• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.317-324
• /
• 2013

Twitter sentiment analysis is to classify a tweet (message) into positive and negative sentiment class. This study deals with SentiWordNet(SWN)-based twitter sentiment analysis. SWN is a sentiment dictionary in which each sense of an English word has a positive and negative sentimental strength. There has been a variety of SWN-based sentiment feature extraction methods which typically first determine the sentiment orientation (SO) of a term in a document and then decide SO of the document from such terms' SO values. For example, for SO of a term, some calculated the maximum or average of sentiment scores of its senses, and others computed the average of the difference of positive and negative sentiment scores. For SO of a document, many researchers employ the maximum or average of terms' SO values. In addition, the above procedure may be applied to the whole set (adjective, adverb, noun, and verb) of parts-of-speech or its subset. This work provides a comparative study on SWN-based sentiment feature extraction schemes with performance evaluation on a well-known twitter dataset.

• Science of Emotion and Sensibility
• /
• v.10 no.4
• /
• pp.613-622
• /
• 2007

Recently, sound design is being made by corporations for the production as well as for marketing and web with consideration of image of productions and attributes to improve corporational image through the design of melody which would remain in users. And sound is becoming an important factor to establish the identity of each area such as life environment and public facilities. At present, our local governments are promoting active business like as CIP to improve urban image but there is a limit to establish identity as the result of its partial focus on visual sense or insufficient recognition about it. Jeonju, the place of sound, has many festivals and great meetings related with sound but it has not identity in the sense of sound. So the purpose of this study is to suggest the condition of sound which has the trait of Jeonju and to provide data for the trait to be used as a necessary element to establish identity in order to activate regional image. For the method of research, sampling Korean beautiful 100 sounds among the natural sounds of residents. most favorite as the samples of sound to search the sound of regional image. Selecting favorite samples among them and analyzed the factors through the questionnaire on the image of adjective in each sample. As the result of analysis, it has been shown that the factor of sound to reveal trait of Jeonju is the image of bright, delight, and cozy with consideration of harmony, dynamics, contrast, and culture. For this study is to provide data so it can be used to actively establish and identify the local image.

• International Journal of Highway Engineering
• /
• v.12 no.2
• /
• pp.51-61
• /
• 2010

According as the quality of life is improved along with economic growth, in the road plan and design sector also, it is now progressed that function oriented design is changed into the landscape oriented design that considers eyesight and emotion, which are psychological properties of users. Accordingly this study tries to come up with reasonable and objective methods to extract various emotional adjectives, which were found by the survey, while minimizing difference among characteristics of emotion and cognition of individuals. First, given semantic differential, based on various emotional adjectives that were found through the survey with the scale up to five points, the author extracted representative emotional adjectives through an element analysis, which is a conventional method of the previous research, and through an identification analysis which is suggested by this study, and then established model I of Quantification. And by using the established quantification model, the author presumed satisfaction degree, and through verifying pair wise comparison with actual satisfaction degree, the author found the results from identification and correlation analysis methods are most similar to actual satisfaction degree. As a result, the author could check the above emotional and correlation analyses were appropriate methods for comprehending which emotional elements are applicable when a continuous road landscape is designed by identification and correlation analyses.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.10
• /
• pp.19-26
• /
• 2006

In this study, psychological assessment was carried out to investigate the driver's psychological characteristics by the change of the headlight. The participants were 20 men and 20 women in their 20s and thirty-two different conditions in combinations of waveform of light, voltage, and alteration time were used. The questionnaire for the assessment was evaluated by 8 subjective item and 5-point SD criteria of 19 pair's adjective. The results were as follows : 1. The assessment results from SD method indicated 4 factors by factor analysis, and it was shown that A waveform had significances in a sense of security and impetus and B waveform had a significance in a sense of security. The levels of the limitations for the voltage change were 12[V] in the factor of a sense of security and 11[V] in the factor of a sense of impetus for A waveform, 12.6[V] in the factor of a sense of security for B waveform. 2. The results of the subjective assessment showed that the limitation of A waveform's brightness change was 12[V]. Moreover, the limitations of voltage changes were 12.67[V] for B waveform brightness change, 12.12[V] for discomfort, 12.71[V] for darkness. And the limitation of C waveform's brightness change was 12[V].

