측 중심전회 (right precentral gyrus, BA9) 영역이 활성화되었고, 유지 조절은 좌측 하전두 회 (left inferior frontal gyrus, BA47), 좌측 중전두회 (left middle frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA6), 과 우측 중전두회 (right middle frontal gyrus, BA47) 영역이 활성화되었다. 상향 조절의 경우, 좌측 내측 전두회 (left medial frontal gyrus, BA6) 과 좌측 하전두 회 (left inferior frontal gyrus, BA47) 영역이 활성화되었다. 이는 하향 조절, 유지 조절, 상향 조절 각각이 서로 구분되는 인지 과정임을 의미한다. 세 목표 모두에서 활성화되는 뇌 영역은 좌측 내측 전두회 (left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA45), 과 좌측 모서리위회 (left supramarginal gyrus, BA40), 좌측 해마회 (left parahippocampal gyrus) 이었다. 넷째, 주의 전환 전략에 있어서 하향 조절에 대해 결합 분석을 실시한 결과 좌측 내측 전두회 (left medial frontal gyrus (BA6), 좌측 중전두회 (left middle frontal gyrus, BA6), 좌측 해마회 (left parahippocampal gyrus), 우측 중전두회 (right middle frontal gyrus, BA6), 우측 하두정소엽 (right inferior parietal lobule, BA40), 과 우측 해마회 (right parahippocampal gyrus) 영역이 활성화됨을 확인하였다. 유지 조절에 대한 분석에서는 좌측 내측 전두회 (left medial frontal gyrus, BA6) 과 우측 하두정소엽 (right inferior parietal lobule (BA40) 영역의 활성화가, 상향 조절에 대한 분석에서는 좌측 내측 전두회 (left medial frontal gyrus, BA6) 영역의 활성화가 나타났다. 재평가 전략에 대한 결합 분석에서는 하향 조절의 경우 좌측 내측 전두회 (left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA45), 좌측 아래관자회 (left inferior temporal gyrus, BA20), 과 우측 하두정소엽 (right inferior parietal lobule, BA40) 영역, 유지 조절의 경우 좌측 하전두 회 (left inferior frontal gyrus, BA45) 영역, 상향 조절의 경우 우측 하두정소엽 (right inferior parietal lobule, BA40) 영역이 활성화되었다. 억제 전략에 대해 동일한 분석을 실시한 결과, 하향 조절에서는 좌측 모서리위회 (left supramarginal gyrus, BA40), 유지 조절에서는 좌측 위 이마회 (left superior frontal gyrus, BA6), 상향 조절에서는 좌측 내측 전두회 (left medial frontal gyrus, BA6) 과 좌측 중전두회 (left middle frontal gyrus, BA6) 영역이 활성화되었다. 다섯째, 뇌 네트워크를 분석한 결과 좌측 내측 전두회 (left medial frontal gyrus, BA6), 좌측 하전두 회 (left inferior frontal gyrus, BA45), 좌측 해마회 (left parahippocampal gyrus), 우측 하두정소엽 (right inferior parietal lobule, BA40), 좌측 하두정소엽 (left inferior parietal lobule, BA40), 과 우측 중전두회 (right middle frontal gyrus, BA9) 사이에 정소절과 관련하여 중요하게 집중된 6개의 노드를 확인하였다. 본 연구 결과를 바탕으로 학교 현장에서 정서조절을 교육할 때 필요한 시사점에 대해 논의하였다.

Exploring changes of engineering students’ emotion through affect-aware feedbacks in physics problem-solving

