• 스마트미디어저널
• /
• 제13권6호
• /
• pp.35-43
• /
• 2024

During the post-pandemic period, the interest in foreign language learning surged, leading to increased usage of language-learning apps. With the rising demand for these apps, analyzing app reviews becomes essential, as they provide valuable insights into user experiences and suggestions for improvement. This research focuses on extracting insights into users' opinions, sentiments, and overall satisfaction from reviews of HelloTalk, one of the most renowned language-learning apps. We employed topic modeling and emotion analysis approaches to analyze reviews collected from the Google Play Store. Several experiments were conducted to evaluate the performance of sentiment classification models with different settings. In addition, we identified dominant emotions and topics within the app reviews using feature importance analysis. The experimental results show that the Random Forest model with topics and emotions outperforms other approaches in accuracy, recall, and F1 score. The findings reveal that topics emphasizing language learning and community interactions, as well as the use of language learning tools and the learning experience, are prominent. Moreover, the emotions of 'admiration' and 'annoyance' emerge as significant factors across all models. This research highlights that incorporating emotion scores into the model and utilizing a broader range of emotion labels enhances model performance.

• 경영과정보연구
• /
• 제25권
• /
• pp.243-273
• /
• 2008

A new research paradigm is emerging within organizational behavior, in both theory and empiricism, based on the increasing recognition of the importance of emotions to organizational life. This paper suggest that emotion intelligence play a moderate variables in relationship of emotion labor and emotional exhaustion. More specifically, it is proposed that emotional intelligence, the ability to understand and manage emotions in the employee self and others, contribute to effective emotions management in organizations. Four major aspects of emotion labor, appraisal and expression of emotion in oneself, appraisal and recognition of emotion in others, regulation of emotion in oneself and use of emotion to facilitate performance, are described. Also, the emotional intelligence are consists of four aspects, frequency of appropriate emotional display, attentiveness to required displayed rules, variety of emotions to be displayed and emotional dissonance. Then I propose how emotional intelligence contributes to of relations the emotion labor and emotional exhaustion. The purpose of this research is to investigate the impact of emotion labor to employee's emotional exhaustion to explore the moderating effects of the emotional intelligence between the emotion labor and emotional exhaustion. To complete the research the data were collected through a questionnaire from 147 employees from service company. After multi-hierarchical regression analysis, the outcomes of this study are the employee's emotional exhaustion are affected negatively by the three factors: major aspects of emotion labor, regulation of emotion in oneself, use of emotion to facilitate performance, make the moderation effect between emotion labor and emotional intelligence. These results indicate that instilling in others an appreciation of the importance of work activities: encouraging of true expression individual emotions, generating and maintaining well emotional climate and cooperation situations, and managing a meaningful environment for an organizational life.

• 아동학회지
• /
• 제35권6호
• /
• pp.65-78
• /
• 2014

The purpose of this study was to examine the relationships between preschooler's sex, effortful control, working memory, and emotion regulation. The moderating effect of sex in the influences of effortful control and working memory on emotion regulation was also investigated. Eighty-eight children from the ages of 3 to 5 years participated in this study. A working memory task of the Korean Wechsler Intelligence Scale for Children IV(K-WISC-IV; Kwak, Oh, & Kim, 2011) was administered to the children. Their parents completed a very short form of the Children's Behavior Questionnaire(Putnam & Rothbart, 2006) and Emotion Regulation Checklist(Shields & Cicchetti, 1997). The results indicated that effortful control significantly predicted emotion regulation. Additionally the moderating effect of sex on the relationship between working memory and emotion regulation was significant. Specifically, the influence of working memory on emotion regulation was significant only in boys, but not in girls. This result suggested that effortful control has an effect on emotion regulation in a stable manner whereas working memory has different effects on the influence of emotion regulation according to sex.

• ETRI Journal
• /
• 제37권6호
• /
• pp.1199-1210
• /
• 2015

Automatic emotion recognition based on facial cues, such as facial action units (AUs), has received huge attention in the last decade due to its wide variety of applications. Current computer-based automated two-phase facial emotion recognition procedures first detect AUs from input images and then infer target emotions from the detected AUs. However, more robust AU detection and AU-to-emotion mapping methods are required to deal with the error accumulation problem inherent in the multiphase scheme. Motivated by our key observation that a single AU detector does not perform equally well for all AUs, we propose a novel two-phase facial emotion recognition framework, where the presence of AUs is detected by group decisions of multiple AU detectors and a target emotion is inferred from the combined AU detection decisions. Our emotion recognition framework consists of three major components - multiple AU detection, AU detection fusion, and AU-to-emotion mapping. The experimental results on two real-world face databases demonstrate an improved performance over the previous two-phase method using a single AU detector in terms of both AU detection accuracy and correct emotion recognition rate.

