• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.495-500
• /
• 2020

뉴스 기사는 반드시 객관적이고 넓은 시각으로 정보를 전달하지 않는다. 따라서 뉴스 기사를 기존의 추천 시스템과 같이 개인의 관심사나 사적 정보를 바탕으로 선별적으로 추천하는 것은 바람직하지 않다. 본 논문에서는 최대한 객관적으로 다양한 시각에서 비슷한 사건과 인물에 대해서 판단할 수 있도록 유사도 기반의 기사 추천 모델을 제시한다. 길이가 긴 문서 사이의 유사도를 측정하기 위해 GPT2 [1]언어 모델을 활용했다. 이 과정에서 단방향 디코더 모델인 GPT2 [1]의 단점을 추가 학습으로 개선했으며, 저장 공간의 효율과 핵심 문단 추출을 위해 BM25 [2]함수를 사용했다. 그리고 준 지도 학습 [3]을 통해 유사도 레이블링이 되어있지 않은 최신 뉴스 기사에 대해서도 자가 학습을 진행했으며, 이와 함께 길이가 긴 문단에 대해서도 효과적으로 학습할 수 있도록 문장 길이를 기준으로 3개의 단계로 나누어진 커리큘럼 학습 [4]방식을 적용했다.

• Industry Promotion Research
• /
• v.8 no.4
• /
• pp.187-200
• /
• 2023

The purpose of this paper is to correspond to four-elements in astrology theory, an intellectual from ancient times, that show personality temperament among MBTI, a representative personality type test in modern times, furthermore, by examining 16 personality type cards in tarot, a play culture and fortune telling culture in which the four-element theory is integrated in symbols, it is a comparative consideration that connects the characteristics of the character types contained in them to the 16 personality types of MBTI. The four preferred types of MBTI are Extravesion(E) and Introversion(I), Sensing(S) and Intuition(N), Thinking(T) and Feeling(F), Judgment(J) and Perception(P). Among them, Western four-elements were able to respond to Fire, Water, Air, and Earth in the order of NF(iNtuitive Feeling Type), SF(Sensory Feeling Type), NT(iNtuitive Thinking Type), and ST(Sensory Thinking Type). This is a result that can be derived by comparing individual personality theory and MBTI temperament theory among the symbols contained in ancient astrological theories. And the classification of boys, knights, queens, and kings in the four classes of person cards could be divided according to the MBTI attitude index. The boy showed an adaptive introvert using I and P, the knight showed an adaptive extrovert using E and P, the queen showed a decisive introvert using I and J, and the king showed an adaptive extrovert using E and J.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.870-873
• /
• 2010

인터넷의 보편화와 사용자 증가는 사회에 많은 변화를 가지고 왔다. 많은 변화 중 인터넷을 통한 뉴스 제공은 종이 신문과는 다르게 인터넷 사용이 가능한 모든 사람들에게 뉴스를 제공 받을 수 있게 되었으며 언제든 원하는 기사를 다시 제공 받을 수 있게 해주었다. 이러한 이유로 인터넷 뉴스는 다양한 연령대의 사용자들이 뉴스를 접할 수 있게 되었고 인터넷 뉴스를 읽은 많은 사용자중 해당 뉴스에 댓글을 남기게 되었다. 이러한 댓글은 사용자의 의견을 내포하고 있는 것으로 본 논문에서는 사용자들이 남긴 댓글에 오피니언 마이닝을 적용하여 사용자 의견을 추출하여 특정 인물에 대한 인지도를 찾아내는 기법을 제시한다.

• The Journal of the Korea Contents Association
• /
• v.21 no.9
• /
• pp.806-816
• /
• 2021

This study aims to describe the reporting patterns of articles on the Emergency Grant for all citizens(EGAC) and compare the reporting attitudes by newspaper companies. The main results are as follows: First, conservative newspapers reported more than four times as much coverage of EGAC as liberal newspapers. Newspaper articles reported during the week of the National Assembly Election Day accounted for about a quarter of the total, and 79.1% of the articles were reported in the political realm of newspapers, and only 2.8% in the social realm. Second, a conservative newspaper reported a critical attitude toward EGAC at 52.6% and favorable articles at 5.3%. On the other hand, in a liberal newspaper, critical articles were 17.1% and favorable articles were 37.1%. The inefficiency of selectivism was reported as the basis for the argument in favor, and concerns about the burden of deterioration in the financial soundness of the opponents were reported the most. Politicians are the most cited sources of information in articles. Finally, in prior to policymaking, the proportion of the media in favor of and against the news was similar, and the proportion of articles with a neutral attitude accounted for more than half. And in the specific method discussion stage, the articles in favor of the article exceeded the proportion of articles on the opposite side.

• The Science & Technology
• /
• v.31 no.2 s.345
• /
• pp.86-88
• /
• 1998

3년 전 우리나라 신문들은 조선조의 선조때 정평구라는 발명가가 세계 최초로 비행기를 만들었다는 기사를 보도해 화제를 모았었다. 비록 임진왜란에 얽혀 생겨난 전설이 확대된 이야기라고는 하지만 1923년 한글학자 권덕규가 쓴 책이 그런 내용이 있었다는 것이다. 또 19세기 초엔 윤달규도 비행기를 만드는 방법을 기록했었다는 구전이 있어 우리나라 옛 발명가 ㆍ기술자들의 배경을 연구해 보는 것은 우리의 과제가 아닐 수 없다.