Lee, Sungeun Sungkyunkwan university 2020 국내박사

The purpose of the research was to design appropriate affect-aware feedbacks to support students’physics problem-solving. For the purpose, a research was conducted in 2018. Participants were 12 freshmen at an engineering university in 2018 in Gyeonggi-do, South Korea. To conduct the research, what were the emotions experienced by the students through affect-aware feedbacks, which changes in students’ emotions were through affect-aware feedbacks and which appropriate affect-aware feedbacks supports physics problem-solving were investigated. Students’ emotions were influenced through affect-aware feedbacks. Two students could realize their emotions through affect-aware feedbacks. Students experienced positive emotions through affect-aware feedbacks mirroring positive emotion. Students experienced negative emotions through affect-aware feedbacks mirroring negative emotions. It means that students’ emotions can be regulated through affect-aware feedbacks In all problems, lower physics level students’ emotions were changed from negative to positive through affect-aware feedbacks even though they could not solve physics problems. Higher physics performance level class students’ emotions were not related with affect-aware feedback when physics problems were easy. When physics problems were difficult, higher physics performance level class students were impact during solving physics problems through affect-aware feedbacks. Emotions of all students were changed from negative to positive through affect-aware feedbacks. A few students were disappointed when they could not solve physics problems even though they were provided with affect-aware feedbacks. Students who were sensitive to emotions and were of lower physics performance level class showed negative emotions to the affect-aware feedbacks which were related to praise. Students who were sensitive to emotions and were of higher physics performance level class preferred the affect-aware feedbacks which were related to praise. Lower physics performance level class students preferred “I will help”. However, higher physics performance level class students showed negative emotion to the affect-aware feedback “I will help”. Therefore, affect-aware feedbacks related with emotions would be useful to lower physics performance level students. Instructive feedback would be useful to higher physics performance level students.