• Science of Emotion and Sensibility
• /
• v.12 no.1
• /
• pp.121-128
• /
• 2009

The article reports findings on: (1) development of emotion assessment scale in evaluating the Television(TV) picture quality; and (2) how psychological and physical factors relate to TV picture quality. A total of 152 adjectives that specifically describe emotional reactions were first selected from a Korean dictionary of adjectives, followed by ratings on their suitability for the evaluation of TV picture quality. The final selection of 19 adjective, based on the reported rating scores greater than 4.1, were used on 126 college students who were asked to perform similarity ratings on the adjectives. Based on factor analyses (i.e., principal component analysis with oblique rotation) on the similarity of scores, the following adjectives were selectively chosen for the development of the new emotion assessment scale: 'neat-messy', 'refreshing-gloomy', 'clean-dirty', 'comfortable-tense', 'smooth-rough', 'bright-dark', 'gorgeous-plain', 'diverse-monotonous', 'satisfying', 'natural', and 'sensuous'. These adjectives composed into two distinct constructs, 'cleanness or smart' factor and 'gorgeousness' factor, which demonstrated sensitivity to changes in brightness, contrast, color, and tint in the TV picture quality, except for changes in sharpness.

• Korean Journal of Social Welfare
• /
• v.59 no.1
• /
• pp.171-197
• /
• 2007

This study attempts to explore and describe the public's image on social welfare professionals in the comparison with other helping professionals. Using a sample (n=1,156) collected from high school students, college students, and citizens, this study comparatively examines the public's image on five helping professionals such as social welfare professionals, psychiatrists, clinical psychologists, nurses, and pastoral counselors. In measuring the public's image, this study uses a semantic differential scale that is composed of 16 pairs of adjective words. In overall, among five helping professionals, social welfare professionals is the most positively recognized; thus, its total score is the highest. By using correspondence analysis, social welfare professionals belong to the second quadrant that includes "practical" and "comfortable". As have discussed in the previous research, however, the analysis reveals that social welfare professionals' expertise is not highly evaluated. On the other hand, ANOVA shows that unlike statistically significant differences between social welfare professionals and other helping professionals, there is no statistically significant difference between social welfare professionals and clinical psychologists. Finally, MANOVA shows that except for gender social demographic variables do not make any differences in the public's image on social welfare professionals. In conclusion, this study discusses diverse directions and measures to strengthen social welfare professionals' competencies including expertise and promote the public's image social welfare professionals.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.28 no.3
• /
• pp.88-96
• /
• 2000

The objective of this study is to evaluate the preference and visual characteristic of users according to the location of benches at urban community parks. The types of benches are separated into four patterns and located in four representative places at urban community parks. Each relations between visual preference and adjective related factors are calibrated by the estimated results of Pearson correlation coefficient. Moreover, the factors which affect the visual preference are obtained by multiple regression analysis and to calibrate the each factors significant level, the method of multivariate variance analysis is applied. The results of this study are summzrized as belows: 1. Four types of factors which consist the visual characteristic are classified as emotional factor of visual images(aesthetic factor(F1), texture related factor(F2)) and physical factor(physical factor(F3), transformable factor(F4)). Each factor's eigenvalue is appears as 5.27∼1.78 and the eigenvalue of emotional factor of visual images is more higher than the physical factor. 2. The correlation coefficient between visual preference according to the location of benches(X21) and aesthetic factor(f1) is estimated as 0.79, which is highest value among the four factors. And the correlation coefficient of texture related factor(f2), physical factor(F3) and transformable factor(F4) is estimated as 0.14, 0.04 and 0.08 respectively. 3. The visual preference of users according to the location of benches is greatly affected by the emotional factor of visual images(F1, F2) and the physical factor(F3, F4) are poorly related. The results of this study suggest the effective guidelines for the location of leisure facilities. Moreover the design and planning of leisure facilities at the urban community park have to be reexamined. What must be examined from now on is as follows: First, the preference research of rest facilities in the urban park through the multiple approach must be carried out continuously. Second, the research about the visual quality of the environmental sight observed in sitting on the bench as well as the visual quality of the showed object and place needs to be supported. Nevertheless, through this study the utilization into the useful data of the plan and the design for the systematic disposition of landscape architecture equipments centered on the users can be expected.

