• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1997.11a
• /
• pp.183-188
• /
• 1997

안구의 운동은 시각 환경에서의 진행중인 정보처리와 관련된 지각적, 인지적 과정을 밀접히 반영하는 중요한 지표로서, 특히 공간 지각과의 상관은 비교적 명확히 확립되어 있다. 본 연구는 공간지각에 관여하는 안구운동의 특성을 파악하여, 공간지각을 반영하는 안구운동 지표를 개발한다는 목표 아래, 피험자가 느끼는 공간의 확장과 축소의 특성을 이중도약과제(double-step paraeigm)를 사용하여 관찰한 것이다. 이중도약과제는 도약(saccadic)안구운동의 오차를 유발시키는 실험기법으로, 두개의 시각자극을 하나씩 연속적으로 보여주되, 두번째 자극은 안구운동이 일어나는 도중에 제시하는 것으로서, 인위적으로 왜곡된 공간에 대한 피험자의 공간적응을 관찰하는데 사용되었다. 이 과제는 다시 자극의 이차도약 방향에 따라 축소감 조건과 확장감 조건으로 나뉘었고, 머리운동의 역할을 판별하기 위해 머리를 고정한 조건과 머리를 자유롭게한 조건으로 분류되었다. 그 결과 머리가 고정된 상태에서는 축소감 조건에 대한 적응이 확장감 조건에서보다 더 빨리 일어나고, 그 적응후의 시선이동의 변화량에서도 축소감 조건이 더 크게 나타났다. 또한 머리를 자유롭게 할 공간 지각의 정확성이 증가하며, 축소감과 확장감 경험속도의 차이가 약 49.2%까지 해소되었으나, 여전히 축소감의 경험이 더 잘 일어났다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.1-4
• /
• 2019

본 연구에서는 적외선 카메라 기반의 비접촉식 측정 방법을 이용하여 동공 반응 데이터를 수집하여 공감의 사회감성을 객관적이고 정량적으로 추정하는데 그 목적이 있다. 실험에는 10명(남 6명, 여 4명, M ± SD = 24.17 ± 2.16세)의 피험자가 참여하였다. 30초의 참조 데이터 측정 후, 공감 유무에 따라 과제는 얼굴 표정 모방 과제와 얼굴 표정 자발적 표현 과제로 구분되어 두 사람은 표정으로 상호작용하였고, 2번씩 반복 진행하며 적외선 카메라를 통해 동공을 촬영하였다. 이진화 및 원형 윤곽선 검출법의 영상처리를 활용하여 동공 데이터를 수집하였고, 이동 평균 기법을 활용해 눈깜빡임 노이즈를 제거하고 동공 크기 개인차로 데이터 표준화를 진행하였다. 공감 유무에 따른 동공 크기 데이터는 정규성 검증 및 독립표본 t검정을 통해 통계적 유의성을 확인하였다. 분석결과, 공감하는 경우(M ± SD = 0.508 ± 1.278)와 공감하지 않은 경우(M ± SD = 1.681 ± 0.968) 동공 크기가 통계적으로 유의미한 차이를 보였다(t(18) = -2.313, p = 0.033). 판별분석을 통해 동공 크기에 따른 공감의 유무를 추정하는 규칙을 정의하였다. 본 연구에서 제안한 동공 크기 데이터를 이용한 공감의 사회감성 추정 기술은 비접촉식 카메라 기반의 기술로 스마트 글래스와 접목되어 다양한 분야에 활용도가 높을 것으로 기대된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.232-235
• /
• 2011