도덕성 발달을 위한 감정교육의 의미와 방법 연구

문기숙 연세대학교 교육대학원 2005 국내석사

오랫동안 감정은 이성 중시의 윤리관 아래에서 소홀히 다뤄져왔다. 그로 인해 도덕적 지식과 합리적인 사고를 추구하는 인간은 길러냈을 지는 모르지만, 자신의 감정을 적절하게 표현하고 타인과 공동체에 따뜻한 관심 가지며 도덕적 앎을 행위로 옮기는 인간을 길러내는 데에는 여러 가지 한계점을 드러냈다. 그러나 우리가 도덕적으로 살아간다는 것은 도덕적 지식과 판단뿐만이 아니라 도덕적 감정을 가지고 행위 하는 것이 되어야 할 것이며, 도덕적 문제사태에 대해 사고하고 판단할 때 대부분 감정도 함께 작용한다는 것이다. 어떤 사물이나 사건에 대한 개인의 인지적 범주가 형성되면 그 범주는 좋다 또는 싫다와 같은 감정을 수반할 수밖에 없는데, 자신의 목적을 달성하는 데 도움을 준다고 믿는 대상에 대해서는 긍정적인 감정을 갖고, 그렇지 못한 대상에 대해서는 부정적인 감정을 갖기 마련이다. 즉, 감정과 인지 그리고 행위는 완전히 분리된 것이 아니라 어떤 형태로든지 연결되어 있다.일반적으로 무감각, 무감동, 무관심, 이탈 등의 특징을 보이는 감정이 결핍된 사람은 무가치함, 소외, 방황, 비인격화 등으로 인해 고통을 겪을 뿐만 아니라 타인과 조화롭게 어울려 살아가지 못 한다. 성숙한 감정을 지닌 사람만이 직면한 문제 사태에 대한 도덕적으로 민감하게 느끼고 반응할 수 있기 때문에 타인의 어려움과 고통을 이해하며, 그들을 위로하고 도와줌으로써 바람직한 인간 관계의 형성도 가능해진다. 따라서 모든 사회적 행동에 포함되어 있는 감정에 대한 민감성을 높이기 위해서는 자신과 타인의 감정을 인식하고 적절하게 표현할 수 있으며 자아존중감(self-respect), 공감(sympathy), 자제력(self-control), 동정심(compassion), 죄책감(guilty conscience)과 같은 도덕적 감정을 함양하고 습관화하는 기회를 제공하여야 한다. 그렇다면 이제 남은 문제는 어떻게 가르칠 것인가 하는 것이다.인간이 감정을 표현하고 인식하는 방법에는 말과 글로 하는 언어적 방법과 얼굴 표정이나 몸짓, 행동, 옷차림 등의 비언어적 방법이 있다. 그리고 도덕과의 교수-학습 유형에는 학생들의 학습 양식에 따라, 남을 배려하고 공감을 불러일으키며 도덕적 감정을 느끼도록 하는 데 유용한 감동형, 도덕적인 추론 과정을 거쳐 도덕적 판단 능력을 키우도록 하는 데 유용한 사고형, 그리고 기본 생활 습관, 예절, 봉사활동, 역할 수행 등 직접적인 행동 체험이나 경험을 통해 도덕성을 갖출 수 있도록 하는 체험형이 있다. 이와 같은 감정의 소통 방법과 도덕과의 교수-학습 유형을 조합하여 학습활동의 형태를 분류해보면 , 해보기(experience), 듣기(listening), 말하기(talking), 읽기(reading), 쓰기(writing)로 생각해볼 수 있다.이러한 교수-학습 유형들은 저마다 독특한 활동과 감정교육으로서의 의미를 지니고 있는데, 먼저 해보기(experience)는 해본다(doing), 되어본다(being), 느껴본다(feeling)는 의미를 함축하고 있다. 대상과의 직접적이고 전체적인 접촉을 통해 도덕적 가치를 깨닫고, 타인의 입장 등을 자각하며, 희로애락을 느낄 수 있다. 해보기는 역할놀이(role-play), 시뮬레이션(simulation), 놀이학습, 봉사활동, 현장학습 등 다양한 활동으로 공동체에 대한 소속감과 상호간의 유대감을 높여주고 창의력과 협동심, 독립심을 갖게 하며 사회와 환경에 대한 관심을 갖게 한다. 또한 타자의 입장을 취해 봄으로써 도덕적 상상력을 향상시킬 수 있다.듣기형의 학습방법에는 소리 귀기울여 듣기, 문학작품이나 미담사례를 활용한 도덕적 이야기 듣기, 라디오와 녹음기를 활용한 청각매체학습법 등이 있다. 이들 활동의 전제 조건이 되는 적극적 경청(active listening)은 대상의 감정 인식과 이를 통해 자기 감정에 대한 반성을 할 수 있고, 대상과 더불어 함께 감정과 의미를 공유해 나가는 과정이다. 때문에 감정 인식의 내용에 적용시켜 수업을 계획해 볼 때 화자에 대한 감정 변화, 듣기 태도에 대한 반성, 듣기 왜곡의 요인 확인 및 제거 등에 긍정적 효과를 기대할 수 있다.말하기(Talking)는 말하는 이가 자신의 생각과 감정을 듣는 이에게 음성언어나 몸짓 언어로 표현하는 행위로, 상대방의 말을 듣고 판단하여 개인의 내적 동기를 충족할 수 있게 한다. 말하기의 학습 활동으로는 도덕적 경험 이야기하기, 이야기 이어가기, 브레인 스토밍(brain storming), 제한 시간을 둔 스피치, 토의, 문답법 등을 고려해볼 수 있는데 이를 감정 표현에 적용시켜 수업모델을 고안해보면 교사에게 자신의 감정을 직접적이며 자연스럽게 표현할 수 있는 기회를 얻게 해주고, 이 과정을 통해서 적절한 방법으로 감정을 표현하는 것을 배울 수 있게 해줄 수 있음을 예상할 수 있다. 읽기(Reading)는 그 대상을 그림, 사진, 컴퓨터·TV의모니터, 영화 장면 등 시청각 기호 체계로까지 확장시켜 인쇄매체(책, 신문), 영상매체(영화, TV), 인터넷매체로까지 넓힐 수 있다. 읽기의 활동은 독자가 가지고 있는 배경 지식과 경험을 활용하여 텍스트로부터 의미를 엮어 나가는 과정으로 더욱 풍요롭고 다양한 상상을 가능하게 해 주고, 세상과 나의 관계에 대한 체험과 깨달음을 넓혀주며, 대상의 감정에 공감도 하고 동정심을 느낌으로써 타인의 감정 상태에 대한 이해를 높일 수 있다. 나아가 읽기 속의 바람직한 모델을 통해 그러한 삶을 영위하는 태도와 동기를 부여받게 되는데 특히 읽기를 통한 모방학습(modeling)은 도덕적 감정의 상태에 반복적으로 노출되는 것을 용이하게 함으로써 도덕적 감정을 습관화하는데 효과적이다. 이에 따라 도덕적 감정을 습관화할 수 있는 내용으로 수업 계획을 구성할 수 있다.브레인 라이팅(brain writing), 마인드 맵, 감정일기 쓰기, 편지(이메일)주고받기, 저널 쓰기, 독후감 쓰기, 이야기 이어 쓰기 등으로 활동할 수 있는 쓰기(writing)형 교수-학습은 자신의 감정을 순수하게 표현하도록 도와주고, 내적 대화를 통해 자기인식을 북돋워 현실감을 갖도록 하며, 창의적 표현과 문제해결능력을 향상시켜준다. 그리고 무엇보다도 감정의 정화를 통해 불안·긴장감·스트레스·좌절감을 해소시켜주고, 의식적이며 내면적인 대화에 의해 감정 충돌을 완화시켜주기 때문에 감정 조절을 위한 수업을 계획할 때 효과적이다.감정교육의 운영은 감각, 이해, 체험, 놀이, 인간관계 그리고 학습자 중심으로 이뤄진다. 그러나 교사의 눈짓, 몸짓 하나마저도 학생들의 감정에 적지 않은 영향을 미치기 때문에 교사의 자질은 어떤 것보다 중요한 문제이다. 교사는 학생들이 정서적으로 안정될 수 있도록 긍정적인 분위기를 조성하고, 학생들이 자유롭게 자신의 감정을 표현하도록 허용적 분위기를 만들어주며, 부정적인 감정을 조절하고 감정을 일으키는 신념을 변화시켜 스스로 문제를 해결할 수 있도록 도와야 할 것이다. 나아가 적절한 감정 반응의 모델을 보여줄 수 있어야 한다.현재 우리나라 학교에서의 감정교육 여건은 무척 나쁘다고 볼 수 있다. 학급 당 학생 수는 여전히 많고 입시 위주의 지식 전달과 암기를 강조함으로써 서로간의 교감의 기회가 적은 것을 뿐 아니라, 수업시간에 감정교육을 활용하다가 진도에 쫓기거나 자칫 수업분위기가 산만해질 우려도 있다. 사실 이런 이유로 감정교육을 포기하거나 교육과정에서 제외시키는 사례도 적지 않을 것이다. 그러나 감정교육이 우리 교육에서 발견되는 많은 문제점들을 보완해줄 수 있는 장점들을 더 많이 가지고 있기에, 적은 시간이라도 감정교육의 방법으로 교육을 실천하는 노력을 멈춰서는 안 될 것이다. For a long time, emotion has been treated lightly because of rational ethics viewpoint. So pursuing moral knowledge and rational thought human being was brought, but it has revealed the limits cultivating human that expressing suitably hisher emotion, interesting in other people and community and practicing moral knowledge. However living morally get to be acting with moral knowledge, judgement and emotion. When we think and judge moral problems, mostly emotion works together. When a personal intelligence build up category about a thing or event, the category accompanies liking or disliking emotion. Heshe has a positive emotion as the thing that is helping for pursuing purpose. On contrary, heshe has a negative sentiment for the thing which is not useful. That is because emotion, intelligence and action are not wholly separated, they are connected with a what kind of form.Generally the man who expose the feature of insensibility, indifference, and aberration has the lack of emotion. Heshe not only suffer from worthlessness, alienation, wandering, impersonality etc. but also cannot live in harmony with others. A man who has a mature emotion can feel morally a facing matter sensitively. So heshe understands others'''''''''''''''' difficulty and pain, consolate and help them. Also it is able to form a desirable human relation. Accordingly in order to raise the sensibility about emotion which includes all kind of social act, students have to recognize others'''''''''''''''' emotion and express appropriately. They need to take a chance that promote and habituate moral emotion such as self-respect, sympathy, self-control, compassion and guilty