• Informatization Policy
• /
• v.27 no.1
• /
• pp.92-114
• /
• 2020

The purpose of this study is to analyze people's motivations to use the National Petition service of CheongWaDae, the Presidential Office of Korea. The online space has been used as a testbed of deliberative democracy. In fact, a wide variety of public opinions are being formed and gaining sympathy through the E-Petitions and Daum's Agora. In this regard, President Moon's government launched a petition site to gather public opinions. For any petition agreed on by more than 20,000 people within 30 days, the relevant ministry or the President's office must provide answers or feedback. This study wants to figure out how this National Petition is different from previous platforms like Agora or E-Petitions and why it is so well-received by people. This study uses a mix of both qualitative and quantitative methods. First, we conducted a focus group interview to factorize experiences of using the National Petition into measurable constructs. Second, we did a survey o 156 Koreans who had experienced the National Petition. Results show that symbolism, usefulness, gratification, and trust have positive impact on continuous usage intention. This study argues that symbolism, usefulness, gratification, and trust factors should be in place rather than technical aspects in order to increase the actual participation of users on the online platform of deliberative democracy. In addition, this study is meaningful in that it examined how different the CheongWaDae's National Petition is from the existing platforms for collecting public opinions and analyzed factors that encourage continuous use.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.37-39
• /
• 2021

청와대 국민 청원 게시판은 중복되는 국민 청원글과 20만 이상의 동의를 받았지만 관리자의 검토로 인해 답변이 지연되는 청원글들이 존재한다. 이는 중복 청원으로 인해 청원 동의 인원이 분산되고 답변이 지연되는 문제로 인해 국민들의 불만을 일으킨다. 따라서, 유사한 청원글을 분류하고 동일한 청원 참여 기간 내 유사한 청원글 수를 기반으로 20만 명 이상의 동의를 받을 청원 예측 모델을 구축하였다. 본문 내용만을 LSTM 모델에 적용했을 때 68%의 정확도, 20만 명 이상의 동의를 받은 청원 글에 대해서는 Precision 60%, F1-score 60%이었으나 청원 동의 가능 기간 내 유사한 글의 개수, 본문 길이, 제목의 길이를 추가하였을 때 모델은 74%의 정확도와 20만 명 이상의 동의를 받은 청원 글에 대해 74%의 Precision, 70%의 F1-score로 본문 내용만으로 학습한 모델보다 예측력이 더 높았다.

• 월간낙농육우
• /
• v.37 no.2
• /
• pp.117-120
• /
• 2017

충청북도 청주시에 위치한 청원목장은 2012년 충북지역 최초로 '낙농체험목장'으로 선정되면서 낙농목장 현장교육과 유가공제품 판매, 숙성 치즈와 와인을 바탕으로 관광 상품을 개발하기 위해 노력하고 있다. 또한 직접 생산한 요구르트를 지역학교에 납품하는 것과 최고의 유가공 제품을 청와대에 납품하겠다는 꿈을 안고 낙농에 전념하고 있는 정원목장의 안용대 (40세) 후계자를 만나봤다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.2
• /
• pp.45-52
• /
• 2020

Since the opening of the national petition site, it has attracted much attention. In this paper, we perform topic analysis of the national petition site and propose a prediction model for answerable petitions based on deep learning. First, 1,500 petitions are collected, topics are extracted based on the petitions' contents. Main subjects are defined using K-means clustering algorithm, and detailed subjects are defined using topic modeling of petitions belonging to the main subjects. Also, long short-term memory (LSTM) is used for prediction of answerable petitions. Not only title and contents but also categories, length of text, and ratio of part of speech such as noun, adjective, adverb, verb are also used for the proposed model. Our experimental results show that the type 2 model using other features such as ratio of part of speech, length of text, and categories outperforms the type 1 model without other features.

• Journal of The Korean Association of Information Education
• /
• v.25 no.4
• /
• pp.633-640
• /
• 2021

Education related issues are social problems in which various groups and situations are intricately linked to each other. It is difficult to find issues by analyzing social phenomena related to education. Korean based text analysis can be analyzed in a quantitative. With the development of text analysis techniques, research results have been recently achieved, and it can be fully utilized to derive educational issues from text data in Korean. In this study, petition articles in the field of childcare/education were collected on the online-board of the Blue House National Petition website, and text analysis was used to derive issues in the education world. The analysis derived 6 topics through Latent Dirichlet Allocation(LDA) among topic modeling techniques. The association rules of major keywords were analyzed and visualized as graphs. In addition to deriving educational issues through the existing questionnaire, it can provide implications for future research directions and policies in that issues can be sufficiently discovered through text-based analysis methods.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.795-806
• /
• 2021

Recently, as text data through online channels have become vast, there is a growing interest in research that summarizes and analyzes them. One of the fundamental analyses of text data is to extract potential topics. Although the researcher may read all the data and summarize the contents one by one, it is not easy to deal with large amounts of data. Blei and Lafferty (2007) and Blei et al. (2003) proposed topic modeling methods for extracting topics using a statistical model. Since the text data is generally collected over time, it is worthwhile to monitor the topic's changes. In this study, we propose a topic index based on the results of the topic model. In addition, a control chart, a representative tool for statistical process management, is applied to monitor the topic index over time. As a practical example, we use text data collected from Blue House National Petition boards between March 5, 2018, and March 5, 2020.

• Journal of Venture Innovation
• /
• v.1 no.1
• /
• pp.129-143
• /
• 2018

When consulting with senior service user or his or her family members, employees of senior welfare facilities face a vertical relationship due to age rather than a horizontal relationship. Despite few cases reported, service users and the families afflict physical and mental pain on the employees through irrational demands, physical abuses, and verbal abuses. In particular, the Korean society has advocated the notion of respecting elders and thus emphasized members of society to provide unconditional support to those of old age. In reality, however, people who work at senior welfare facilities report the difficulty of providing supports to heavy demands in selfish complaints that are often impossible to fulfill. Starting from May 2018, there has been a petition to the Korean Blue House, seeking protective measures for 'Senior welfare facility professions who are exposed to violence'. The study conduct researches on the effect of job stress on the organizational commitment for senior welfare facility employees from suffering emotional labor. Furthermore, it also aims to point the difficulties that the professions face and the solutions that alleviate the conflicts between the rights of services users of senior welfare facilities and its staffs. The study surveyed 178 staffs who work in senior welfare facilities in Seoul and Gyeonggi Province as its research method. The collected data was analyzed by using IBM SPSS Statistics 24.0 to derive the general characteristics of the sample, reliability, feasibility analysis, correlation analysis, and verification of the research hypothesis. The study was able to conclude the following: First, the frequency of emotional expression of senior welfare facility staffs had negative(-) influences on job stress. Second, the incongruity of emotions of senior welfare facility staffs had negative(-) influences on job stress. Third, the incongruity of emotions of senior welfare facility staffs had negative (-) influences on job stress. Fourth, the job stress showed mediating effects between emotional labor factors and organizational commitment