• 한국의류산업학회지
• /
• 제7권2호
• /
• pp.162-168
• /
• 2005

The pictures of design details, such as collar type, sleeve type, skirt type, and skirt length, and color tone were evaluated by 377 persons in terms of sensibility and emotion. The data were analyzed by SPSS using ANOVA and Factor analysis to find out the most effective types of details on consumer's sensibility and emotion, and the methods were introduced. The most effective type is skirt length on sensibility and emotion of women's dress. The second type is different according to sensibility and emotion. Sensibility and emotion were composed of three concept: contemporary, mature and character. Sleeve type is second determinant to contemporary concept, and color tone is to mature concept, collar type is to character concept. 41 each details of design were positioned into 3D-concept space to connect each detail type and fashion concept of women's dress.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2003년도 추계종합학술대회 논문집
• /
• pp.447-453
• /
• 2003

Emotion을 이용한 컴퓨터 인공 지능, 그래픽, 로봇, 상호 작용 등 다양한 분야에 나타나고 있다. 이에 각 분야에 적용되어진 이론적 배경과, 적용의 특징, 기술 등을 본 글에서 다루고자 한다. 먼저 이론적 접근방식에 있어서는 심리학적 접근과, 사람의 감정 연구, Behavior-Bas설 접근, 생물 행동적 접근, 등이 있으며 이를 구현하기 위한 기술로는 학습 알고리즘, Neural Network 의 Self-Organizing Maps, Fuzzy Cognition Maps등이 있다. 적용 분야로는 Software Agent, Agent Robot과 Entrainment Robot 등이 있다. 본 글에서는 이들의 적용 사례들을 살펴보고 Emotion Architecture에 대해서 분석하고자 한다.

• 아동학회지
• /
• 제30권3호
• /
• pp.85-98
• /
• 2009

The purpose of this study was to examine the path model of child's sex, temperament, maternal parenting behavior, and child's emotion regulation on child social behaviors. The subjects were 286 elementary school children. Data were gathered through questionnaires reported by mothers and teachers. Path analysis revealed that (1) mother's overprotective or coercive parenting behaviors effected neither child's emotion regulation nor social behaviors (2) child's sex and activity level effected child's aggression both directly and indirectly through child's emotion regulation (3) child's 'activity level' and 'avoidance' temperament effected child's social withdrawal both directly and indirectly through child' emotion regulation. Findings underscore the role of emotion regulation as a mediator in predicting child aggression and social withdrawal.

• 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.

• 디지털융복합연구
• /
• 제14권3호
• /
• pp.269-278
• /
• 2016

본 연구는 보건계열 여대생들의 긍정정서, 부정정서 및 취업스트레스와 우울 간의 관련성을 파악하고 우울에 미치는 융복합적 영향을 분석하였다. 조사대상은 호남지역의 4개 대학에서 임의로 선정된 419명으로 하였으며, 자료수집은 2015년 3월 9일부터 4월 30일까지 자기기입식 설문지를 통해 이루어졌다. 우울은 긍정정서와 유의한 음의 상관관계를, 부정정서 및 취업스트레스와 유의한 양의 상관관계를 보였다. 위계적 다중회귀분석 결과, 자아존중감이 낮을수록, 주관적행복이 낮을수록, 절망감이 높을수록, A형행동유행이 높을수록, 성격스트레스가 높을수록 우울수준이 높았으며 이들의 설명력은 47.1%이었다. 공분산 구조분석 결과, 긍정정서, 부정정서 및 취업스트레스와 우울의 인과관계가 확인되었다. 이상의 연구결과를 볼 때, 보건계열 여대생들의 우울수준을 낮추기 위해서는 긍정정서를 높이고 부정정서 및 취업스트레스를 낮추는 노력이 필요하다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.150-154
• /
• 2006

In this paper, we apply several pattern recognition algorithms to emotion recognition system with speech signal and compare the results. Firstly, we need emotional speech databases. Also, speech features for emotion recognition are determined on the database analysis step. Secondly, recognition algorithms are applied to these speech features. The algorithms we try are artificial neural network, Bayesian learning, Principal Component Analysis, LBG algorithm. Thereafter, the performance gap of these methods is presented on the experiment result section.