conscience. Then what is remained is how to teach.There are two methods recognizing and expressing emotion-verbal method of speaking and writing and nonverbal method of a look, gesture, action and appearance etc. And in moral education there are three types of teaching-learning as styles of studying of students. The first is the type of impression which is useful to caring others, arousing sympathy, feeling moral emotion. The second is the type of thought which is useful to cultivating the power of moral judgement from the moral deductive process. The last is the type of experience that have morality from a direct acting experience of basic living habits, etiquette, serving to community, role-playing.When these emotional communication methods and teaching-learning types of moral education is classified by the form of studying action, there are experience, listening, talking, reading and writing. These teaching -learning types have meanings such as each peculiar action and emotion education. First of all, they imply meanings of experience, doing, being and feeling etc. Students realize the moral value through direct and wholly contacting to objects, recognize others'''''''''''''''' situation and feel joy, anger, sorrow, and pleasure.Doing promote a strong bond each other and affinity to community through varied conduct such as role-playing, simulation, playing-studying, serving to society and field studying etc.Studying method of the type of listening has listening sounds, listening moral stories using literature and praiseworthy examples. And also there is an auditory media studying method using radio and recorder.Active listening which is to be condition of these activities can have emotional recognizing of objects and reflection of self-emotion. It is the process that share emotion and meaning with objects. So as we have a plan to apply the content of emotion cognition, we can expect the effect of emotion change to speaker, reflection of listening attitude, distortion cause verification and removal of listening.Talking is action that a speaker express hisher thought and emotion with verbal language and gesture to a listener. As listening the others'''''''''''''''' talking and judging it, it gets to satisfy a personal inner motivation. The studying activity of talking is concerned talking moral experience, story-relaying, brain storming, speech in limited time, discussion and inquiry and answer method etc. As we design a class model applying emotional expression, can give a chance expressing naturally and directly hisher emotion to a teacher. And I expect for students to study expressing their emotion naturally in this process.The objects of reading can expand painting, picture, monitor of computer-TV, scene of film etc. into the media of print(book, press), the media of image(movie, TV), the media of internet. Acting of reading can be able to imagine plentifully and variously as a process weaving mean from the text with the background and experience of a reader. to expand experience and realizing about the world and self, to cultivate understanding of emotion condition as feel compassion and sympathy emotion of the object. Furthermore the reader is given the attitude and motivation administrating such a life through gaining desirable model from reading. Specially it is effective that habituate moral emotion. Because the modeling from reading is to be easy to exposing repeatedly of moral emotion situation. On this, the class plan is designed as contents about habituating moral emotion.Teaching-studying of writing type which works with brain writing, mind map, emotion diary writing, exchanging mails, writing journal, impression of a book, relaying stories etc. helps to express purely students'''''''''''''''' emotion. And it gets to have a sense of reality to promote a self-understanding from the inner dialogue, to improve the power of solving problems. And first of all because it dissolves anxiety, stress, frustration through the purification of the emotion and relief the collision of the sentiment, when a class for the feeling control is designed, it is effective.The management of the emotion education is formed of sense, understanding, experience, playing, human relation and learner-centered system. But the quality of a teacher is very important matter because a teacher''''''''''''''''s significant look, gesture influence the emotion of student also. Teachers have to conduce the positive atmosphere to set at ease the emotion of students, to make the allowed air to express emotion freely, to control the negative emotion, to help students in order to solve their problems themselves through changing their faith. Moreover they have to show the proper model of emotional response.Now I think that our emotion education condition in school is not good. There are many students per class. It remains the situation to prepare for an entrance examination, to deliver simply knowledge, to emphasize memory work as before. So the class has not only little chance for mutual response but distract atmosphere as we imply emotional education method because of speedy process of classwork. As a matter of fact, because of these reasons it is likely to abandon emotional education or exclude it from educational processes. However emotional education has much merits to complete problems from our education system. So we have to make efforts to practice a method of emotion education.

