• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.73-80
• /
• 2008

In this paper, an advertisement-keyword finding method using document clustering is proposed to solve problems by ambiguous words and incorrect identification of main keywords. News articles that have similar contents and the same advertisement-keywords are clustered to construct the contextual information of advertisement-keywords. In addition to news articles, the web page and summary of a product are also used to construct the contextual information. The given document is classified as one of the news article clusters, and then cluster-relevant advertisement-keywords are used to identify keywords in the document. We could achieve 21% precision improvement by our proposed method.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.53-57
• /
• 2010

현재 많은 포털 사이트에서는 인기가 있거나 중요도가 높은 키워드에 대해 정보를 제공해주는 태그 클라우드나 연관 검색어 등의 기능이 제공되고 있다. 하지만 대부분의 뉴스기사 페이지들은 날짜와 분야별로 기사들이 나열되어 있으며 사용자는 카테고리별로 나누어진 기사를 읽을 수만 있을 뿐 그 기사와 연관된 다른 기사의 정보에 대해서 한눈에 알아 볼 수 있는 방법은 미흡한 실정이다. 또한 연관 검색어 서비스도 사용자가 검색한 입력 내용을 기반으로 연관성 정도를 분석하여 객관성을 보장하지 못하고 있다. 본 논문에서는 기존의 태그 클라우드 방식에서 좀 더 나아가 축적된 뉴스 기사로 부터 검색 키워드와 밀접히 연관된 키워드를 추출하여 제공하는 기사 검색 시스템을 소개한다. 이 시스템은 사용자가 기사 검색을 하였을 때, 키워드와 가장 밀접한 기사를 검색해 주는 것뿐만 아니라 검색어와 관련된 연관 키워드들을 보여주고 연관된 키워드간의 관계성을 보여줌으로써 뉴스 기사들 속에 숨겨진 연관정보의 탐색을 가능하게 한다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.274-279
• /
• 2020

대화 시스템은 사용자의 입력 발화에 대해 적절하고 의미 있는 응답을 생성하는 시스템으로 seq2seq 구조를 갖는 대화 모델이 주로 연구되고 있다. 그러나 seq2seq 기반 대화 모델은 입력 발화와 관련성이 떨어지는 응답을 생성하거나 모든 입력 발화와 어울리지만 무미건조한 응답을 생성하는 문제가 있다. 본 논문에서는 이를 해결하기 위해 입력 발화에서 고려해야 하는 키워드를 찾고 그 키워드를 반영하는 응답을 생성하는 모델을 제안한다. 제안 모델은 주어진 입력 발화에서 self-attention을 사용해 각 토큰에 대한 키워드 점수를 구한다. 키워드 점수가 가장 높은 토큰을 대화의 주제 또는 핵심 내용을 포함하는 키워드로 정의하고 응답 생성 과정에서 키워드와 관련된 응답을 생성하도록 한다. 본 논문에서 제안한 대화 모델의 실험 결과 문법과 입력 발화와 생성한 응답의 관련성 측면에서 성능이 향상되었음을 알 수 있었다. 특히 관련성 점수는 본 논문에서 제안한 모델이 비교 모델보다 약 0.25점 상승했다. 실험 결과를 통해 본 논문이 제안한 모델의 우수성을 확인하였다.

• Journal of Korean Library and Information Science Society
• /
• v.48 no.1
• /
• pp.207-225
• /
• 2017

The aim of this study was to discover various Library and Information Science (LIS) research areas by examining similarities and differences between LIS journals in terms of keyword characteristics. To conduct this study, for the years from 2004 to 2016, the keywords of 6 international journals were downloaded from Scopus database (http://www.scopus.com), and the keywords of 4 Korean journals were downloaded from the RISS database (http://www.riss.co.kr). The characteristics of keywords were investigated by examining frequently used keywords and frequently used distinctive keywords pertaining to international and Korean journals. The distinctive keywords are referred to as the keywords that appear in one domain but not in another. The result of this study indicated the following: a) a frequency analysis of the keywords showed major research themes and unique traits concerning Korea. b) In general, the keywords used in Korean journals frequently reflected the library as a major subject area of research, while keywords used in international journals reflected bibliometrics and information retrieval as major subject areas of research. c) The overarching themes of each created dataset were clearly noticeable in frequently used distinctive keywords. d) Some keywords were bound by a nation or by a region due to their scope of usage. The important implication of this study is that both most frequently used keywords and most frequently used distinctive keywords seemed to adequately represent the LIS subject areas.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.295-297
• /
• 2002

