• Journal of Korean Library and Information Science Society
• /
• v.48 no.1
• /
• pp.161-189
• /
• 2017

The purpose of this study is to describe the experience of visually impaired academic researchers' use of scholarly contents and to explore intrinsic nature of the experience. In-depth interview was conducted with a total number of twelve visually impaired academic researchers and the data were analyzed using Colaizzi's phenomenological research method. A total of 107 significant statements were extracted, divided into 44 themes and 12 theme clusters. The statements were then classified into four categories. The 'scholarly contents acquisition and use' category has to do with difficulties that these experience when negotiating with internet sites with poor web accessibility and full-text availability. The 'changes in perception and emotions' category deals with transitions in perception and mood experienced by visually impaired academic researchers' over time. The 'relationships with support personnel' category includes issues related with the difficulty of securing support person, support person's inadequate level of competence, and establishing/sustaining personal relationships. Finally, the 'improvement requirements' category includes issues that these researchers want resolved with regard to contents acquisition and use.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.700-702
• /
• 2022

코로나 바이러스-19 감염증 상황이 지속됨에 따라 영유아 비대면 상담이 증가하였다. 비대면이라는 제한된 환경에서, 보다 정확한 상담을 위해 영유아의 감정을 예측하는 보조도구로써 CNN 학습모델을 이용한 감정분석 결과를 활용할 수 있다. 하지만, 대부분의 감정분석 CNN 모델은 성인 데이터를 위주로 학습이 진행되므로 영유아의 감정인식률은 상대적으로 낮다. 본 논문에서는 영유아와 청소년 데이터의 감정분석 정확도 차이의 원인을 XAI 기법 중 하나인 LIME을 사용해 시각화하여 분석하고, 분석 결과를 근거로 영유아 데이터에 대한 감정인식 성능을 향상시킬 수 있는 방법을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.55-58
• /
• 2024

최근 각 기업의 AI 면접시스템 도입이 증가하고 있으며, AI 면접에 대한 실효성 논란 또한 많은 상황이다. 본 논문에서는 AI 면접 과정에서 지원자를 평가하는 방식을 시각, 음성, 자연어처리 3영역에서 구현함으로써, 면접 지원자를 다방면으로 분석 방법론의 적절성에 대해 평가하고자 한다. 첫째, 시각적 측면에서, 면접 지원자의 감정을 인식하기 위해, 합성곱 신경망(CNN) 기법을 활용해, 지원자 얼굴에서 6가지 감정을 인식했으며, 지원자가 카메라를 응시하고 있는지를 시계열로 도출하였다. 이를 통해 지원자가 면접에 임하는 태도와 특히 얼굴에서 드러나는 감정을 분석하는 데 주력했다. 둘째, 시각적 효과만으로 면접자의 태도를 파악하는 데 한계가 있기 때문에, 지원자 음성을 주파수로 환산해 특성을 추출하고, Bidirectional LSTM을 활용해 훈련해 지원자 음성에 따른 6가지 감정을 추출했다. 셋째, 지원자의 발언 내용과 관련해 맥락적 의미를 파악해 지원자의 상태를 파악하기 위해, 음성을 STT(Speech-to-Text) 기법을 이용하여 텍스트로 변환하고, 사용 단어의 빈도를 분석하여 지원자의 언어 습관을 파악했다. 이와 함께, 지원자의 발언 내용에 대한 감정 분석을 위해 KoBERT 모델을 적용했으며, 지원자의 성격, 태도, 직무에 대한 이해도를 파악하기 위해 객관적인 평가지표를 제작하여 적용했다. 논문의 분석 결과 AI 면접의 다면적 평가시스템의 적절성과 관련해, 시각화 부분에서는 상당 부분 정확도가 객관적으로 입증되었다고 판단된다. 음성에서 감정분석 분야는 면접자가 제한된 시간에 모든 유형의 감정을 드러내지 않고, 또 유사한 톤의 말이 진행되다 보니 특정 감정을 나타내는 주파수가 다소 집중되는 현상이 나타났다. 마지막으로 자연어처리 영역은 면접자의 발언에서 나오는 말투, 특정 단어의 빈도수를 넘어, 전체적인 맥락과 느낌을 이해할 수 있는 자연어처리 분석모델의 필요성이 더욱 커졌음을 판단했다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.152-157
• /
• 2008

The human uses the optic plentifully that an emotion the human knowledge. by the light it perceives the object and we live middle of color together. The color is close relation in our life. against a color from in many the optic information it is sensitive and it accepts. Therefore if expresses a emotion with color, human knowledge there is a probably of accepting intuition. The purpose of this dissertation to The emotion expression which uses a hue and the hue which leads the relationship research of emotion. In emotional circle of Plutchik, It selects the emotion where becomes the basic and the hue which similar has an impression and feature from the Harris of Moses Harris it searches emotion to use a hue circle with the method which it makes the emotion it expresses. Examines satisfaction of hue and emotion for emotion expression. The magnetic pole of emotion continuously comes in, There must be it will be able to confirm change of many emotion as a real-time. The shooting game the magnetic pole of multi emotion continuously comes in, Because it will be able to confirm the change of emotion as a real-time, suitable the applies for the research of emotion expression Consequently, The application it tried with character hue of shooting game.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.613-617
• /
• 2021

