• The Journal of the Korea Contents Association
• /
• v.11 no.5
• /
• pp.413-423
• /
• 2011

The objective of this study was to explain structural relations among perceived justice of service recovery, customer's emotion and satisfaction in the airline service sector. For this purpose, using a sample of 272 airline service customers who experienced complaints with airline service, we investigate the effects of the dimensions of perceived justice on the emotions triggered by service recovery. In this study, 4 hypotheses based on literature reviews were employed. The data and hypotheses were examined using Structural Equation Modeling(SEM) by AMOS. The main findings are as follows. Firstly, procedural justice has an effect on both positive and negative emotions. Secondly, both interaction justice and distributive justice have effects on positive emotion but not on negative emotion. Lastly, only positive emotion has influence on recovery satisfaction.

• Korean Journal of Cognitive Science
• /
• v.19 no.4
• /
• pp.477-497
• /
• 2008

Mood classification of blog text is an interesting problem, with a potential for a variety of services involving the Web. This paper introduces an approach to mood classification enhancements through the normalized negation n-grams which contain mood clues and corpus-specific term weighting(CSTW). We've done experiments on blog texts with two different classification methods: Enhanced Mood Flow Analysis(EMFA) and Support Vector Machine based Mood Classification(SVMMC). It proves that the normalized negation n-gram method is quite effective in dealing with negations and gave gradual improvements in mood classification with EMF A. From the selection of CSTW, we noticed that the appropriate weighting scheme is important for supporting adequate levels of mood classification performance because it outperforms the result of TF*IDF and TF.

• The Journal of the Korea Contents Association
• /
• v.16 no.5
• /
• pp.428-439
• /
• 2016

It becomes undeniable trends that offline shopping stores operate their own online shopping stores too. The multi-channel shopping stores like this allow consumers to have much choices to shop from either offline channel or online channel. This trend, however, also opens new research issues. Especially, we have found from literature survey that a new research model is necessary for more in-depth study of the consumer behavior analysis in the multi-channel trends like this, where those constructs such as offline trust, uncertainty, switching cost, and individual negative emotion are considered. It is noted, especially in the multi-channel environments, that uncertainty and switching cost need to be considered, and that individual tends to feel negative emotion much more. By relying on 406 valid questionnaires, we obtained empirical results such that switching cost and offline trust have a positive effect on continuance intention, and uncertainty tends to increase switching cost. Individual negative emotion also affects continuance intention significantly.

• Journal of Industrial Convergence
• /
• v.20 no.11
• /
• pp.41-47
• /
• 2022

This study explored the academic emotions of university freshmen depending on the type of online class(pre-recorded lecture vs. real time online class) that they took during the COVID-19 lockdown. 170 freshmen participated in the survey based on the 'Academic Emotion Questionnaire(AEQ)', and the statistical results are as follows; Firstly, research showed that the participants felt higher positive emotions for pre-recorded lecture than for real time online class, and higher negative emotions for real time online class than for pre-recorded lecture(p < .01). Secondly, participants felt different emotions depending on English level(p < .01). Thirdly, participants felt different emotions depending on their majors(p < .01). Students majoring in science & engineering felt higher positive emotions than those in humanities & social studies in pre-recorded lecture class. Fourthly, participants felt different emotions depending on gender(p < .01). Female students felt higher negative emotions than male students. Finally, the pedagogical implications and suggestions were discussed.

• 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.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.379-383
• /
• 2021

감정 분석은 텍스트 데이터에서 인간이 느끼는 감정을 다양한 감정 유형으로 분류하는 것이다. 그러나 많은 연구에서 감정 분석은 긍정과 부정, 또는 중립의 극성을 분류하는 감성 분석의 개념과 혼용되고 있다. 본 연구에서는 텍스트에서 느껴지는 감정들을 다양한 감정 유형으로 분류한 감정 말뭉치를 구축하였는데, 감정 말뭉치를 구축하기 위해 심리학 모델을 기반으로 분류한 감정 어휘 사전을 사용하였다. 9가지 감정 유형으로 분류된 한국어 감정 어휘 사전을 바탕으로 한국어 영화 리뷰 말뭉치에 9가지 감정 유형의 감정을 태깅하여 감정 분석 말뭉치를 구축하고, KcBert에 학습시켰다. 긍정과 부정으로 분류된 데이터로 사전 학습된 KcBert에 9개의 유형으로 분류된 데이터를 학습시켜 기존 모델과 성능 비교를 한 결과, KcBert는 다중 분류 모델에서도 우수한 성능을 보였다.