서비스 산업의 효과를 증강시키기 위한 그룹 감성 기반의 다감각 자극 기술에 대한 연구

김영주 상명대학교 일반대학원 2018 국내박사

Emotion plays an important role in enhancing interpersonal relationships and determine groups behavior. Emotion has been reported to influence on not only decision making and work efficiency but also a predictor of user behavior. Individual emotion has been studied for developing emotion recognition. Although group emotion has observed to be important of applying industry service and marketing, individual emotion has attempted to be studied for recognition and still has not been enough to describe public emotion behavior. Therefore, group emotion is demanding to be studied for recognition and application of industry. Group emotion is defined according to both the intensity of relationship and individual level of emotion. A leader's emotion of the group rather than a collection of individual emotion has been observed to be main contributor of determining a group emotion. Ripple effect describes mechanism of emotion contagion related to group emotion and unconscious mimicking emotional response each other including body movement, facial expression, and verbal expression and other physiological response. Therefore, response synchronization has been studied to determine group emotion in this study. Body movement in the group has been analyzed according to synchronization to a leader's and the group emotion has been classified into four emotion domain in Russell's emotion model. The service industry has shown much interest on customers’emotion as they are a significant factor in purchase intention or service experience. To understand the needs of customers, group emotion should be researched as customers could experience service or product differently depending on the quality of group emotion. Multi-sensory stimulation also plays an important role in how we feel and behave. For example, research on cure for learning disabilities and dementia has applied multi-sensory stimulation in recently years. Also, the service industry has invested to develop multi-sensory stimulation such as fragrance, mood lights, background music, and physical architecture to induce consumers’ positive emotions. Sensory marketing enhancing customer's interest, satisfaction and motivation according to multi-sensory stimulation has been developed by understanding the group emotion in the service domains. For verification and application of group emotion stimulated by multi-sensory to enhancement of achieving business goal. The three service domains were selected in this study based on the service process matrix: education, welfare, and marketing. First, the service effect in the kindergarten was to enhance children's attention in the class through presenting the multi-sensory stimulation. Second, the service effect in the welfare services was to improve mental health with increased physical activity levels caused by multi-sensory stimulation during the Tai Chi class. Lastly, the marketing services was to increase customer satisfaction for increasing sales in the coffee shop when presenting the multi-sensory stimulation. Ten children aged from 5 to 7 were exposed to the multi-sensory stimulation in the kindergarten class and their body movement were measured through camera. Their body movement was analyzed to verify the effects of multi-sensory stimulation on the education service domain. Nine elderly people aged from 60 to 70 were asked to participate a Tai Chi class at a welfare center. They were also exposed to multi-sensory stimulation and their body movement was analyzed to verify the effect of multi-sensory stimulation in the welfare service domain. 234 customers aged form 20 to 40 were exposed to multi-sensory stimulation which intended to induce certain emotion in specific time. Participants in the three service domains were also asked to compare a multi-sensory stimulation and a non-stimulus condition to identify enhancement of group emotion through subjective assessment. The Wilcoxon signed-rank test was performed to find the statistical significance of the mean difference (p <.05). Service satisfaction and body movement increased significantly when participants experience the multi-sensory stimulation. The amount of movement was larger when participants felt pleasant-relaxation than in pleasure-arousal emotion by the multi-sensory stimulation. On the other hand, the frequency power of movement was larger in when participants felt pleasant-relaxation. These results showed that group emotion was enhanced by the multi-sensory stimulation. In conclusion, this study proposed new method of recognizing group emotion according to measurement and analysis of body movement in the group. Group emotion has been modulated by multi-sensory stimulation for achieving service business goals effectively. Multi-sensory stimulation has been observed to improve group emotion and its proper design has accelerated customer's experience for benefit of service industry. The methods and results in this study will contribute the development of designing sensory marketing and service marketing. key words: Group emotion, Multi-sensory stimulation, Body-movement, Augmenting emotion

