• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2021

This study proposed a Long-Short Term Memory network to consider changes in emotion over time, and applied an attention mechanism to give weights to the emotion states that appear at specific moments. We used 32 channel EEG data from DEAP database. A 2-level classification (Low and High) experiment and a 3-level classification experiment (Low, Middle, and High) were performed on Valence and Arousal emotion model. As a result, accuracy of the 2-level classification experiment was 90.1% for Valence and 88.1% for Arousal. The accuracy of 3-level classification was 83.5% for Valence and 82.5% for Arousal.

• Journal of Service Research and Studies
• /
• v.13 no.3
• /
• pp.1-19
• /
• 2023

Despite the growing importance of video-based social media content, such as vlogs, as a marketing tool in the travel industry, there is limited research on the characteristics that enhance engagement among potential travelers. This study explores the influence of emotional valence in YouTube travel content on viewer engagement, specifically likes and comments. We analyzed 4,619 travel-related YouTube videos from eight popular tourist cities. Using negative binomial regression analysis, we found that both positive and negative emotions significantly influence the number of likes received. Videos with higher positive emotions as well as negative emotions receive more likes. However, when it comes to the number of comments, only negative emotions showed a significant positive influence, while positive emotions had no significant impact. These findings offer valuable insights for marketers seeking to optimize engagement strategies on YouTube, considering the unique nature of travel products. Further research into the effects of specific emotions on engagement is warranted to improve marketing strategies. This study highlights the powerful impact of emotions on viewer engagement in the context of social media, particularly on YouTube.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.375-377
• /
• 2012

스마트폰과 같은 모바일 기기가 발전함에 따라 SNS, 모바일 메신저, SMS와 같은 단문 기반 메시지는 자신의 감정을 가장 잘 표현하는 매체이다. 그럼에도 불구하고 기존 연구는 주로 장문의 텍스트로부터 긍정, 부정 분류나 문서의 성향을 분석하는 것에 그치는 경우가 많다. 의미지향(Semantic Orientation)방법은 검색엔진을 통해 감정 키워드와 인지하고자 하는 단어의 동시 빈출 정도를 PMI로 계산한 것으로 WordNet과 같은 의미 사전이 존재하지 않는 한국어의 특성에서 적용 가능한 방법이다. 본 논문에서는 의미 지향성 및 다른 텍스트 기반 감정 분류 기술에 대해 비교하고 이들을 활용하여 한국어로 구성된 단문 텍스트에서 효율적인 감정 분류 기법을 제안하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.109-114
• /
• 2015

대화 시스템에서 사용자 발화에 대한 감정 분석은 적절한 시스템 응답과 서비스를 제공하는데 있어 매우 중요한 정보이다. 본 연구에서는 단순한 긍, 부정이 아닌 분노, 슬픔, 공포, 기쁨 등 Plutchick의 8 분류 체계에 해당하는 상세한 감정을 분석 하는 데 있어, 임베딩 모델을 사용하여 기존의 어휘 자질을 효과적으로 사용할 수 있는 새로운 방법을 제안한다. 또한 대화 속에서 발생한 감정의 지속성을 반영하기 위하여 문장 임베딩 벡터와 문맥 임베딩 벡터를 자질로서 이용하는 방법에 대해 제안한다. 실험 결과 제안하는 임베딩 자질은 특히 내용어에 대해 기존의 어휘 자질을 대체할 수 있으며, 데이터 부족 문제를 다소 해소하여 성능 향상에 도움이 되는 것으로 나타났다.

• Annual Conference on Human and Language Technology
• /
• 2011.10a
• /
• pp.94-97
• /
• 2011

본 논문은 자동으로 한글 트위터 메시지(트윗: tweet)에 포함된 감정을 분석하는 방법에 대하여 기술한다. 제안된 시스템에 의하여 수집된 트윗들은 어떤 질의에 대해 긍정 혹은 부정으로 분류된다. 이것은 일반적으로 어떤 상품을 구매하기 원하는 고객이나, 상품에 대한 고객들의 평가를 수집하기 원하는 기업에게 유용하다. 영문 트윗에 대한 연구는 이미 활발하게 진행되고 있지만 한글 트윗, 특히 감정 분류에 대한 연구는 아직 공개된 것이 없다. 수집된 트윗들은 기계 학습(Naive Bayes, Maximum Entropy, 그리고 SVM)을 이용하여 분류하였고 한글 특성에 따라 자질 선택의 기본 단위를 2음절과 3음절로 나누어 실험하였다. 기존의 영어에 대한 연구는 80% 이상의 정확도를 가지는 반면에, 본 실험에서는 60% 정도의 정확도를 얻을 수 있었다.

• Journal of Korea Entertainment Industry Association
• /
• v.14 no.8
• /
• pp.381-390
• /
• 2020

This purpose of study was to influence of fitness club leader's emotional labor on job involvement and occupation performance. This study aims at providing fundamental data and information on fitness club leader's emotional labor. The survey was done through 250 copies and excluding 23 copies ran an analysis on the remaining 227(90.8%) copies. After question investigating the data which is collected used IBM SPSS statistics 21 and IBM AMOS 21 program, frequency analysis, Exploratory factor analysis and confirmatory factor analysis, convergent validity, discriminant validity, Cronbach's α, correlation analysis, path analysis through Structural Equation Model(SEM). The result of this study were as follows. First, fitness club leader's emotional labor showed (-) effects on job involvement. Second, fitness club leader's emotional labor showed (-) effect on occupation performance. Third, job involvement showed (+) effects on occupation performance. Fitness instructors have severe emotional labor. Therefore fitness instructors manage their emotional labor. This can increase job commitment and job performance. For teeth manager need to increase support options from fitness instructors.

