• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2003.11a
• /
• pp.1261-1266
• /
• 2003

본 연구는 가상현실 극장에서 실시간 상호 작용 효과를 잘 수용할 수 있는 가상 현실 콘텐츠를 기획하고 그 시나리오를 구성하는 요소들과 인터랙션 기술 개발의 방향 수립을 위한 체계적인 사용성 평가 방법론을 제시하였다. 연구에 활용한 가상실험 콘텐츠는 Heritage Alive!로서 시나리오 구성에서 시스템 구성, 인터랙션 요소들을 사용자 참여를 통한 사용성 평가 수행을 실시하여 그 실용화 가능성과 발전 방향을 평가하였다. 사용성은 비디오를 통한 전체 관람 모습을 촬영, 관찰하여 몰입감과 콘텐츠를 연관지어 분석하였고, 사용자의 인터랙션을 컴퓨터 시스템의 로그 파일을 기록하여 입력 장치의 조작성과 과제에 대한 몰입감을 정량적으로 추출할 수 있었다. 그리고 설문지에 감성적인 측면을 질의함으로써 정성적인 평가 자료로 활용하였다.

• Science of Emotion and Sensibility
• /
• v.13 no.4
• /
• pp.659-668
• /
• 2010

This paper examines users' emotion from both 2D and 3D web interfaces and finds their differences. First, 77 words representing users' emotion were collected from the previous research papers. Second, a web survey system was developed using these collected words and prepared 3 web interface prototypes to collect users' emotions from different types of web interfaces. Finally, a web survey was conducted and its results were analyzed. The result of the survey showed that there were emotional words that were commonly experienced from either 2D or 3D web interfaces. However, it also showed that there were emotional differences between 2D and 3D web interface; 3D web interfaces provide users with specific emotional experiences because of their own characteristics - depth and dynamic movement. It is believed that the words collected from the survey could be the criteria to evaluate the quality of the 3D web interfaces and encourage the research on users' emotion from 3D interfaces.

• The Journal of the Korea Contents Association
• /
• v.12 no.11
• /
• pp.30-38
• /
• 2012

Sentiment analysis is concerned with extracting and analyzing different kinds of user sentiment expressed in a variety of social media such as blog and twitter. Although sentiment analysis techniques are actively studied for these days, evaluation sets are not developed yet for Korean sentiment analysis. In this paper, we constructed an evaluation set for Korean sentiment analysis. To evaluate sentiment analysis systems more throughly, each sentence in our evaluation set is tagged with the polarity of the sentiment as well as the category and the strength of the sentiment. We divide kinds of sentiment into 7 positive categories and 15 negative categories. Each category is given the strength of the sentiment from 1 to 3. Our evaluation set consists of 3,270 sentences extracted from various social media. For each sentence, 5 human taggers assigned the category and the strength of the sentiment expressed in the sentence. The ratio of inter-taggers agreement was 93% in the polarity, 70% in the category, 58% in the strength of sentiment. The ratio of inter-taggers agreement our evaluation set is a bit higher than other evaluation sets developed for German and Spanish. This result shows our evaluation set can be used as a reliable resource for the evaluation of sentiment analysis systems.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.72-75
• /
• 1999

사이버 채팅 시스템(Cyber Chatting System)은 서로 다른 곳에서 통신을 하는 사용자들이 가상의 공간에서 대화할 수 있도록 서비스를 제공한다. 현재 국내외로 많은 사이버 채팅 시스템이 운영 중에 있다. 사이버 채팅 시스템들도 다른 시스템들과 마찬가지로 사용자들이 원하는 서비스를 제공하고 있는가를 판단하고 개선 방향을 얻기 위해서는 사용성 평가를 받아야 한다. 사용성 평가는 사용성 요소들을 중심으로 이루어지기 때문에 본 논문에서는 사이버 채팅 시스템을 평가하기 위해 필요한 사용성 요소들을 분석하여 보았다. 분석결과 기존의 만족도와 수행도 이외에 정신 모형을 기반으로하는 체크리스트의 필요성이 발견되었다.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.501-510
• /
• 2010

The knowledge base on emotional information is one of the key elements in the implementation of emotion retrieval systems for contents design of Mobile devices. This study proposed a new approach to the knowledge base implementation by automatically extracting color components from full-color images. In this study, the validity of the proposed method was empirically tested. Database was developed using 100 interior images as visual stimuli and a total of 48 subjects participated in the experiment. In order to test the reliability of the proposed 'emotional information knowledge base', firstly 'recall ratio' that refers to frequencies of correct images from the retrieved images was derived. Secondly, correlation Analysis was performed to compare the ratings by the subjects to what the system calculated. Finally, the rating comparison was used to run a paired-sample t-test. The analysis demonstrated satisfactory recall ration of 62.1%. Also, a significant positive correlation (p<.01) was observed from all the emotion keywords. The paired Sample t-test found that all the emotion keywords except "casual" retrieved the images in the order from more relevant to less relevant images and the difference was statistically significant (t(9)=5.528, p<.05). Findings of this study support that the proposed 'emotional information knowledge base' established only with color information automatically extracted from images can be effectively used for such visual stimuli search tasks as commercial interior images.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.64-72
• /
• 2014

