• 대한건축학회논문집:계획계
• /
• 제34권2호
• /
• pp.67-74
• /
• 2018

The purpose of this study was to analyze relationship between emotion and behavior with the color images of indoor space in hotels. The study methods evaluation experiments of emotion and behavior with computer graphic images. Study results are as follows: First, The color image according to the indoor space had a significant influence on the user's emotions. Lobby and restaurant had difference in pleasure arousal emotion by color image, and also guest room had difference in pleasure dominance emotion by color image. Second, The color image according to the indoor space had a significant influence on the user's behavior. Also lobby and restaurant had difference in movement hobby eating resting behavior by color image, and guest room had difference in hobby eating resting behavior by color image. Third, As a result of analyzing the effect of user's emotions on the behavior according to the indoor space: In the lobby, the more un-arousal increasing of users, the more hobby resting behavior increasing. And the more dominance increasing of users, the more movement hobby eating resting behavior increasing. In the restaurant, the more dominance increasing of users, the more movement eating hobby behavior increasing. The more arousal increasing of users, the more movement resting behavior increasing. The more un-arousal increasing of users, the more hobby eating behavior increasing. In the guest room, the more un-arousal dominance increasing of users, the more hobby eating resting behavior increasing. And also the more arousal increasing of users, the more movement behavior increasing.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2012년도 춘계학술대회
• /
• pp.89-90
• /
• 2012

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권12호
• /
• pp.986-995
• /
• 2009

색은 일반적으로 주요 속성인 색상, 채도, 명도가 다양한 수치로 결합되어 사람의 감정에 영향을 미친다. 반면, 사람은 같은 색이더라도 개인에 따라 다양한 감정을 느낀다. 이러한 색과 감정의 특성을 감성 기반의 디지털 기술과 컨텐츠에 활용하면, 상호작용과 함께 사용자의 흥미와 몰입을 이끌어 낼 수 있다. 이를 위해, 본 논문은 일반적으로 사람들이 어떤 색에 대해 어떤 감정을 느끼는지를 정의한 다음, 개인의 취향을 최대한 반영한 색변환 방법을 제안한다. 먼저, 색과 감정의 관계를 템플릿으로 정의한 후, 색변환을 수행한다. 이때, 색에 대한 개개인의 감정은 다르기 때문에, 각 템플릿은 모든 사람에게 동일하게 적용되지 않고, 개인의 취향에 따라 다르게 적용되어야 한다. 이를 위해, 사용자의 색상, 채도 명도에 대한 선호도를 학습을 통해 가중치를 얻어 적용함으로서 각 사용자에게 적합한 변환을 수행한다. 실험과 설문조사 결과, 템플릿을 동일하게 적용하는 것보다 사용자 취향을 반영한 변환이 사용자의 감성을 만족시켜주었음을 알 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제17권9호
• /
• pp.1125-1133
• /
• 2014

Recently, there are many researches have been studying for analyzing user interests and emotions based on users profiles and diverse information from Social Network Services (SNSs) due to their popularities. However, most of traditional researches are focusing on their researches based on single resource such as text, image, hash tag, and more, in order to obtain what user emotions are. Hence, this paper propose a method for obtaining user emotional information by analyzing texts and images both from Instagram which is one of the well-known image based SNSs. In order to extract emotional information from given images, we firstly apply GRAB-CUT algorithm to retrieve objects from given images. These retrieved objects will be regenerated by their representative colors, and compared with emotional vocabulary table for extracting which vocabularies are the most appropriate for the given images. Afterward, we will extract emotional vocabularies from text information in the comments for the given images, based on frequencies of adjective words. Finally, we will measure WUP similarities between adjective words and emotional words which extracted from the previous step. We believe that it is possible to obtain more precise user emotional information if we analyzed images and texts both time.

• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.541-572
• /
• 2023

Amazon Go is a cashierless convenience store concept, which is seen as a disruption in the grocery retail segment. Although Amazon Go has the ability to disrupt the retail segment, there are speculations on how Amazon Go will be perceived by users. Existing studies have not utilized user-generated content to understand the factors that affect customer behaviour in case of Amazon Go. Additionally, in case of phygital retail, studies have not attempted at understanding the effect of emotions and gratifications on user behaviour. To address the gap of exploring user perspectives based on their experience, we have examined the impact of gratifications and emotions on the acceptance of phygital retail using user-generated-content. A mixed-method approach has been utilized using only user-generated content. Utilizing topic-modelling based content analysis and emotion analysis on 30 articles related to Amazon Go, we found themes like, convenience, technology, experience, personalization, enjoyment and emotions like, bad, good, annoyance, success. In the empirical analysis, we have utilized 522 reviews about Amazon Go from the cognition and emotion theory stance, and found that hedonic gratifications have a positive impact on challenge emotions. We also found a significant impact of emotions on customer's favourite behaviour.