• Annual Conference on Human and Language Technology
• /
• 2009.10a
• /
• pp.56-60
• /
• 2009

오늘날 인터넷은 개인의 감정, 의견을 서로 공유할 수 있는 공간이 되고 있다. 하지만 인터넷에는 너무나 방대한 문서가 존재하기 때문에 다른 사용자들의 감정, 의견 정보를 개인의 의사 결정에 활용하기가 쉽지 않다. 최근 들어 감정이나 의견을 자동으로 추출하기 위한 연구가 활발하게 진행되고 있으며, 감정 분석에 관한 기존 연구들은 대부분 어구의 극성(polarity) 정보가 있는 감정 사전을 사용하고 있다. 하지만 인터넷에는 나날이 신조어가 새로 생기고 언어 파괴 현상이 자주 일어나기 때문에 사전에 기반한 방법은 한계가 있다. 본 논문은 감정 분석 문제를 긍정과 부정으로 구분하는 이진 분류 문제로 본다. 이진 분류 문제에서 탁월한 성능을 보이는 Support Vector Machines(SVM)을 사용하며, 문서들 간의 유사도 계산을 위해 문장의 부분 문자열을 비교하는 문자열 커널을 사용한다. 실험 결과, 실제 영화평에서 제안된 모델이 비교 대상으로 삼은 Bag of Words(BOW) 모델보다 안정적인 성능을 보였다.

• Culinary science and hospitality research
• /
• v.15 no.2
• /
• pp.136-149
• /
• 2009

The purpose of this paper is to explore the types of failed service and its effect on customer's negative emotions in the restaurant business and their influence on customer's behavior. The study examines the restaurant attributes of failed service in order to determine which variables have the greatest impact on customer's negative emotions and behaviors. To accomplish the purpose of this study, a casual model is developed - which analyzes the main antecedents, moderators and consequences of failed service in the restaurant business. The findings of this study are as follows. 4 types of failed services are found: lack of tangibles, doubt of reliability, unresponsiveness, no expressed empathy. They have an effect on customer's negative emotions(regret and disappointment). And the customer's negative emotions brings out negative behaviors(bad actions, switching brand, protest, negative word of mouth). Customer's regret causes bad actions and switching brand, and customer's disappointment caused switching brand and bad information by word of mouth.

• Science of Emotion and Sensibility
• /
• v.22 no.4
• /
• pp.45-56
• /
• 2019

The regulation of emotion is known to mediate the relationship between emotion-relevant differences in individuals and their life outcomes. This study attempted to include a situational factor in addition to the mediation model and investigated whether this conditional component changed the patterns of indirect effects. The researchers recruited 180 emotional laborers working in diverse domains and used a questionnaire to ascertain their negative affectivity, cognitive reappraisal, emotional exhaustion, and the intensity of negative comments they usually received from customers. The results of the conditional indirect effect analysis revealed the positive indirect influence of negative affectivity on emotional exhaustion through cognitive reappraisal when emotional labors receive highly negative comments from customers (high intensity of the situation). Similarly, negative indirect effects were found when emotional labors receive slightly negative comments from customers (low intensity of the situation). The outcomes of this study suggest that cognitive reappraisal can mediate to decrease emotional exhaustion in contexts that arouse more intensive negative emotions; it can also mediate to increase emotional exhaustion in contexts that arouse less intensive negative emotions. The implications of this study include the importance of integrating individual differences with situational factors. The study also provides information about the distinctiveness of groups of emotional laborers.

• Knowledge Management Research
• /
• v.22 no.1
• /
• pp.243-267
• /
• 2021

Sentiment represents one's own state through the process of change to stimulus, and emotion represents a simple psychological state felt for a certain phenomenon. These two terms tend to be used interchangeably, but their meaning and usage are different. In this study, we try to find out how it affects the helpfulness of reviews by classifying sentiment and emotion through online reviews written by online consumers after purchasing and using various products and services. Recently, online reviews have become a very important factor for businesses and consumers. Helpful reviews play a key role in the decision-making process of potential customers and can be assessed through review helpfulness. The helpfulness of reviews is becoming increasingly important in practice as it is utilized in marketing strategies in business as well as in purchasing decision-making issues of consumers. And academically, the importance of research to find the factors influencing the helpfulness of reviews is growing. In this study, Yelp.com secured reviews on restaurants and conducted a study on how the sentiment and emotion of online reviews affect the helpfulness of reviews. Based on the prior research, a research model including sentiment and emotions for online reviews was built, and text mining analyzes how the sentiment and emotion of online reviews affect the helpfulness of online reviews, and the difference in the effects on emotions It was verified. The results showed that negative sentiment and emotion had a greater effect on review helpfulness, which was consistent with the negative bias theory.