• KNOM Review
• /
• 제24권2호
• /
• pp.35-47
• /
• 2021

끊임없는 경쟁과 발전을 요구하는 현대사회에는 다양한 스트레스가 존재하고 그 스트레스는 많은 경우 인물의 표정과 언어로 표현된다. 따라서 스트레스는 표정과 언어 분석을 통하여 측정할 수 있으며, 이를 효율적으로 관리하기 위한 시스템 개발이 필요하다. 본 연구에서는 표정과 언어 감성 분석을 통하여 스트레스를 측정할 수 있는 시스템을 제안한다. 인물의 표정과 언어 감성을 분석하여 주요 감성값 기준으로 스트레스 지수를 도출하고 표정과 언어의 일치성을 기준으로 통합 스트레스 지수를 도출하는 스트레스 측정 방법을 제안한다. 스트레스 측정기법을 통한 정량화, 일반화는 다수의 연구자가 객관적인 기준으로 스트레스 지수를 평가할 수 있도록 할 수 있다.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.215-220
• /
• 2022

Emotion recognition is one of the most important and challenging areas of computer vision. Nowadays, many studies on emotion recognition were conducted and the performance of models is also improving. but, more research is needed on emotion recognition and sentiment analysis of video viewers. In this paper, we propose an emotion analysis system the includes a sentiment analysis model and an interest prediction model. We analyzed the emotional patterns of people watching popular and unpopular videos and predicted the level of interest using the emotion analysis system. Experimental results showed that certain emotions were strongly related to the popularity of videos and the interest prediction model had high accuracy in predicting the level of interest.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권4호
• /
• pp.153-160
• /
• 2021

IT 기술 발달에 따른 영상 콘텐츠 생산과 소비가 증가함에 따라 영상 콘텐츠를 통한 제품 리뷰 정보로 구매의사 결정이 빈번해졌다. 따라서, 리뷰 영상에 대한 신뢰성을 평가할 필요가 있다. 본 연구에서는 제품 리뷰 영상을 얼굴 표정 분석과 텍스트 마이닝을 통해 리뷰어의 표정과 음성을 분석하여 영상의 신뢰도를 분석한다. 영상 내 인물 표정의 감성 값을 추출하는 알고리즘을 활용하여 비언어 감성을 정량화하고, 유의미한 감정 변화 구간을 추출한다. 유의미한 감정 변화 구간의 리뷰어 음성을 텍스트화하여 표준어 및 비표준어 감성 사전 활용을 통해 긍정과 부정으로 리뷰에 대한 언어 감성 분석 후 수치화 한다. 비언어 감성 분석과 언어 감성 분석의 결과를 통합하여 일치 여부에 따라 신뢰도를 도출한다. 본 연구를 통해 영상 콘텐츠의 신뢰성 평가 방법을 제시한다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제14권1호
• /
• pp.142-151
• /
• 2022

In this paper, a model combined with explanatory artificial intelligence (xAI) models was presented to secure the reliability of machine learning-based sentiment analysis and prediction. The applicability of the proposed model was tested and described using the IMDB dataset. This approach has an advantage in that it can explain how the data affects the prediction results of the model from various perspectives. In various applications of sentiment analysis such as recommendation system, emotion analysis through facial expression recognition, and opinion analysis, it is possible to gain trust from users of the system by presenting more specific and evidence-based analysis results to users.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.9-12
• /
• 2021

현대 사회에서 극심한 스트레스로 고통을 호소하는 사람들이 많아짐에 따라 효과적인 스트레스 측정 시스템의 필요성이 대두되었다. 본 연구에서는 영상 속 인물의 표정과 음성 감성 분석을 통한 통합 스트레스 분석 시스템을 제안한다. 영상 속 인물의 표정과 음성 감성 분석 후 각 감성값에서 스트레스 지수를 도출하고 정량화한다. 표정과 음성 스트레스 지수로 도출된 통합 스트레스 지수가 높을수록 스트레스 강도가 높음을 증명하였다.

• 치위생과학회지
• /
• 제7권2호
• /
• pp.89-96
• /
• 2007

The purpose of this study was to examine the relationship between the self-expression level of dental hygiene students related to communicative competence and their stress during clinical practice and what affected their stress. The subjects in this study were 125 dental hygiene students in W college, on whom a survey was conducted from September 18 through 30, 2006. After the collected data were analyzed with SPSS WIN 10.0 program, the following findings were acquired: 1. When a factor analysis was made to evaluate the self-expression of the students, there appeared three different categories of self-expression: voice/content, facial expression/attitude and sentiment. The three made a 58.1% prediction of their self-expression. As for overall reliability, they turned out highly reliable(Cronbach'a = .881). 2. The dental hygiene students got a mean of 3.58 out of possible five points in self-expression, which indicated that they expressed themselves relatively well. Concerning connections between their general characteristics and self-expression level, those who were inactive during clinical practice got a mean of 3.28, whereas the others who were active got a mean of 3.85. It implied that those who took a more active attitude to clinical practice expressed themselves better(p < .01). The person with whom they found it hard to get along made a statistically significant difference to their self-expression(p < .05). The students who didn't fare well with dental hygienists got the best score(3.70). The second best group(3.53) didn't get along with dentists, followed by assistant nurses(3.46) and patients/caregivers(3.31). As for the impact of the field of dream job, the students who hoped to work or study overseas(4.21) excelled in self-expression those who wanted to be hired in a general hospital, to go onto a school of higher grade and to work in a public dental clinic(p < .05). Among the general characteristics, satisfaction level with major, health status and motivation of choosing dental hygiene made no statistically significant differences to their self-expression. 3. Regarding relations between self-expression level and stress about clinical practice, those who didn't express themselves properly in terms of sentiment scored higher in stress level(3.65). Their stress was statistically significantly different according to self-expression level (p < .05). 4. As for the influence of self-expression and general characteristics on stress with clinical practice, sentiment was selected from among the self-expression categories as a decisive factor to affect stress. Their stress varied statistically significantly with that(p < .05). In contrast, their demographic variables made no statistically significant difference to that, which made a 79.2% prediction of it.