정서 변화가능성 신념(EMB)이 정서조절방략과 지각된 정서조절성공에 미치는 영향

정예슬 전북대학교 일반대학원 2021 국내석사

This study investigated how Emotion Malleability Beliefs(EMB) have an adaptive and maladaptive effect on emotion regulation strategies by manipulating the belief that emotions are fixed or malleable. Two experimental groups were randomly assigned and manipulated with the belief that emotions are fixed or malleable. Both groups were asked to recall autobiographical negative memory and then measured emotional regulation strategies, perceived emotional1[- regulation success and self-criticism. Participants in the emotion malleability condition reported increased uses in the ‘passive thinking’ and decreased uses in the ‘negative thinking’ strategy after manipulated with the emotion malleability belief, whereas the fixed emotion condition showed decreased uses in overall emotional regulation strategies except ‘blaming others’ strategy. The emotion malleability group (compared to the fixed emotion group) reported higher scores on perceived emotional regulation success. The fixed emotion group (compared to the emotion malleability group) reported engaging more in ‘negative thinking' and 'blaming others’ tactics. These results suggest emotion malleability beliefs have various effects on emotion regulation strategies. The implication of this work is to find the causal relationship between emotion malleability beliefs and emotion regulation strategies in both positive and negative aspects.

Emotional speech analysis: database, emotion recognition, and synthesis

변성우 상명대학교 일반대학원 2021 국내박사

Recently, the interaction between humans and computers is actively changing into a bidirectional interface, and a better understanding of human emotions is needed, which could improve human machine interaction systems. The goal of this human interface is to extract and recognize the emotional state of individuals accurately and to provide personalized media according to a user’s emotional state. The most important issue in the speech-emotion recognition system is the effective parallel use of the extraction of proper speech-signal features and an appropriate classification engine. To accurately recognize and analyze emotions from speech, it is also important to construct a superior speech database. The key to these studies is to guarantee verified, reliable expressions of emotion. Therefore, statistical evaluation of whether speech data involves emotions is needed. In this work, we constructed a Korean emotional speech database for speech emotion analysis, and proposed a feature combination that can improve emotion recognition performance, using an recurrent neural network model. Furthermore, we propose an emotional speech synthesizer constructed by embedding not only speaking styles, but also emotion styles. To do this, the database was recorded using three different methods. The emotion categories involved were ("Neutrality", "Happiness", "Anger", "Sadness", "Excitement", and "Fear") or ("Neutrality", "Happiness", "Anger", and "Sadness"), depending upon the methods used. To investigate the acoustic features, which can reflect distinct momentary changes in emotional expression, we extracted F0, MFCC, chroma, spectral features, harmonic features, and others. Statistical analysis was performed to select an optimal combination of acoustic features that affect the emotion from speech. We used a recurrent neural network based model to classify emotions from speech. We also extended speaker embedding to multi-condition embedding by adding emotion embedding in Tacotron, so that the synthesizer can generate emotional speech. The model was trained on the emotional style of the speakers, and the use of multiple speakers means a lack of emotional state in one speaker's speech data can be complemented by data from other speakers. To evaluate the performance of the proposed method, A five-scale MOS test was carried out using five subjects.