지식표현은 일반적으로 논리, 규칙, 프레임 또는 의미망 형태로 표현되며, 최근에는 의미망을 이용한 온톨로지 형태로 표현되고 있다. 이러한 지식표현 방법은 개념을 설명하는 문맥적인 정보나 개념들 간의 구조적인 정보를 이용하여 개념에 대한 지식을 논리적으로 표현하는데 중점을 두었다. 하지만, 지식표현에 사용되는 의미정보는 사람에 의해 수집되고 정제되기 때문에 많은 시간, 비용 및 인력이 필요하다는 한계가 있고, 새로운 의미를 추가하거나 기존의 의미를 수정하는 것이 매우 어렵다는 한계가 있다. 색채는 특정 대상이나 개념에 대한 의미, 연상, 상징 등 객관적인 특징 뿐 아니라 시대, 나라, 문화와 같은 사회적 배경을 반영하기 때문에, 정보를 제공하고 감성을 전달하는 효과적인 수단으로 사용되고 있다. 이에 본 논문은, 색채를 이용한 의미정보모델 구축을 위해, 색채정보를 수집하고 정량적으로 분석하는 방법을 제안한다. 긍정/부정/불안/중립으로 구성된 감성어휘 273개를 이용하여 이미지를 수집한 결과 총 130,944개의 이미지를 수집하였다. 이미지에는 여러 가지 사물, 행동, 배경, 색채 등 다양한 정보가 혼재되어 있어 감성어휘와 연관된 색채를 구별하기 어렵기 때문에 이미지를 직관적으로 설명할 수 있는 사용자 태그를 별도로 수집하였다. 태그는 총 2,836,395개를 수집하였고 각 이미지와 그룹에서의 가중치를 구하였다. 태그의 가중치를 통해 이미지가 그룹 내에서 갖는 중요도를 판별하였고, 각 그룹 별로 상위 30%의 이미지를 추출하여 대표 색채를 분석하였다.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.1-15
• /
• 2022

In this study, text analysis was performed on the mealkit product review data to identify factors affecting the evaluation of the mealkit product. The data used for the analysis were collected by scraping 334,498 reviews of mealkit products in Naver shopping site. After preprocessing the text data, wordclouds and sentiment analyses based on word frequency and normalized TF-IDF were performed. Logistic regression model was applied to predict the polarity of reviews on mealkit products. From the logistic regression models derived for each product category, the main factors that caused positive and negative emotions were identified. As a result, it was verified that text analysis can be a useful tool that provides a basis for maximizing positive factors for a specific category, menu, and material and removing negative risk factors when developing a mealkit product.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2013

This study examined that how precisely MFCC, LPC, energy, and pitch related parameters of the speech data, which have been used mainly for voice recognition system could predict the vocal emotion categories as well as dimensions of vocal emotion. 110 college students participated in this experiment. For more realistic emotional response, we used well defined emotion-inducing stimuli. This study analyzed the relationship between the parameters of MFCC, LPC, energy, and pitch of the speech data and four emotional dimensions (valence, arousal, intensity, and potency). Because dimensional approach is more useful for realistic emotion classification. It results in the best vocal cue parameters for predicting each of dimensions by stepwise multiple regression analysis. Emotion categorizing accuracy analyzed by LDA is 62.7%, and four dimension regression models are statistically significant, p<.001. Consequently, this result showed the possibility that the parameters could also be applied to spontaneous vocal emotion recognition.

• Science of Emotion and Sensibility
• /
• v.25 no.2
• /
• pp.87-100
• /
• 2022

People who spend more time alone tend to report higher levels of loneliness. However, whether people experience loneliness in solitude can differ The current research investigated the role of a sense of power as a predictor of loneliness among people who lack social interaction. investigated factors predicting loneliness in people with little social time large-scale survey data. As a result of discriminant analysis, a sense of power was verified as a factor that lonely non-lonely groups. a sense of power As a result, a causal relationship between a sense of power and social loneliness was confirmed. When people feel alone, a high sense of power can work as a buffer against loss of belongingness and the experience of social loneliness. This research focused on psychological rather than situational factors to alleviate loneliness in the current situation where social encounters are limited due to the increase of single-person households and the 19 pandemic.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.141-155
• /
• 2017

As the use of SNS becomes more active, many people are posting their thoughts about specific events in their SNS in the form of text. As a result, SNS is used in various fields such as finance and distribution to conduct service satisfaction surveys and consumer monitoring. However, in the transportation area, there are not enough cases to utilize unstructured data analysis such as emotional analysis. In this study, we developed an emotional analysis methodology that can be used in transportation by using highway VOC data, which is atypical data collected by Korea Expressway Corporation. The developed methodology consists of morpheme analysis, emotional dictionary construction, and emotional discrimination of the collected unstructured data. The developed methodology was verified using highway related tweet data. As a result of the analysis, it can be guessed that many information and information about the construction and the accident were related to the highway during the analysis period. Also, it seems that users complain about the delay caused by construction and accident.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.97-113
• /
• 2016