본 연구에서는 정보 검색의 효과를 향상시키기 위한 방안으로 개념망을 제안한다. 개념망은 주어진 문서의 집합에서 제시된 주요 개념을 추출하고, 추출된 개념들 사이의 관련성을 분석하여, 관련성이 높은 개념 사이에는 링크를 설정함으로써 개념을 노드로 하는 네트워크를 구성한 것이다. 개념 추출과 링크 설정은 문서에 출현하는 명사의 출현 빈도를 근거로 하였다. 사용자가 정보검색을 위하여 키워드를 입력하면 본 시스템은 입력된 키워드를 중심으로 구축된 개념망을 제시한다. 사용자는 제시된 개념망을 조사함으로써, 자신이 입력한 단어가 검색하고자 하는 목표개념을 적절히 반영한 단어인지 확인할 수 있고, 새로운 검색어를 추가하거나 기존의 것을 수정함으로써 검색의 효과를 향상시킬 수 있다.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.22 no.1
• /
• pp.113-129
• /
• 2020

In this study we examined the topic analysis and correlation analysis by text mining to extract meaningful information or rules from the self introduction letter of freshman at Korea National College of Agriculture and Fisheries in 2020. The analysis items are described in items related to 'academic' and 'in-school activities' during high school. In the text mining results, the keywords of 'academic' items were 'study', 'thought', 'effort', 'problem', 'friend', and the key words of 'in-school activities' were 'activity', 'thought', 'friend', 'club', 'school' in order. As a result of the correlation analysis, the key words of 'thinking', 'studying', 'effort', and 'time' played a central role in the 'academic' item. And the key words of 'in-school activities' were 'thought', 'activity', 'school', 'time', and 'friend'. The results of frequency analysis and association analysis were visualized with word cloud and correlation graphs to make it easier to understand all the results. In the next study, TF-IDF(Term Frequency-Inverse Document Frequency) analysis using 'frequency of keywords' and 'reverse of document frequency' will be performed as a method of extracting key words from a large amount of documents.

• Journal of Internet of Things and Convergence
• /
• v.10 no.6
• /
• pp.67-79
• /
• 2024

This study analyzed domestic media reports to determine trends in how public facilities such as childcare centers and Elderly Care Facilities perceive major disasters. To this end, press articles from approximately four years from 2021 to October 2024 were analyzed using BIGKinds. As a result, first, in the keyword trend, there were 209 articles on 'childcare center +serious accident' and 23 articles on 'elderly care + serious accident'. Second, as a result of the relationship analysis, the main keywords for childcare centers were business owners and managers, workers (workers), civil servants, and local government heads, while the main keywords for elderly care facilities were business owners and managers, Gyeongsangbuk-do Governor (Governor), and nursing assistants. Third, as a result of the analysis of related words, the main keywords for childcare centers are public facilities, safety inspections, workplaces, district heads, business owners, management managers, on-site inspections, small business owners, local governments, and workers, while the main keywords for elderly care facilities are public facility managers, daycare centers, social welfare facilities, Gyeonggi-do Suwon-si, countermeasures, Gyeongbuk-do, Jincheon-gun. Based on the research results, suggestions were made to raise awareness of and prevent major disasters by establishing a safety and health management system, organizing a local government organization dedicated to major disasters and supporting a budget for major disaster prevention and response, implementing safety and health education within facilities and establishing procedures for hearing opinions from workers, and developing and distributing a manual for major disaster prevention education and response.

• Journal of the Korean Society for information Management
• /
• v.23 no.1 s.59
• /
• pp.99-119
• /
• 2006

The most widely used information searching method in the current internet environment is the keyword-based one, which has certain limitations in terms of precision and recall. Most major internet portals provide directory-based searching as a means to complement these limitations. However, that they adopt different classification schemes brings significant inconvenience to the users, and it consequently suggests a need to develop mapping gateway to provide cross-portal, or cross-directory information searching. In this context, this study attempts to develop a prototype system of intermediary gateway for integrated search, using the directory services of three major portals, Naver, Yahoo and Empas, and test its performance.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.11-13
• /
• 2019

대중들에게 정보를 빠르고 정확하게 제공하는 대표 매체인 뉴스 기사는 일 평균 1만 5천 건 이상이 보도되고 있다. 특정 주제 또는 분야에 대한 전반적인 동향을 파악하고자 대량의 텍스트 데이터를 수집하여 텍스트 마이닝(Text mining)과 머신러닝 등을 적용하는 연구들이 활발하게 수행되고 있다. 본 연구에서는 서울시의 이슈 및 문제를 파악하고자 약 5년간 뉴스 기사를 수집하여 키워드 분석 및 토픽 모델링을 적용하였다. 분석 결과 5년간의 뉴스 기사에서 빈번하게 출현하는 키워드들을 도출하였고 연도별로 도출된 키워드들을 비교분석하였다. 또한 토픽 모델링 적용 결과 뉴스 기사를 구성하는 20개의 주제를 도출하였으며 이를 기반으로 서울시의 주요 이슈들을 파악할 수 있다. 본 연구는 연도별, 분야별 세부 내용 및 시계열 분석, 다른 도시들의 이슈 및 문제를 도출하는데 활용될 것으로 기대된다.