End-to-end multimodal fusion-conformerBERT model for emotion recognition

이상현 Graduate School, Korea University 2022 국내박사

Emotion recognition is a communication method that helps understand humans and build empathy and intimacy. An intuitive method to achieve natural, intelligent human-computer interaction is the intellectual ability of machines to understand and empathize with human emotional states. However, the emotional state of the speaker is very complex and changes dynamically depending on contextual language expression or nonverbal contexts such as speech and facial expressions. Although most previous studies performed emotion recognition using a unimodal, it is still difficult to understand human emotions. This dissertation aims to improve the performance of emotion recognition through multimodal fusion to integrate all audio, visual and text input for human-computer interaction. Before describing the proposed method, previously studied approaches to emotion recognition and research issues are reviewed. Then, the nonverbal audio and visual build a unimodal by comparing handcraft features and deep learning features. Nonverbal expressions are important clues to understanding emotions, and these sounds and facial expressions contain more detailed information than abstract words. Therefore, extracting differentiated audio and visual features to improve multimodal performance is one of the main tasks of emotion recognition research. This dissertation conducts comparative experiments by selecting handcraft features and deep learning features used in previous studies. Convolution-augmented Transformer (Conformer) encoder allows audio and visual unimodal to efficiently capture both local feature and global feature contextual information, which aids in emotion recognition. Next, a novel end-to-end multimodal method for emotion recognition is proposed. Understanding complex human emotions requires modeling fusion approaches for intra-modal interactions across text, visual and audio modalities. However, each modality contains positive and negative information. For example, in a video, there are frames in which emotion is not prominent. Negative information corresponds to noise between each modality, and such information should be blocked. This dissertation proposes a Positive Sample Filter Fusion for Cross-modal (PSF2C) module to construct all pairwise similarity maps between each modality and to obtain paired features with high similarity. In addition, the proposed model has a Temporal Weight Fusion (TWF) module to give temporal weights to better utilize temporal correlations. Especially, text modality effectively distills knowledge using pre-trained Bidirectional Encoder Representation from Transformer (BERT) with self-supervised learning. Ablation analysis of the model proposed in this dissertation shows that audio and visual components contribute significantly to the recognition results than text using a single BERT. In addition, the performance shows that the fusion process of the PSF2C module that aggregates positive information and the TWF module that assigns time weights is effective. These positive modalities of audio, visual, and text suggest that they contain highly complementary information for sentiment analysis. The method in this dissertation achieves state-of-the-art performance on CMU Multimodal Opinion Sentiment Intensity (CMU-MOSI) and Interactive Emotional Dyadic Motion Capture (IEMOCAP) datasets. 감정 인식은 인간을 이해하고 공감과 친밀감을 형성하는 데 도움이 되는 의사소통 방법이다. 로봇은 자연스러운 인간의 감정 상태를 이해하기 위해 human-to-machine 상호작용에 대한 지능적인 직관 능력을 습득해야 한다. 그러나, 문맥적 언어 표현과 비언어적 표현에 따라 동적 변화로 인해 화자의 감정 상태는 매우 복잡하다. 대부분 기존 감정 인식 연구는 단일 modality만을 고려했기 때문에 다차원의 인간의 감정을 이해하는 것은 여전히 어려운 일이다. 본 논문은 감정 인식을 향상시키기 위해 오디오, 시각, 텍스트를 적용하여 multimodal 융합 시스템 구현을 목표로 한다. 또한, multimodal 성능을 향상시키기 위해 차별화된 시청각 특징을 추출하는 것은 감정 인식 연구의 주요 과제 중 하나이며 비언어적 표현인 시청각 신호는 감정을 이해하는 데 중요한 단서이다. 추가적으로, 시청각 정보는 단어 조합으로 구성된 텍스트 정보 보다 더 자세한 정보를 담고 있다. 따라서, 효과적인 감정 인식 비언어적 특징을 추출하기 위해 먼저 시청각의 대표적인 handcraft 특징과 deep learning 특징을 비교 실험을 진행한다. 특징 비교 실험은 글로벌 특징과 로컬 특징을 캡처할 수 있는 Convolution-augmented Transformer (Conformer) 인코더를 제안하여 다른 시퀀스 모델인 Recurrent Neural Networks (RNNs)과 Transformer로 비교 분석한다. 마지막으로, 본 논문에서는 Conformer 모듈에서 추출한 시청각 표현과 Bidirectional Encoder Representation from Transformer (BERT) 모델의 텍스트 표현을 결합한 End-to-End 기반의 새로운 Fusion-ConformerBERT를 제안한다. 또한, 각 modality의 representation 정보는 훈련에 영향을 미치는 프레임과 특징 정보가 존재한다. 이때, 프레임에서 강인한 특징은 positive 정보, 그렇지 않은 약한 특징은 negative 정보로 가정한다. 이러한 negative 정보는 감정 인식 훈련 간의 노이즈에 해당하며 negative 영향을 가진 정보는 차단해야 한다. 따라서, Fusion-ConformerBERT는 Positive Sample Filter Fusion for Cross-modal (PSF2C) 모듈을 제안하여 각 modality 간의 모든 쌍 similarity map을 구성하고 유사성이 낮은 정보인 negative는 차단하고 높은 쌍의 특징인 positive 정보를 필터링한다. 또한, Temporal Weight Fusion (TWF) 모듈을 제안하여 시간적 상관관계에 따른 시간 가중치를 부여한다. Fusion-ConformerBERT에 제안된 텍스트 모델은 Self-supervised learning으로 사전 훈련된 BERT 모델을 사용함으로써 소규모 감정 데이터에 대한 overfitting 문제를 해결한다. 추가적으로, 본 논문의 다양한 ablation 분석을 진행하며 modality 간의 융합에 대한 영향을 비교한다. 나아가, 제안된 Fusion-ConformerBERT에서 positive 정보를 집계하는 PSF2C와 시간 가중치를 부여하는 TWF 모듈의 융합 프로세스가 효과적인 것으로 성능을 보여준다. 제안된 모델에서 오디오, 시각적, 텍스트의 이러한 긍정적인 modality은 감성 분석을 위한 매우 보완적인 정보를 포함하고 있음을 시사한다. 실험은 CMU Multimodal Opinion Sentiment Intensity (CMU-MOSI)와 Interactive Emotional Dyadic Motion Capture (IMEOCAP) 데이터 셋을 사용하며 제안된 Fusion-ConformerBERT은 실험에서 최신 의 성능을 달성한다.

