• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.450-452
• /
• 2020

기술의 발전과 함께 사용자에게 가까이 자리 잡은 소셜 네트워크 서비스는 이미지, 동영상, 텍스트 등 활용 가능한 데이터의 수를 폭발적으로 증가시켰다. 작성자의 감정을 포함하고 있는 텍스트 데이터는 시장 조사, 주가 예측 등 다양한 분야에서 이용할 수 있으며, 이로 인해 긍부정의 이진 분류가 아닌 다중 감정 분석의 필요성 또한 높아지고 있다. 본 논문에서는 딥러닝 기반 감정 분류에 심리학 이론의 기반 감정 모델을 활용한 결합 모델과 단일 모델을 비교한다. 학습을 위해 AI Hub에서 제공하는 데이터와 노래 가사 데이터를 복합적으로 사용하였으며, 결과에서는 대부분의 경우에 결합 모델이 높은 결과를 보였다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.121-123
• /
• 2022

본 현대사회는 문명적, 기술적, 산업적으로 발전함에 따라 그에 상응하는 절도, 폭행, 살인 등 중대범죄의 범위를 벗어나 이념과 국가, 종교, 등 가치관과 사상에 따른 테러 사건 등 국제적인 범죄도 증가하고 있는 추세이며, 국제사회는 중대범죄 및 전쟁의 공포보다 예측 불가능, 막대한 대량 피해를 불러오는 테러에 의한 공포심을 더 비중 있게 대하는 현실에 직면했다. 테러범죄는 개인을 넘어 다중에게 피해를 입힐 수 있는 범죄인만큼 대중에게 경각심과 위험성을 알리기 위해선 구체적이고 손쉽게 이해할 수 있는 명확성이 필요하다. 테러는 수년간 다양한 방식과 개념들이 증식했으며 피해 또한 더 이상 소규모인원, 특정인을 향한 계획적인 범행에서 불특정 다수를 향한 뉴테러리즘식의 테러로 발전하고 있어 안보의 개념에도 영향을 미치고 있다. 따라서 대한민국 역시 언제까지나 테러의 위험성으로부터 안전을 확신할 수 없기 때문에 국내 정서에 맞는 테러 대응방안과 시스템 구축을 통해 뉴테러리즘의 발생 가능성을 염두 하고 대비할 필요가있다.

• Korean Journal of Cognitive Science
• /
• v.22 no.1
• /
• pp.39-55
• /
• 2011

People tend to overestimate their emotional reactions to events such as physical handicap and buying a new car in the future. Students overestimate their reactions to a future grade as compared to their reactions after receiving the grade. Impact bias refers to people's tendency to overestimate the intensity and the duration of emotional reactions to a future event. The present study explored whether impact bias occurs to risky objects such as nuclear energy, genetically engineered food, and mobile phone. Participants were asked to predict their emotional reactions at three time points, that is, at the present, a week after, and a year after. They predicted their reactions before and after two debiasing tasks. The present study demonstrated a different pattern of impact bias at three time points: A largest bias was observed a week after the present. A defocalism manipulation has eliminated the impact bias whereas an adaptation manipulation has not. Several points were discussed regarding the difference between the previous and the present work.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.419-430
• /
• 2014

The main object of the study is to investigate factors affecting the suicide ideation. According to the socioemotional selectivity theory, because of limitation of life time, the family relationship is more important for elderly than young or middle aged group. Based on this theory authors hypothesizes that the familism may show negative relationship with suicide ideation only in elderly group. The data for the study comes from the survey titled understanding on the successful aging of Korean people conducted in 2008. The sample size of the survey is 1,000 and the survey was conducted by the face to face interview with the standardized questionnaire. According to the analysis, familism shows negative relationship with suicide ideation only in elderly group, not in young or middle adult group.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.4
• /
• pp.353-371
• /
• 2010

Library anxiety has been recognized as one of the representative fields that concerns user's affectivity in library and information study. Considerable library users have been discovered to experience library anxiety according to researches. Although digital libraries are becoming more popular changing drastically from traditional libraries, few studies have addressed the measurement of digital library anxiety(DLA). The purpose of this study is to develop and validate a multidimensional digital library anxiety scale(DLAS) based on previous research in library anxiety and digital libraries. It will become possible to define the construct of DLAS, provide its underlying dimensionalities, and find out how much they explain the construct. Through the exploratory factor analysis, DLAS has been developed with 39 items representing seven distinct factors which were interpreted as affect, resources, know-how, security, language, technology, and task explaining 51.165% of DLA. Also, DLAS' characteristics about demographic variables and use pattern were found through the T-test and ANOVA analysis for each factor.