• 한국컴퓨터정보학회논문지
• /
• 제29권5호
• /
• pp.177-187
• /
• 2024

요약 배경: 기존 음악 추천 시스템은 가사의 의도된 감정과 사용자가 실제로 느끼는 감정 사이의 불일치를 충분히 고려하지 않았다. 모델: 본 연구에서는 LDA 모델을 활용하여 가사와 사용자 댓글의 주제 벡터를 생성하고, 시간 감쇠 효과와 재생 횟수를 반영한 사용자 행동 궤적과 통계 특성을 결합하여 사용자 선호도 모델을 구축했다. 결과: 실증 분석 결과, 제안 모델이 가사만 활용한 기존 모델보다 높은 정확도로 음악을 추천했다. 시사점: 본 연구는 감정 인식과 사용자 행동 분석을 통합하여 개인화된 음악 추천 시스템을 개선하는 새로운 방법론을 제시한다.

• Asia pacific journal of information systems
• /
• 제23권3호
• /
• pp.55-76
• /
• 2013

The principal objective of the work is to confirm the effects of perceived interactivity, trust, and emotion on intentions to use IPTV service. The empirical investigation into IPTV service users suggests that (i) the perception of interactivity should be directly related with trust, (ii) Users' trust should bolster users' emotion in a positive or negative aspect, and (iii) such emotion is verified to affect the intention to use IPTV continuously. More specifically, we demonstrate that positive and negative emotions influence user intentions positively and negatively. Additionally, we find that the trust mediates perceived interactivity and emotions, and both trust and emotion mediate the relationship between perceived interactivity and intentions to use IPTV. The work indicates that trust and emotion of users should be considered from IS perspective in an attempt to build the intention to use IPTV. IPTV firms should consider in their IPTV design and offering strategy how to enhance positive emotions for user retention and eventually bolster intentions to use IPTV continuously.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2001년도 춘계학술대회 논문집
• /
• pp.109-113
• /
• 2001

The purpose of this paper is to propose an analytical method for evaluating user satisfaction of Internet websites using the structural equation model(SEM). This paper is intended to identify critical evaluation factors of user satisfaction for websites to determine criteria for evaluating the websites, and use the criteria to develop a SEM model for quantitatively evaluation of each factors' effects of user satisfaction. The SEM model used 2 variables of usability and good-looks for the evaluation factors of websites user satisfaction and each factors have 4 sub evaluation criteria, 3 portal sites were evaluated to construct the SEM model, and 155 subjects participated the website evaluation using the walk-through and face-to-face survey method. Analysis results showed that the SEM model was statistically significant for all the 3 websites evaluated. Both the usability and good-looks two factors also showed significant effects to user satisfaction of websites and have positive correlation. The user satisfaction was more effected by the usability factor than good-looks, and the simplification and harmonization were the most critical sub-factors of the usability and good-looks.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.179-183
• /
• 2000

By spread of Internet, we become to use several of communication such as email, ICQ, VoIP etc. But as become convenient to use, user must be aware of variety of information regarding the media and partner user. The forecast is that this problem grows larger and larger as new media are brought in the expanding communications network. In this research, we suggest an agent MIA (Media Integration Agent) that manages the information instead of user. The MIA is an agent that obtains situation of user, and dynamically exchanged addresses and tendency of using medias in form of vCard. By use of this, user can choose better communication media. Accordingly seamless communication environment that user doesn't have to be aware of various information is formed.

• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.372-377
• /
• 2006

본 논문에서, 우리는 뇌파를 이용하여 사용자의 감정을 인식하는 감정인식 모델을 제안한다. 사용자의 감정을 인식하기 위해서는 우선 생체 데이터나 감정 데이터를 포함한 뇌파의 정량적인 데이터를 획득하는 방법이 필요하며 다음으로 획득된 뇌파를 통하여 현재 사용자의 감정 상태를 규명하는 패턴인식 기법이 중요한 문제가 된다. 본 논문에서는 뇌파를 통하여 현재 사용자의 감정 상태를 규명하고 인식할 수 있는 패턴인식 기법으로 Multi Layer Perceptron(MLP)을 사용한 패턴인식 기법을 사용한다. 본 논문에서 제안한 감정인식 모델의 실험을 위하여 특정 공간 내에서 여러 피험자의 감정별 뇌파를 측정하고, 측정된 뇌파로 집중도 및 안정도를 도출하여 유의미한 데이터로 감정 DB를 구축한다. 감정별 DB를 본 논문에서 제안한 감정인식 모델로 학습한 후 새로운 사용자의 뇌파로 현재 사용자의 감정을 인식한다. 마지막으로 피험자의 수와 은닉 노드의 수에 따른 인식률의 변화를 측정함으로서 뇌파를 이용한 감정인식 모델의 성능을 평가한다.