• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.199-202
• /
• 2001

일반적으로 음성신호로부터 사람의 감정을 인식할 수 있는 요소는 (1)대화의 내용에 사용한 단어, (2)톤 (Tone), (3)음성신호의 피치(Pitch), (4)포만트 주파수(Formant Frequency), 그리고 (5)말의 빠르기(Speech Speed) (6)음질(Voice Quality) 등이다. 사람의 경우는 주파수 같은 분석요소 보다는 론과 단어, 빠르기, 음질로 감정을 받아들이게 되는 것이 자연스러운 방법이므로 당연히 후자의 요소들이 감정을 분류하는데 중요한 인자로 쓰일 수 있다. 그리고, 종래는 주로 후자의 요소들을 이용하였는데, 기계로써 구현하기 위해서는 조금 더 공학적인 포만트 주파수를 사용할 수 있게 되는 것이 도움이 된다. 그러므로, 본 연구는 음성 신호로부터 피치와 포만트, 그리고 말의 빠르기 등을 이용하여 감성 인식시스템을 구현하는 것을 목표로 연구를 진행하고 있는데, 그 1단계 연구로서 본 논문에서는 화가 나서 내뱉는 알과 기쁠 때 간단하게 사용하는 말들을 기반으로 하여 극단적인 두 가지 감정의 독특한 특성을 찾아낸다.

• 한국실내디자인학회논문집
• /
• 제16권1호
• /
• pp.91-98
• /
• 2007

Hotels had main functions of providing lodging and food and beverages in the past but hotels theses days have been changing fast to satisfy changes of social paradigm. Hotels are providing various services and further more they are places to represent certain local culture by various ways including improved entertaintment factors. accommodating combined purpose, enhancing characteristics and unique factors. These new trials can be analyzed as concepts of pursuing variety, sensual expression and pursuing originality. The concept of hotel shows new trend of expressions in design by the changes. These trends of expressions can be characterized with differentiation, sameness, heterogeneity, combination and time frame. In this study, by analyzing cases that these characteristics we applied for expanding the range of understanding toward new application method and expect to be applied to appropriate design concept of hotel culture in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5321-5334
• /
• 2019

Data mining technology is frequently used in identifying the intention of users over a variety of information contexts. Since relevant terms are mainly hidden in text data, it is necessary to extract them. Quantification is required in order to interpret user preference in association with other structured data. This paper proposes rating and comments mining to identify user priority and obtain improved ratings. Structured data (location and rating) and unstructured data (comments) are collected and priority is derived by analyzing statistics and employing TF-IDF. In addition, the improved ratings are generated by applying priority categories based on materialized ratings through Sentiment-Oriented Point-wise Mutual Information (SO-PMI)-based emotion analysis. In this paper, an experiment was carried out by collecting ratings and comments on "place" and by applying them. We confirmed that the proposed mining method is 1.2 times better than the conventional methods that do not reflect priorities and that the performance is improved to almost 2 times when the number to be predicted is small.

• 성인간호학회지
• /
• 제22권2호
• /
• pp.130-142
• /
• 2010

Purpose: The purpose of this study was to analyze attitude toward dignified dying of Korean students majoring in human service area. Methods: The Q-methodology which provides a method of analyzing the subjectivity of each item was used. The 34 selected Q-statements from each of 38 subjects were classified into a shape of normal distribution using a 9 point scale. The collected data was analyzed using a QUANL PC program. Results: Four types of attitude toward dignified dying from the subjects were identified. Type I is an expression type for happy emotion, Type II is a dislike type for life prolongation, Type III is a pursuit type for relationship improvement, and Type IV is a perception type for family presence. Conclusion: The results of the study indicate that integrating multi-disciplinary curriculum development related to dignified dying and death education for students majoring in human service area are needed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.4090-4102
• /
• 2018

After emerging online communications, text mining and sentiment analysis has been frequently applied into analyzing electronic word-of-mouth. This study aims to develop a domain-specific lexicon of sentiment analysis to predict box office success in Korea film market and validate the feasibility of the lexicon. Natural language processing, a machine learning algorithm, and a lexicon-based sentiment classification method are employed. To create a movie domain sentiment lexicon, 233,631 reviews of 147 movies with popularity ratings is collected by a XML crawling package in R program. We accomplished 81.69% accuracy in sentiment classification by the Korean sentiment dictionary including 706 negative words and 617 positive words. The result showed a stronger positive relationship with box office success and consumers' sentiment as well as a significant positive effect in the linear regression for the predicting model. In addition, it reveals emotion in the user-generated content can be a more accurate clue to predict business success.