• Journal of the Korea Convergence Society
• /
• v.8 no.3
• /
• pp.141-150
• /
• 2017

The purpose of this study was to identify relationship among the depression, social support and quality of sleep in elderly insomnia patients. A total of 143 patients with insomnia diagnosed according to DSM-IV criteria. Quality of sleep, depression, and social support were measured using a self structured questionnaire and participant's medical records were reviewed for obtaining their clinical information. Quality of sleep was positively associated with depression(r=.255, p<.05), and negative correlation with social support(r=-.270, p<.001). The significant factors for quality of sleep were information support(${\beta}=-0.406$, p<.05) and affectionate support(${\beta}=-0.525$, p<.05). These factors explained 13.2% of the variance in quality of sleep. The elderly patients suffering the insomnia need the nursing interventions considering information support and affectionate support in order to improve sleep quality.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.281-286
• /
• 2012

In the growing standard of people's lives, we want desire to create eco-friendly water space what is called the Green Technology that is in the limelight. These green space is introduced the cultural contents and we use the water, music, and nature as tool of emotional verbalism. Presently, when we want to make scenario, water landscape scenario is made by director. but these systems have some disadvantages as the cost and limitation of direction. There is a growing interest in the integrated control system based on PC and Internet. In this paper, it is about fountain control system. Previous research area was only one using programmable logic controller or industrial PC. we proposed the development of intelligent green fountain culture system for healthy emotional self-concept. And we made automatic weather sensing system that is designed by the intelligent green fountain culture system to estimate the time-variant system.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.57-66
• /
• 2023

In this study, we propose a novel research framework for the recommendation system that can estimate the user's emotional state and reflect it in the recommendation process by applying deep learning techniques and emotion AI (artificial intelligence). To this end, we build an emotion classification model that classifies each of the seven emotions of angry, disgust, fear, happy, sad, surprise, and neutral, respectively, and propose a model that can reflect this result in the recommendation process. However, in the general emotion classification data, the difference in distribution ratio between each label is large, so it may be difficult to expect generalized classification results. In this study, since the number of emotion data such as disgust in emotion image data is often insufficient, correction is made through augmentation. Lastly, we propose a method to reflect the emotion prediction model based on data through image augmentation in the recommendation systems.

• Korean Journal of Culture and Social Issue
• /
• v.22 no.3
• /
• pp.431-453
• /
• 2016

The current study explored relationships of learned helplessness, depression, organizational commitment and job engagement. We investigated the mediating effects of depression between learned helplessness and organizational commitment and between learned helplessness and job engagement. Also, this study examined the moderating effects of calling between depression and organizational commitment and between depression and job engagement. we collected data from 310 military officers working at ROK Air Force air wing located at Gyeonggi-do. The results showed that depression mediated between learned helplessness and organizational commitment and between learned helplessness and job engagement, respectively. The results showed that calling moderated organizational commitment, job engagement. In the discussion section, we discussed about theoretical and practical implications of this study.

• The Journal of the Korea Contents Association
• /
• v.22 no.6
• /
• pp.453-466
• /
• 2022

This study attempted to examine the role of gender roles in psychological distress of Korean adult men. Specifically, it was attempted to verify whether compliance with multidimensional male gender roles predicts psychological distress through gender role conflict. To this end, this study was conducted on 358 male participants aged 19 to 39 using the Korean Conformity to Masculine Norm Inventory, Korean Male Gender Role Conflict Scale, and General Health Questionnaire. As a result of the study, it was found that the influence on psychological distress through male gender role conflict was different depending on the sub-factors of the male gender norm. The sub-factors of masculine norms, 'power and control', 'job - independence', and 'emotion suppression', were statically predicted psychological distress through the medium of 'fear for femininity', which is a sub-factor of gender role conflict. Meanwhile, among the male norms, 'male leadership' and 'family support' had negative direct effects on psychological distress, and the indirect effects through gender role conflict were not significant. The results of this study suggest that the sub-factors of male norms have different functions for psychological distress, and in particular, the dysfunctional role of male norms can be caused by negative emotions about femininity during gender role conflict.