Due to the growth of internet data and the rapid development of internet technology, "big data" analysis is actively conducted to analyze enormous data for various purposes. Especially in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of existing structured data analysis. Various studies on sentiment analysis, the part of text mining techniques, are actively studied to score opinions based on the distribution of polarity of words in documents. Usually, the sentiment analysis uses sentiment dictionary contains positivity and negativity of vocabularies. As a part of such studies, this study tries to construct sentiment dictionary which is customized to specific data domain. Using a common sentiment dictionary for sentiment analysis without considering data domain characteristic cannot reflect contextual expression only used in the specific data domain. So, we can expect using a modified sentiment dictionary customized to data domain can lead the improvement of sentiment analysis efficiency. Therefore, this study aims to suggest a way to construct customized dictionary to reflect characteristics of data domain. Especially, in this study, movie review data are divided by genre and construct genre-customized dictionaries. The performance of customized dictionary in sentiment analysis is compared with a common sentiment dictionary. In this study, IMDb data are chosen as the subject of analysis, and movie reviews are categorized by genre. Six genres in IMDb, 'action', 'animation', 'comedy', 'drama', 'horror', and 'sci-fi' are selected. Five highest ranking movies and five lowest ranking movies per genre are selected as training data set and two years' movie data from 2012 September 2012 to June 2014 are collected as test data set. Using SO-PMI (Semantic Orientation from Point-wise Mutual Information) technique, we build customized sentiment dictionary per genre and compare prediction accuracy on review rating. As a result of the analysis, the prediction using customized dictionaries improves prediction accuracy. The performance improvement is 2.82% in overall and is statistical significant. Especially, the customized dictionary on 'sci-fi' leads the highest accuracy improvement among six genres. Even though this study shows the usefulness of customized dictionaries in sentiment analysis, further studies are required to generalize the results. In this study, we only consider adjectives as additional terms in customized sentiment dictionary. Other part of text such as verb and adverb can be considered to improve sentiment analysis performance. Also, we need to apply customized sentiment dictionary to other domain such as product reviews.

• Journal of Food Hygiene and Safety
• /
• v.36 no.4
• /
• pp.331-341
• /
• 2021

DNA barcode sequences of commercial seafood products, which are difficult to morphologically discriminate, were analyzed to determine cases of food fraud. The gene sequences were analyzed by amplifying the COX I (cytochrome C oxidase subunit I) gene region of mitochondrial DNA, which is mainly used for species identification. The DNA barcode sequences were compared with the gene sequence of each fish registered in the US National Center for Biotechnology. A total of 46 processed seafood products (12 Pagrus majo, 4 Oplegnathus fasciatus, 7 Dentex tumifrons, 2 Acanthopagrus schlegelii, 7 Oreochromis niloticus, 6 Branchiostegus japonicus, 8 Branchiostegus albus) were investigated. Having DNA sequence identity of more than 97% was judged as the same species. As a result of this study, no cases of forgery and alteration were detected. However, some disparities in the commercial names used in local markets and the standard names given in the Korea Food Code were found, which may cause confusion for consumers. It is therefore suggested that the standard name or scientific name be displayed on seafood product labels.

• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.359-372
• /
• 2019

Metabolic syndrome is deeply related with risks of chronic disease and mortality. Furthermore, the metabolic syndrome disorder in childhood and adolescence usually tends to lead to a number of cardiovascular disease in the stage of adulthood. In this sense, metabolic syndrome needs to be investigated seriously. The purpose of this study is therefore to prove the relationship between dietary habits(high carbohydrate, high calorie) and metabolic syndrome among adolescents. We also aim to clarify the relationship between emotional factors perceived by adolescents and metabolic syndrome. Our empirical results based on KNHANES dataset significantly demonstrates that the HDL-cholesterol is a decisive factor for the diagnosis of metabolic syndrome disorder. Additionally, emotional experience factors such as stress also show significant effects in difference of adolescents' metabolic syndrome.