THE ROLE OF EMOTION IN THE RELATIONSHIP BETWEEN CUSTOMERS AND CONTACT PERSONNEL

이상현 Purdue University 2004 해외박사

Through buyer-seller interaction, salespeople conceivably will influence how customers feel when shopping; in essence, salespersons are likely to have an impact on customer’s emotions. Although previous work has considered the effect store environment has on customer emotions, no extant research has examined how customer emotions emerge after interacting with salespeople or what the outcomes of those emotions are. The purpose of this study is to explain the association between salesperson attributes and customer emotions in buying situations that entail substantial customer/ salesperson interaction. Further, it examined how emotions affect a customer’s evaluation of relationship satisfaction and whether this construct affects purchase intention. A mail survey was conducted to collect data in the customer-car salesperson relationship context. Among the 5,000 mailed questionnaires, a total of 322 useable responses were obtained representing a response rate of 6.5 %. The structural equation model was used to test the specific hypotheses. This study found several factors affecting emotion constructs and those construct’s effect on the relationship satisfaction and further intention. The major findings of this study can be summarized as follows. 1) There is a positive relationship between selected characteristics of salespeople (trustworthiness, empathy, and professional appearance) and customers’ positive emotion. 2) There is a negative association between certain salesperson attributes (trustworthiness, empathy, and accessibility) and customers’ negative emotion. 3) Customers are more satisfied with their relationship with the salesperson when they experience a higher level of positive emotion. 4) When customers experience higher negative emotion, customers are less satisfied with the relationship. 5) Customers are more likely to maintain their relationship with the salesperson when they are more satisfied with that relationship. Findings from this study provide insights for managers about what must be done to attract and retain customers. As customers interact with sales personnel, fostering favorable customer emotions can conceivably lead to satisfied customers and build ongoing relationship.