• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.470-473
• /
• 2004

In this paper, the comparison of speech feature parameters for emotion recognition is studied for emotion recognition using speech signal. For this purpose, a corpus of emotional speech data recorded and classified according to the emotion using the subjective evaluation were used to make statical feature vectors such as average, standard deviation and maximum value of pitch and energy. MFCC parameters and their derivatives with or without cepstral mean subfraction are also used to evaluate the performance of the conventional pattern matching algorithms. Pitch and energy Parameters were used as a Prosodic information and MFCC Parameters were used as phonetic information. In this paper, In the Experiments, the vector quantization based emotion recognition system is used for speaker and context independent emotion recognition. Experimental results showed that vector quantization based emotion recognizer using MFCC parameters showed better performance than that using the Pitch and energy parameters. The vector quantization based emotion recognizer achieved recognition rates of 73.3％ for the speaker and context independent classification.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.04a
• /
• pp.998-1000
• /
• 2014

상황인식 컴퓨팅 환경에서 가장 핵심적인 부분은 서비스를 제공받는 객체의 상황(Context)을 인식하고 정보화하여 그 상황에 따라서 객체 중심의 지능화된 최적의 서비스를 제공해 주는 것이다. 이러한 지능화된 최적의 서비스를 제공하기 위해서는 최적의 상황을 인식하는 상황인식 컴퓨팅 기술 연구와 그 상황을 설계하는 모델링 기술이 중요하다. 또한, 인간과 컴퓨터간의 의사소통을 원활히 할 수 있는 최적의 상황을 인식해야 한다. 현재까지 연구된 대부분의 상황인식 컴퓨팅 기술은 상황정보로 객체의 위치정보와 객체의 식별정보만을 주로 사용하고 있다. 그러므로 지정된 공간에서 상황을 발생시키는 객체를 식별하는 일과 식별된 객체가 발생하는 상황의 인식에만 주된 초점을 두고 있다. 그러나 본 논문에서는 객체의 감정표현단어를 상황정보로 사용하여 감정인식을 위한 상황인식 미들웨어로서 ECAM의 구조를 제안한다. ECAM은 감정표현단어의 범주화 기술을 기반으로 온톨로지를 구축하여 객체의 감정을 인식한다. 객체의 감정표현단어 정보를 상황정보로 사용하고, 인간의 감정에 영향을 미칠 수 있는 환경정보(온도, 습도, 날씨)를 추가하여 인식한다. 객체의 감정을 표현하기 위해서 OWL 언어를 사용하여 온톨로지를 구축하였으며, 감정추론 엔진은 Jena를 사용하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.889-890
• /
• 2009

유비쿼터스 컴퓨팅 환경에서 가장 핵심적인 부분은 상황(Context)을 인식하고, 그 상황에 따라서 최적의 서비스를 제공해 주는 것이다. 이러한 최적의 서비스를 제공하기 위해서는 최적의 상황을 인식하는 상황인식 컴퓨팅 기술 연구와 그 상황을 설계하는 모델링 기술들이 중요하다. 현재 대부분의 상황인식 컴퓨팅 기술은 지정된 공간에서 상황을 발생시키는 객체를 식별하는 일과 식별된 객체가 발생하는 상황의 인식에 주된 초점을 두고 있다. 또한, 상황정보로는 객체의 위치 정보만을 주로 사용하고 있다. 그러나 본 논문에서는 객체의 감성어휘를 상황정보로 사용하여 감성을 인식할 수 있는 상황인식 미들웨어로서 EIP-CAM의 구조를 제안한다. EIP-CAM 구조의 모델링은 상황인식 모델링과 서비스 모델링으로 구성된다. 또한, 감성어휘의 범주화 기술을 기반으로 온톨로지를 구축하여 객체의 감성을 인식한다. 객체의 감성어휘를 상황정보로 사용하고, 부가적으로 환경정보(온도, 습도, 날씨 등)를 추가하여 인식한다.. 객체의 감성을 표현하기 위해서 OWL 언어를 사용하여 온톨로지를 구축하였으며, 감성추론 엔진은 Jena를 사용했다.

• Knowledge Management Research
• /
• v.16 no.1
• /
• pp.225-242
• /
• 2015

Cyberbullying, i.e., posting malicious comments online, has been identified as a critical issue in the online and social media context. It has become prevalent on a global scale, which happens across all ages. As a way to reduce and prevent cyberbullying, it is important to promote online prosocial behavior. In line with the concept of online prosocial behavior, we suggest posting benevolent comments against posting malicious comments as a new type of online prosocial behavior, which can combat cyberbullying and facilitate positive online culture. This study thus aims to analyze what motivates people to post benevolent comments in the online context. Based on interview methods, we extracted seven driving factors (self-presentation, pleasure, social contribution, emotional support, reputation, monetary reward, and reciprocity) and two inhibiting factors (social anxiety and effort) of posting benevolent comments online. This study has its theoretical contribution in exploring the motivation factors leading to the posting of benevolent comments by extending the concept of online prosocial behavior. It also has its practical implications by providing guidance for promoting prosocial behavior in the online context.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.466-468
• /
• 2003