• 프린팅코리아
• /
• s.7
• /
• pp.160-161
• /
• 2003

지난 11월 10일 모 인터넷 신문이 한 인쇄인의 죽음을 보도하자 기사 하단에는 고인의 명복을 비는 글들이 3일 동안 100여건이 넘게 남겨졌다. 또한 보라매 병원 영안실에 마련된 고인의 빈소에는 방용석 노동부 장관을 비롯해 김근태, 장영달, 심재권, 이강래, 이창복 의원 등 이른바 재야출신 정 관계 인사들의 화환이 도착해 고인의 지난 이력을 말해 주고 있었다. 인터넷상의 짤막한 글이나 조화로 산 자들의 예우를 받은 인물은 고세진인쇄 강운기 사장. 을지로 중앙극장 건너편 골목길을 지나 마스터 기계 두 대가 전부인 조그마한 인쇄사를 운영했던 고강운기 사장에 대한 그들의 예우는 평소 고인에게 갚을 수 없는 빚을 졌기 때문이다.

• Cartoon and Animation Studies
• /
• s.44
• /
• pp.85-116
• /
• 2016

This is the in-depth research dealing with Animatoon, the only animation-specialized magazine in Korea. By examining articles provided under the 'Animatoon Report' category, which is one of article categories set by the publisher, this research tries to find out the topic of articles and examine the tendency of topic. 'Animatoon Report' is chosen because the category title does not clearly show characteristics of articles, but has the second largest number of articles among all categories. First, the articles of the first ten years (1995-2005) has the largest number of pages as well as images, which means each article of this period tries to enrich its contents. Second, the role of magazine reporters are not critical considering the number of articles written by reporters are smaller than those made by the editorial department. Third, articles tries to deal with diverse issues and are mostly placed in front of the magazine. Fourth, in early days, articles used to provide the 3~5 lines of introductory summaries, but changed into provide the lead, the Korean and English subtitle, and so on. Fifth, articles mostly focus on issues of animation and Korea rather than other areas and countries. The results on the basis of article type are as follows. Among the types of people, work, organization/company, event, policy/industry, and etc, the policy/industry type has the largest amount of articles, and articles on the policy and those on the industry shows similar number of articles. Second, the event type has the second largest number of articles even though there are several separate categories only for the event. Third, articles in the et cetera type are often seen in early days because Animatoon who did not systemize the company itself focused on animation history and production techniques. Fourth, articles both on the people and the work type are consistently seen through the whole time period, but those on organization/company and event has more and more articles as time passes. In conclusion, it is possible to mention that the 'Animatoon Report' type shows more interest in policy and industry, and its interest on both issues are consistently seen from 2001 to 2015.

• Journal of the Korea Convergence Society
• /
• v.10 no.12
• /
• pp.345-352
• /
• 2019

The purpose of this study was to investigate the types and characteristics of collective expression of aggression by sport situation factors in international sport games. For that, each 5 articles on male and female Korean team matches in 2018 Asian games with most replies and their each 100 most recommended replies were collected and analyzed. As the conclusions, first, there were more frequent aggression in critical articles on Korean's losing, and the public sympathy on sport situation effected on collective expression of aggression. Second, the types of collective expression showed almost same frequency as hurling abuses, ability disparagement, and personal attack, and the targets were the main person of the background situation. This study could be valued with the new research perspectives with sport situation factors on the relations among sport and aggression.

• Journal of the Daesoon Academy of Sciences
• /
• v.47
• /
• pp.105-138
• /
• 2023

The purpose of this study is to examine the significance of various figures in The Canonical Scripture and their contents. The Canonical Scripture (jeon-gyeong 典經) is a record of the beliefs and deeds of Kang Jeungsan, composed through the memories of the followers of Kang Jeungsan who followed the words of The Canonical Scripture. In other words, The Canonical Scripture is understood as the scripture of Daesoon Jinrihoe that contains the religious deeds and teachings of Kang Jeungsan. It is divided into seven parts and 17 chapters. Those seven parts, some of which contain more than one chapter, are as follows: Acts, Reordering Works, Progress of the Order, Dharma, Authority and Foreknowledge, Saving Lives, and Prophetic Elucidations. In particular, The Canonical Scripture records the deeds of historical figures from both China and Korea, and this prominently includes the life history of Kang Jeungsan, and this is an especially pronounced feature of the sections Acts, Progress of the Order, and Prophetic Elucidations. In addition, each chapter describes the teachings and faith-inspiring acts of Kang Jeungsan and presents the gist of the Daesoon Thought while referring to the lives and actions of various historical figures. In this paper, introductions to the figures that appear in each section are provided to help readers better understand the contents of The Canonical Scripture. Therefore, this study focuses on the major figures introduced in The Canonical Scripture in connection with the religious values of Daesoon Thought. Through this, a contribution is made to the academic development of Daesoon Thought by specifically exploring and examining the contents of the figures who appear in The Canonical Scripture. This is a surprisingly underdeveloped area of study in Daesoon Thought.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2021

In the political field of news articles, there are polarized and biased characteristics such as conservative and liberal, which is called political bias. We constructed keyword-based dataset to classify bias of news articles. Most embedding researches represent a sentence with sequence of morphemes. In our work, we expect that the number of unknown tokens will be reduced if the sentences are constituted by subwords that are segmented by the language model. We propose a document embedding model with subword tokenization and apply this model to SVM and feedforward neural network structure to classify the political bias. As a result of comparing the performance of the document embedding model with morphological analysis, the document embedding model with subwords showed the highest accuracy at 78.22%. It was confirmed that the number of unknown tokens was reduced by subword tokenization. Using the best performance embedding model in our bias classification task, we extract the keywords based on politicians. The bias of keywords was verified by the average similarity with the vector of politicians from each political tendency.