As the importance of interface became emphasized recently, function of icon as an element that helps operation and formative function as an aesthetic element are becoming emphasized. Specially, various research methodologies for measuring the understanding degree of users are being attempted in functional aspect, however, they are facing limitations as user evaluation method of quantitative investigation for statistical analysis became overly dependent on the consent from majority. To overcome such limitation, a methodology of measuring sensibility as aesthetic impression or individuality based on the system of emotion or system of understanding of users and designing icon based on the measurement is being attempted continuously. Therefore, this study suggested an evaluation method using reminding words and conducted an empirical study to apply results on the icon design by applying the evaluation method on icon design of printing products to measure the user sensibility and understanding level. Through this process, this study intended to research summaries on the design evaluation method which based on the evaluation of user sensibility and understanding level and to debate effective design methodologies through the process of applying these summaries on the project. The intention was to progress discussion from practical application perspectives apart from the textbook type discussion by applying a research methodology through concrete cases. This study objectified sensibility and understanding level of users in the icon design aspect, suggested a methodology that can be applied on the design, and it is expected to be used when progressing the icon and GUI design.

• Science of Emotion and Sensibility
• /
• v.2 no.2
• /
• pp.83-91
• /
• 1999

사이버 채팅 시스템(Cyber Chatting System)은 한 명 이상의 참여자들이 사이버 공간에서 대화할 수 있도록 해주는 양방향 이사 소통 시스템이다. 컴퓨터를 통한 통신이 점차 확산되어 가면서 사이버 채팅 시스템도 그 중요도가 새롭게 인식되고 있고, 국내외로 많은 사이버 채팅 시스템이 운영 중에 있다. 사이버 채팅 시스템들도 다른 시스템들과 마찬가지로 사용자들이 원하는 서비스를 제공하고 있는가를 판단하고 개선 방향을 얻기 위해서는 사용성 평가를 받아야 한다. 기존의 일반적인 프로그램 평가 방식이나 웹 페이지 평가 방식만을 적용해서는 사이버 채팅 시스템의 특징을 반영하는 평가를 하기에 충분하지 않다. 그러므로, 본 논문에서는 사용자들이 일반 대화에서 얻은 정신 모형을 바탕으로 사용성 평가 방식을 개발하여 채팅 시스템의실질적 사용성을 분석할 수 있도록 하였다. 이러한 평가 시스템을 적용하면 사용자의 예상과 기대를 기반으로 시스템의 사용성을 평가하여 보다 나은 시스템 개발을 위한 개선 방향을 효과적으로 제시할 수 있다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.242-247
• /
• 1999

디자이너는 제품의 디자인에 대한 고객의 감성적 평가에 대한 예측을 필요로 하고 있는데 특히 Web상에서 제품을 평가하는 사례가 늘어감에 따라 보다 차별화된 감성적 평가 모형이 요구되고 있다. 본 연구에서는 이미 연구된 다양한 디자인의 명세화 방법을 조사ㆍ분석하여 사용자로 하여금 Web상에서 좋은 제품을 선택하게 하는 감성적인 속성을 명세화하는 몇 가지 모델을 제시하고 이를 인공신경망을 통한 검증을 거쳐서 디자인 평가를 수행할 수 있는 적절한 감성요소 명세화의 방법을 제시하였다. 또한 이러한 명세화된 감성속성을 가지고 인공신경망을 응용하여 감성적인 속성을 고려하여 디자인을 평가할 수 있는 연구모형을 구축하였다.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.419-431
• /
• 2018

In this paper, we propose a novel method for monitoring mood trend of Twitter users by analyzing their daily tweets for a long period. Then, to more accurately understand their tweets, we analyze all types of content in tweets, i.e., texts and emoticons, and images, thus develop a multimodal sentiment analysis method. In the proposed method, two single-modal analyses first are performed to extract the users' moods hidden in texts and images: a lexicon-based and learning-based text classifier and a learning-based image classifier. Thereafter, the extracted moods from the respective analyses are combined into a tweet mood and aggregated a daily mood. As a result, the proposed method generates a user daily mood flow graph, which allows us for monitoring the mood trend of users more intuitively. For evaluation, we perform two sets of experiment. First, we collect the data sets of 40,447 data. We evaluate our method via comparing the state-of-the-art techniques. In our experiments, we demonstrate that the proposed multimodal analysis method outperforms other baselines and our own methods using text-based tweets or images only. Furthermore, to evaluate the potential of the proposed method in monitoring users' mood trend, we tested the proposed method with 40 depressive users and 40 normal users. It proves that the proposed method can be effectively used in finding depressed users.

• The Journal of the Korea Contents Association
• /
• v.19 no.3
• /
• pp.80-88
• /
• 2019

With more emphasis on emotional communication with users in product design field, designers' clear and prompt grasp of user's emotion has become the core activity in product design research. To increase the flexibility applying emotion measurement in the process of product design, this study has used Facial Action Coding System (FACS) of behavioral emotion measurement method in product design evaluation. To select specimens, it has flexibly used the emotional product Image Map. Then this study has selected six product irritants inducing positive, negative and neutral emotions, and conducted FACS experiment with ordinary product users of 20 generations as the experimental subject, and analyzed users' emotional state in response to the irritants through their facial expressions. It also analyzes the advantages and disadvantages of FACS in the process of product design, such as "recording users' unconscious facial expressions" and puts forward some applicable schemes, such as "choosing a product stimulus with high user response". It is expected that this paper can be helpful to the flexibility of FACS as a method to predict user's emotion in advance at the trial stage of product design before launching them to the market.