According to the growth of the service industry, stresses from emotional labor workers have been emerging as a social problem, thereby so-called the Emotional Labor Protection Act was implemented in 2018. However, insufficient substantial protection systems for emotional workers emphasizes the necessity of a digital stress management system. Thus, in this paper, we suggest a stress detection system for customer service representatives based on deep learning facial expression recognition. This system consists of a real-time face detection module, an emotion classification FER module that deep-learned big data including Korean emotion images, and a monitoring module that only visualizes stress levels. We designed the system to aim to monitor stress and prevent mental illness in emotional workers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.559-561
• /
• 2022

인공지능 시대에 들어서면서 개인 맞춤형 환경을 제공하기 위하여 사람의 감정을 인식하고 교감하는 기술이 많이 발전되고 있다. 사람의 감정을 인식하는 방법으로는 얼굴, 음성, 신체 동작, 생체 신호 등이 있지만 이 중 가장 직관적이면서도 쉽게 접할 수 있는 것은 표정이다. 따라서, 본 논문에서는 정확도 높은 얼굴 감정 식별을 위해서 Convolution Block Attention Module(CBAM)의 각 Gate와 Residual Block, Skip Connection을 이용한 Identity- CBAM Module을 제안한다. CBAM의 각 Gate와 Residual Block을 이용하여 각각의 표정에 대한 핵심 특징 정보들을 강조하여 Context 한 모델로 변화시켜주는 효과를 가지게 하였으며 Skip-Connection을 이용하여 기울기 소실 및 폭발에 강인하게 해주는 모듈을 제안한다. AI-HUB의 한국인 감정 인식을 위한 복합 영상 데이터 세트를 이용하여 총 6개의 클래스로 구분하였으며, F1-Score, Accuracy 기준으로 Identity-CBAM 모듈을 적용하였을 때 Vanilla ResNet50, ResNet101 대비 F1-Score 0.4~2.7%, Accuracy 0.18~2.03%의 성능 향상을 달성하였다. 또한, Guided Backpropagation과 Guided GradCam을 통해 시각화하였을 때 중요 특징점들을 더 세밀하게 표현하는 것을 확인하였다. 결과적으로 이미지 내 표정 분류 Task에서 Vanilla ResNet50, ResNet101을 사용하는 것보다 Identity-CBAM Module을 함께 사용하는 것이 더 적합함을 입증하였다.

• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.121-138
• /
• 2017

As information users seek multimedia with a wide variety of information needs, information environments for multimedia have been developed drastically. More specifically, as seeking multimedia with emotional access points has been popular, the needs for indexing in terms of abstract concepts including emotions have grown. This study aims to analyze the index terms extracted from Getty Image Bank. Five basic emotion terms, which are sadness, love, horror, happiness, anger, were used when collected the indexing terms. A total 22,675 index terms were used for this study. The data are three sets; entire emotion, positive emotion, and negative emotion. For these three data sets, co-word occurrence matrices were created and visualized in weighted network with PNNC clusters. The entire emotion network demonstrates three clusters and 20 sub-clusters. On the other hand, positive emotion network and negative emotion network show 10 clusters, respectively. The results point out three elements for next generation of multimedia retrieval: (1) the analysis on index terms for emotions shown in people on image, (2) the relationship between connotative term and denotative term and possibility for inferring connotative terms from denotative terms using the relationship, and (3) the significance of thesaurus on connotative term in order to expand related terms or synonyms for better access points.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.3
• /
• pp.285-304
• /
• 2021

The study has a purpose of understanding the factors that affect the oranizational commitment of the employees working in the libraries for visually impaired. To do this, the study chose personal background, emotional labor, role, job characteristics, organizational culture and organizational justice and attempted to find out how these factors affect the oranizational commitment. As a research method, mixed study method was used where quantitative analysis was complemented by qualitative analysis. For quantitative analysis, statistical analysis was conducted using the retrieved questionnaires. For qualitative analysis, the researcher had a one-on-one talk with the experts and employees who want to participate using an interview note was recomposed based on the survey responses. In the study results, emotional labor, job characteristics, organizational culture and organizational justice was proven to have influence on job engagement. To improve the job engagement, autonomy should be guaranteed by minimizing the organizational intervention to the assigned works and expanding the discretionary power. Furthermore, intensive management of the employees' emotional labor and fair process regarding the work performance is highly important.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.685-688
• /
• 2022

본 논문은 자연어 처리와 Face Detection 기술을 활용하여 사용자의 현재 감정 상태에 따른 디지털 미디어 아트를 구현하는 방법을 기술한다. 사용자의 현재 표정과 감정을 분석하고, 감정에 따라 다양한 시각 효과 및 다른 성격의 텍스트를 화면에 송출하는 방식으로 사용자와 상호작용한다.

• KIISE Transactions on Computing Practices
• /
• v.22 no.5
• /
• pp.209-217
• /
• 2016

As smartphone usage increases, the number of consumers who refer to review data of e-commercial products using web sites and SNS is also explosively multiplying. However, reading review data using traditional websites and SNS is time consuming. Also, it is impossible for consumers to read all the reviews. Therefore, a system that collects review data of products and conducts sentiment word analysis of the review is required to provide useful information. The majority of systems that provide such information inadequately reflect the properties of the product. In this study, we described a system that provides analysis and evaluation of e-commerce products through review sentiment words as reflected properties of the product. Furthermore, the system enables consumers to access processed information about reviews quickly and in visual format.