• Science of Emotion and Sensibility
• /
• v.15 no.1
• /
• pp.87-96
• /
• 2012

This paper proposes a Image retrieval system that searches the closest images to the user's emotional need and displays images with higher ratings of color harmony from Moon-Spencer's Color Harmony Theory first. Once an emotional adjective is placed, the system searches for images with colors that contain more elements derived from Aesthetic Measure results and displays in such order. In order to test reliability of the proposed emotion retrieval method based on Moon-Spencer's Color Harmony Theory, this study compared the order of Aesthetic Measure results with the user satisfaction ratings using 200 sample images. The analysis demonstrated that the participants' average satisfaction on 15 emotion adjectives selected for the study was 5.0 on a 7-point Likert scale. Correlation analyses were performed to test the consistency the orders between Aesthetic Measure values and user satisfaction ratings. Positive correlations above R=.5 were observed in all 14 emotion words except "Clear". These findings prove the potential of the proposed emotion retrieval system based on Moon-Spencer's Color Harmony Theory to effectively reflect user emotion in such visual stimulus search as image database.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.3
• /
• pp.359-364
• /
• 2011

The study uses department of the sensitivity and fuzzy reasoning, one of artificial intelligence algorithms, so that develop LED lighting system based on fuzzy reasoning for systematical control of the LED color temperature. In the area of sensitivity engineering, by considering the relation between color and emotion expressed as an adjective word, the corresponding sensitivity word can be determined, By taking into consideration the relation between the brain wave measured from the human brain and the color temperature, the preferred lesson subject can be determined. From the decision of the sensitivity word and the lesson subject, we adjust the color temperature of RGB (Red, Green, Blue) LED. In addition, by using the information of the latitude and the longitude from GPS(Global Positioning System), we can calculate the on-line moving altitude of sun. By using the sensor information of both temperature and humidity, we can calculate the discomfort index. By considering the altitude of sun as well as the value of the discomfort index, the illumination of W(white) LED and the color temperature of RGB LED can be determined. The (LED) sensitivity lighting control system is bulit up by considering the sensitivity word, the lesson subject, the altitude of sun, and the discomfort index The developed sensitivity lighting control system leads to more suitable atmosphere and also the enhancement of the efficiency of lesson subjects as well as business affairs.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.1
• /
• pp.75-83
• /
• 2015

As the importance of realistic game character in order to cause the interest of player is increased, it is necessary to develop the character that acts like a man by applying the human characteristics in the step of game character design. Formerly, there is a limit to create the human-like character because there is no set the character's personality in the game developing level. In this paper, therefore, we propose the correlation between Five Factor Model and Ego-state for game character. Five Factor Model and Ego-state are theories about person's characteristic. Five Factor Model is personality description method. Ego-state has an emphasis on internal mental processes directly from observable behaviors. In this regard, these theories could be used to the character defined its personality and designed to act by personality. To do this, it needs to determine the relations between Five Factor Model and Ego-state. Therefore we seek for the relations between two theories using Adjective Check List(ACL) and analysis their results with surveys. In the future, it is expected to construct a personality model using these analysis results, and develop the character based on realistic behavior.