• Annual Conference on Human and Language Technology
• /
• 2008.10a
• /
• pp.201-206
• /
• 2008

본 논문은 한국어 문서 감정분류에 기반이 되는 감정 자질의 가중치 강화를 통해 감정분류의 성능 향상을 얻을 수 있는 기법을 제안한다. 먼저, 어휘 자원인 감정 자질을 확보하고, 확장된 감정 자질이 감정 분류에 얼마나 기여하는지를 평가한다. 그리고 학습 데이터를 이용하여 얻을 수 있는 감정 자질의 카이 제곱 통계량(${\chi}^2$ statics)값을 이용하여 각 문장의 감정 강도를 구한다. 이렇게 구한 문장의 감정 강도의 값을 TF-IDF 가중치 기법에 접목하여 감정 자질의 가중치를 강화시킨다. 마지막으로 긍정 문서에서는 긍정 감정 자질만 강화하고 부정 문서에서는 부정 감정 자질만 강화하여 학습하였다. 본 논문에서는 문서 분류에 뛰어난 성능을 보여주는 지지 벡터 기계(Support Vector Machine)를 사용하여 제안한 방법의 성능을 평가한다. 평가 결과, 일반적인 정보 검색에서 사용하는 내용어(Content Word) 기반의 자질을 사용한 경우 보다 약 2.0%의 성능 향상을 보였다.

• Science of Emotion and Sensibility
• /
• v.26 no.3
• /
• pp.83-100
• /
• 2023

This study determines whether the perception of the frequency of experiencing positive, negative, and surprise emotions changes according to the level of cognitive well-being. Furthermore, we determined practical means to analyze which emotions can be managed in daily life as an effective means of improving overall life satisfaction by identifying representative specific emotions that strongly predict the level of cognitive well-being. To this end, the between-subjects factorial design is adopted to measure the frequency of emotional experiences according to the level of cognitive well-being in 438 university undergraduate students. For cognitive well-being, the life satisfaction scale (SWLS) was used, and the PANAS-X scale was used to measure emotional frequency. As a result, first, the group with high cognitive well-being displays a higher frequency of positive and surprise emotional experiences and a lower frequency of negative emotional experiences than the group with low cognitive well-being. Second, the results confirm that representative emotions affecting cognitive well-being included 8 positive emotions, 7 negative emotions, and 1 surprise emotion. Among them, positive emotions include "happy" and "confident," negative emotions include "dissatisfied with self" and "disgusted with self," and surprise emotions include words such as "amazed." Therefore, we can conclude that the representative emotions are those with the greatest influence on cognitive well-being. Therefore, increasing the frequency of specific emotions (e.g., happy, confident, and surprise) and decreasing the frequency of others (e.g., dissatisfied with self and disgusted with self) could be effective in improving cognitive well-being than unconditionally examining emotions experienced in daily life.

• The Journal of the Korea Contents Association
• /
• v.16 no.2
• /
• pp.82-95
• /
• 2016

This research has analyzed the influence of information search on festival image, emotional response, re-visit intention and intention to share information. Image of festival was assumed to be composed of three components of cognitive, affective and unique image. Emotional response was divided into positive and negative emotion. As the results of influence analysis, word of mouth-effect and online media such as SNS had a significant effect on unique image of the festival. whereas official homepage showed a significant impact on cognitive image. Among three factors of image, affective image had a great influence on positive emotion. as three image factors are associated with positive emotion. Also, Affective emotion was analyzed to have significant influence on re-visit intention and intention to share information.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.31-32
• /
• 2013

본 논문에서는 영화의 등장인물의 성향을 파악하기 위해 시나리오의 대사로부터 감정어를 추출하고, 등장인물의 감정어들을 긍정, 부정, 중립의 3개로 단순화하여 등장인물의 성향을 가시화 시켜주는 방법을 제안한다. 대사로부터 감정어를 추출하기 위해 WordNet 기반의 감정어 추출 방법을 제안한다. WordNet은 단어 간에 상위어와 하위어, 유사어 등의 관계로 연결된 네트워크 구조의 사전이다. 이 네트워크 구조에서 최상위의 감정 항목과의 거리를 계산하여 단어별 감정량을 계산하여 대사를 30 차원의 감정 벡터로 표현한다. 등장인물별로 추출된 감정 벡터를 긍정, 부정, 중립의 3개의 차원으로 단순화 하여 등장인물의 성향을 표현한다.