• 한국간호교육학회지
• /
• 제17권2호
• /
• pp.178-189
• /
• 2011

Purpose: The purpose of this study was to analyze types of undergraduate nursing student's perception toward happiness. Method: The Q-methodology, which provides a method of analyzing the subjectivity of each item, was used. The 34 selected Q-statements from each of 41 subjects were classified into a shape of normal distribution using a 9 point scale. The collected data was analyzed using a QUANL PC program. Result: Four types of perception of happiness in Korean undergraduate nursing students were identified. Type I is a family support vs. emotion type, Type II is a self satisfaction vs. perception type, Type III is a relation oriented vs. action type, and Type IV is a self regulation vs. belief type. Conclusion: It can be concluded that obtaining happiness by pursuing a satisfactory life through creation of values can play an important role in happiness. Therefore, the results of this study suggest that the concept of happiness might be included in nursing curriculum.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.489-492
• /
• 2002

최근 인간형 로봇에 대한 개발이 괄목할 만한 성장을 이루고 있고, 친근한 로봇의 개발에 중요한 역할을 담당하는 것으로써 감성/감정의 인식이 필수적이라는 인식이 확산되고 있다. 본 논문은 음성의 감정인식에 있어 가장 큰 부분을 차지하는 피치의 패턴을 인식하여 감정을 분류/인식하는 시뮬레이터의 개발과 실험결과를 나타낸다. 또한, 피치뿐 아니라 음향학적으로 날카로움, 낮음등의 요소를 분류의 기준으로 포함시켜서 좀더 신뢰성 있는 인식을 할 수 있음을 보인다. 시뮬레이터의 내부 구조로는 음성으로부터 피치를 추출하는 부분과 피치의 패턴을 학습시키는 DRNN 부분, 그리고, 음향적 특성을 추출하는 음향 추출부가 주요 요소로 이루어져 있다. 그리고, 피치를 추출하는 방법으로는 Center-Clipping 함수를 이용한 autocorrelation approach를 사용하고, 학습 시 최적의 개체를 찾는 방법으로써 (1+100)-ES를 사용한다.

• 디지털산업정보학회논문지
• /
• 제13권2호
• /
• pp.71-76
• /
• 2017

In this study, we learned about the emergence of on-line communications originating from peoseuteol Computer Communications, the limitations of online communication, and the definition, traits and development of emoticons that serve as complementary roles, such as emotion and status. After analyzing various literacture and references, it was found that the emoticons functioned as a function of communicating the visual language of the digital era and communicating more sensitively to emotional factors. In a multimedia environment, emoticons are developed at a more advanced stage as the users' own icons due to a stronger tendency to pursue particularity and uniqueness. It is expected that eomotions added with multimedia functions will be more popular and vary in type. However, although the diversification of emotions as a commercial tool is already actively progressing, there appears a reverse effect in which an excessive use of emoticons is considered insincere in online communications. In such a background, research should be conducted that can support a systematic and effective development of emoticons through visual research rather than producing multimedia emoticons indiscreetly.

• International Journal of Advanced Culture Technology
• /
• 제9권3호
• /
• pp.86-91
• /
• 2021

This study starts with the premise that many problematic situations in modern society can seriously damage personal feelings and that this phenomenon can create anxiety in individuals and society. In order to address such anxiety in individuals and society, we would like to propose measures to heal emotions. Accordingly, 270 research trends related to emotions studied from 2005 to 2020 will be analyzed to establish the direction of future research on emotion healing. As a result of analyzing the trends of healing papers, active healing studies have been conducted since 2010, but reading and writing healing through specific academic societies has been the main focus. Theoretical research accounted for a large portion, and emotional research was steadily conducted. Although healing methods are expanding to various topics, they have not been commercialized as specific methods. As a result, we hope that concrete research to heal individual emotions will be expanded and measures to implement a stable future society will be proposed.

• 동의신경정신과학회지
• /
• 제27권2호
• /
• pp.119-130
• /
• 2016

Objectives The Purpose of this study was to conduct a characteristic study on cancer patients using the Core Seven Emotions Inventory (CSEI) followed by a correlation analysis with STAI, STAXI and BDI.Methods This study was conducted by analyzing the medical records of 21 patients who had visited ○○ University Oriental hospital and completed the Core Seven Emotions Inventory (CSEI), BAI, and BDI. A total of 21 patients diagnosed with Cancer were analyzed using SPSS (Statistical Package for the Social Science, IBM, United States of America, Version 22.0). Frequency Analysis, independent t-test, one-sample t-test, and correlation analysis were conducted.Results 1. The Seven Emotion Characteristics of the Cancer patients showed a fairly stable emotional Distribution. The Gong (恐) and Kyeong (驚) emotions were relatively higher than U (憂), Bi (悲), Sa (思), Hui (喜), No (怒). 2. According to Gender, Female patients exhibited higher Sa (思) and Kyeong (驚) emotions while male patients exhibited higher Bi (悲) Emotion. 3. No (怒), U (憂), Bi (悲), Sa (思), Gong (恐), and Kyeong (驚) emotions showed a high correlation with the BDI and BAI scores of cancer patients.