유비쿼터스 컴퓨팅이라는 주제를 놓고, 예술가의 상상력과 과학자의 지식을 융합한 연구를 통해 다수의 사용자가 인터렉트 할 수 있는 감성공간을 구현하였다. 이와 같은 연구의 새로운 패러다임은 문화 산업과의 연계를 통한 창구효과를 통하여 경제적, 문화적 이익을 창출 할 수 있다. 아울러, 한국적인 가족 문화와 감성에 맞는 유비쿼터스 컴퓨팅의 연구는 분야에 제한 받지 않고, 다각적인 방법론으로 접근한다면 학제간의 연계발전을 가지게 되는 것은 물론. 편리한 미래의 생활 환경을 창출하는 상승효과를 이룰 것이다. 이러한 연구의 개념을 시각화한 설치 미술을 통한 Group context에 맞는 감성공간을 구현 하였다.

• Journal of Digital Convergence
• /
• v.13 no.11
• /
• pp.99-108
• /
• 2015

The aim of this research is to investigate empirically the interrelationship among emotional labor strategies, frontline employee creativity, service performance, and specifically examines the mediating effect of employee creativity in the relationship between emotional labor strategies and service performance in the context of bank industry. The data were collected from frontline employees of banks in Daegu and Gyeongnam. A total of 484 questionnaires were used for the final analysis. Consistent with hypotheses, the results of analysis show that surface acting has a negative effect on employee creativity, while deep acting has a positive effect on employee creativity, and employee creativity has a positive effect on service performance. Furthermore, employee creativity has mediating effect in the relationship between emotional labor strategies-performance.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.199-206
• /
• 2018

The current study investigated mediating effects of self-regulatory system in the context of public service announcements (PSAs). We conducted a survey to collect participants' orientation of self-regulatory systems, emotional response and evaluation of PSAs. A total of 70 undergraduate students with mean age of 22.49 (SD = 3.22). Results showed that emotional engagement to the PSAs is affected by ad liking and, in turn, directly influences intention to act as a campaign outcome. Furthermore, our findings suggested that promotion-oriented individuals are more likely to commit PSA messages than do the prevention-oriented individuals. Therefore, messages of the PSA campaign should include hope and aspiration, indicating the connection of accomplishment and advancement.

• Fashion & Textile Research Journal
• /
• v.21 no.4
• /
• pp.432-451
• /
• 2019

Companies and brands that practice sustainability pay attention to New Media due to its ability to build a sustainable relationship between companies and consumers. The need for research on specific roles, characteristics, and social media effects on eco-friendly advertising has had rapid growth in marketing programs for sustainable activities especially shown through social media. Information about sustainable fashion has spread to consumers through social media, and multifarious efforts have been made to attract the attention of youth. Despite the dramatic increase in eco-friendly marketing through social media as a part of sustainability, there is a lack of research on the major influences of emotional factors such as ad color and expression in social media. In this context, it is meaningful to identify relationships between emotional responses, advertising value and consumer behavior of sustainable fashion brands in Instagram and implement a suitable advertising type (color vs expression) for consumers. We used 366 responses for the final analysis. Data were analyzed by factor analysis, structural equation modeling using SPSS 18.0 and AMOS 18.0. The results of this study suggest that emotional responses, advertising value have a significant effect on the flow. This study expands on a previously limited research field by verifying consumer responses to image advertising on Instagram, rather than general sustainable fashion marketing. The study results also provide meaningful implications for a relation formation between customers and fashion brands vis-${\grave{a}}$-vis sustainable social media marketing.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1317-1324
• /
• 2016

Utilizing the Arduino platform to express the emotions that reflect the colors expressed the jewelry. Emotional color expression utilizes Plutchik's Wheel of Emotions model was applied to the similarity of emotions and colors. It receives the recognized value from the temperature, lighting, sound, pulse sensor and gyro sensor of a smart jewelery that can be easily accessible from your smartphone processes that recognize and process the emotion applied the rules of inference based on ontology. The emotional feelings color depending on the color looking for the emotion seen in context and applied to the smart LED jewelry. The emotion and the color combination of contextual information extracted from the recognition sensors are reflected in the built-in smart LED Jewelry depending on the emotions of the wearer. Take a light plus the emotion in a smart jewelery can represent the emotions of the situation, the doctor will be able to be a tool of representation.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.40-46
• /
• 2020

With the development of the Internet, users share their experiences and opinions. Since related keywords are used witho0ut considering information such as the general emotion or genre of an unstructured document such as a movie review, the sensitivity accuracy according to the appropriate emotional situation is impaired. Therefore, we propose a system that predicts emotions based on information such as the genre to which the unstructured document created by users belongs or overall emotions. First, representative keyword related to emotion sets such as Joy, Anger, Fear, and Sadness are extracted from the unstructured document, and the normalized weights of the emotional feature words and information of the unstructured document are trained in a system that combines CNN and LSTM as a training set. Finally, by testing the refined words extracted through movie information, morpheme analyzer and n-gram, emoticons, and emojis, it was shown that the accuracy of emotion prediction using emotions and F-measure were improved. The proposed prediction system can predict sentiment appropriately according to the situation by avoiding the error of judging negative due to the use of sad words in sad movies and scary words in horror movies.