• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.528-531
• /
• 2021

Nowadays recommendation systems are so ubiquitous, where our many decisions are being done by the means of them. We can see recommendation systems in all areas of our daily life. Therefore the research of this sphere is still so active. So far many research papers were published for clothing recommendations as well. In this paper, we propose the clothing-recommendation system according to user emotion and weather information. We used social media to analyze users' 6 basic emotions according to Paul Eckman theory and match the colour of clothing. Moreover, getting weather information using visualcrossing.com API to predict the kind of clothing. For sentiment analysis, we used Emotion Lexicon that was created by using Mechanical Turk. And matching the emotion and colour was done by applying Hayashi's Quantification Method III.

• Science of Emotion and Sensibility
• /
• v.17 no.3
• /
• pp.65-74
• /
• 2014

Due to recent interest in user experience and its significance, much research surrounding this theme is now being conducted. In this research, I investigated user experience during usage of a product and the satisfaction acquired by it, as well as the relationship between satisfaction of having used a product and whether the user would be more likely to purchase another product from the same company. The same experiment was conducted in South Korea and the United States of America in order to get more generalized experimental results. I found that amongst the six representative user emotions expressed while using a product, two of them correlated the most. First, 'Satisfaction in Usability' (the emotions aroused by satisfaction with usage or the practicality of the product); and second, 'Discomfort or Displeasure' (uncomfortable or unpleasant emotions expressed while using a product. The above two factors were found to be of the most influence concerning satisfaction of the product. Also 'Satisfaction in Usability' was found to be of the most influence in their preferability towards purchasing an item from the same company in the future. The significance of this finding is that aside from focussing on the attractiveness of the product's exteriors and design, one should be concerned on the ease of usage and effectiveness as well as usability of the product, all of which contribute to how efficiently a consumer will utilize the product. Furthermore, in agreement with previous research concerning the correlation between satisfaction of a product and positive perspective on consecutive purchases, the result of this study shows that the more satisfaction consumers feel after using a product, the more likely they are to purchase additional merchandises from the same company which manufactured the original product.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.129-146
• /
• 2010

System response times(SRTs) are getting important while increasing the function of system. In the past, most research studied SRTs on situation of computer usage. There are lacking the research on simple domain. This study focuses on behavioral and emotional effect on situation of cell phone usage(experience 1; independent variables: degree of SRTs, dependent variables: behavioral and emotional evaluation). And this study investigates the behavioral and emotional effect in same SRTs on different situation(experience 2; independent variables: degree of SRTs, usage mode, dependent variables: behavioral and emotional evaluation, stress, mental strain). The result indicated that long SRTs increased problem solving time and negative emotion. User evaluated the system differently according to usage mode after they performed the same task. In other word, if user had a strong goal, then they felt more negative emotion and mental effort than the user don't have a strong goal. In the goal mode group, it was important there are being of delay or not. This study demonstrated that SRTs and usage mode influence user's emotion and behavior performance in same task.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.818-820
• /
• 2022

The keyword 'healing' is essential to the competitive society and culture of Koreans. In addition, as the time at home increases due to COVID-19, the demand for indoor healing services has increased. Therefore, this thesis analyzes the user's facial expression so that people can receive various 'customized' healing services indoors, and based on this, provides lighting, ASMR, video recommendation service, and facial expression recording service.The user's expression was analyzed by applying the ensemble algorithm to the expression prediction results of various CNN models after extracting only the face through object detection from the image taken by the user.

• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.521-530
• /
• 2008

Graphical user interface design, the visual language to convey information about the icon and the user's information is a medium that can lead to action. Graphical user interface to communicate with the user icon, the user is easy to use, so any time you want to provide information effectively. Communication in order to increase the efficiency of the Graphic User Interface on the nature of the medium must be made to develop the appropriate icon. In this research icon of the type of icon painting. A picture of the icon representation of each type of detail, according to a rating of johyeongjeok identify the elements of the correlation between. On the type of representation of each of Art and Design elements that I know what I saw. The icon design based on user preferences provide guidance on the direction of design-oriented. When the data can be used to designs based on the theory has to offer.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.83-88
• /
• 2017

The personal activity information is expanding as a way to utilize wearable devices that are emerging as next generation smart devices. This paper develops an application for collecting heartbeat rate and location information of a user using SmartWatch, which is a smartphone and wearable device, and analyzing it through machine learning to infer user's emotion information. By using smart phone and smart watch, developed application can collect biometric data and location information by simply executing application and doing everyday life. In addition, adding the location information to the hearbit rate data, it proves higher utilization than existing ones.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.1
• /
• pp.17-22
• /
• 2006

Variable contents are extracted and used to improve the correctness of the retrieval in the content-based in age retrieval. This way use the physical feature for the retrieval. In this way of retrieval, the user has to know the basic physical features and spatial relationship of target images that he wants to retrieve. There are some restriction to reflect the user's intend. We need the retrieval system that reflect the user's intend. In this paper, we propose an emotion-based retrieval system. It is different from past emotion based image retrieval in point of view that it uses relevance feedback to estimate the users intend and it is easily combined with past content-based image retrieval system. The features and similarity measures are adopted from MPEG-7 color descriptors which are proper retrieval of large multimedia databases. We use wallpaper images for the experiment. The result shows that the system get successful result.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.381-387
• /
• 2013

Recently, emotional contents that induce emotions and respond to emotions are given attention in the field of cultural industries, and extracting emotion caused by multimedia contents is being noted. Furthermore, since multimedia contents have been quickly produced and distributed these days, researches automatically to extract the feeling of multimedia contents are being accelerated. In this paper, we will study the method of emotional value extraction in the multimedia contents using the volume value of the multimedia contents in a certain frequency among sound informations. This study allows to extract the emotion of multimedia contents automatically, and the extracted information will be used to provide user's current emotion, weather, etc. for the users.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.985-987
• /
• 2010

In this paper, we propose a maximum entropy-based emotion recognition model using individual average difference. In order to accurately recognize an user' s emotion, the proposed model utilizes the difference between the average of the given input physiological signals and the average of each emotion state' signals rather than only the input signal. For the purpose of alleviating data sparse -ness, the proposed model substitutes two simple symbols such as +(positive number)/-(negative number) for every average difference value, and calculates the average of physiological signals based on a second rather than the longer total emotion response time. With the aim of easily constructing the model, it utilizes a simple average difference calculation technique and a maximum entropy model, one of well-known machine learning techniques.