• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.9-16
• /
• 2006

In this paper, the acoustic model output of CSR(Continuous Speech Recognition) was used to analyze news data News database used in this experiment was consisted of 2,093 articles. Due to the low efficiency of language model, conventional Korean CSR is not appropriate to the analysis of news data. This problem could be handled successfully by introducing post-processing work of recognition result of acoustic model. The acoustic model more robust than language model in Korean environment. The result of post-processing work was made into KIF(Keyword information file). When threshold of acoustic model's output level was 100, 86.9% of whole target morpheme was included in post-processing result. At the same condition, applying length information based normalization, 81.25% of whole target morpheme was recognized. The purpose of normalization was to compensate long-length morpheme. According to experiment result, 75.13% of whole target morpheme was recognized KIF(314MB) had been produced from original news data(5,040MB). The decrease rate of absolute information met was approximately 93.8%.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.85-106
• /
• 2021

The purpose of this study is to examine the concept and definition of fake news focusing on misinformation/false information and is to examine the ways in which our society can respond to the distortion of social reality and damage to democracy caused by information distortion such as fake news. To do this, the concept of fake news was examined based on the level of facticity and intention to device, and our social environment in which fake news was created and spread was examined from the perspective of datafication. In this environment, the library community, which plays a pivotal role in human access to and use of information, argued that it should strive to establish and provide universal literacy education in order to realize the Sustainable Development Goals of the UN 2030 agenda. The core of universal literacy education is to understand the society by investigating and analyzing data communication types according to the degree of datafication and the political, economic, social, and cultural background of society. For this reason, it was concluded that universal literacy should be implemented flexibly according to the degree of datafiation and users of each society.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.99-102
• /
• 2017

대규모의 데이터가 생산되고 저장되는 정보화 시대에서 현재와 과거의 데이터를 바탕으로 미래를 추측하고 방향성을 알아갈 수 있는 빅데이터의 중요성이 강조되고 있다. 정형화 되지 못한 대규모 데이터를 빅데이터 분석 도구인 R과 웹크롤링을 통해 분석하고 그 통계를 기초로 데이터의 정형화와 정보 분석을 하도록 한다. 본 논문에서는 R과 웹크롤링을 이용하여 최근 이슈가 되고 있는 벤처창업을 주 키워드로 하여 뉴스 및 SNS에서 나타나는 벤처창업 관련 빅데이터를 분석한다. 뉴스기사와 페이스북, 트위터에서 벤처창업 관련 데이터를 수집하고 수집된 데이터에서 키워드를 분류하여 효율적인 벤처창업의 방법과 종류, 방향성에 대해 예측한다. 과거의 벤처창업 실패요인을 분석하고 현재의 문제점을 찾아 데이터 분석을 통해 벤처창업의 흐름과 방향성을 제시하여 창업자들이 겪을 수 있는 어려움을 사전에 예측하고 파악함으로써 실질적인 벤처창업에 크게 이바지할 것으로 보여 진다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.59-62
• /
• 2017

본 논문에서는 텍스트 형태의 빅 데이터를 분산처리 환경에서 기계학습을 이용하여 분석하고 유의미한 데이터를 만들어내는 시스템에 대해 다루었다. 빅 데이터의 한 종류인 뉴스 기사 빅 데이터를 분산 시스템 환경(Spark) 내에서 기계 학습(Word2Vec)을 이용하여 뉴스 기사의 키워드 간의 연관도를 분석하는 분산 처리 시스템을 설계 및 구현하였고, 사용자가 입력한 검색어와 연관된 키워드들을 한눈에 파악하기 쉽게 만드는 시각화 시스템을 설계하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• The Journal of Society for e-Business Studies
• /
• v.23 no.4
• /
• pp.19-39
• /
• 2018

Recently, fake news has attracted worldwide attentions regardless of the fields. The Hyundai Research Institute estimated that the amount of fake news damage reached about 30.9 trillion won per year. The government is making efforts to develop artificial intelligence source technology to detect fake news such as holding "artificial intelligence R&D challenge" competition on the title of "searching for fake news." Fact checking services are also being provided in various private sector fields. Nevertheless, in academic fields, there are also many attempts have been conducted in detecting the fake news. Typically, there are different attempts in detecting fake news such as expert-based, collective intelligence-based, artificial intelligence-based, and semantic-based. However, the more accurate the fake news manipulation is, the more difficult it is to identify the authenticity of the news by analyzing the news itself. Furthermore, the accuracy of most fake news detection models tends to be overestimated. Therefore, in this study, we first propose a method to secure the fairness of false news detection model accuracy. Secondly, we propose a method to identify the authenticity of the news using the social data broadly generated by the reaction to the news as well as the contents of the news.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.227-230
• /
• 2015

For analyzing and prediction of economic trends, it is necessary to collect particular economic news and stock data. Typical Web crawler to analyze the page content, collects document and extracts URL automatically. On the other hand there are forms of crawler that can collect only document of a particular topic. In order to collect economic news on a particular Web site, we need to design a crawler which could directly analyze its structure and gather data from it. The wrapper-based web crawler design is required. In this paper, we design a crawler wrapper for Economic news analysis system based on big data and implemented to collect data. we collect the data which stock data, sales data from USA auto market since 2000 with wrapper-based crawler. USA and South Korea's economic news data are also collected by wrapper-based crawler. To determining the data update frequency on the site. And periodically updated. We remove duplicate data and build a structured data set for next analysis. Primary to remove the noise data, such as advertising and public relations, etc.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.234-237
• /
• 2000

멀티미디어 데이터를 다루는 기술이 급격하게 발전함에 따라 멀티미디어 데이터베이스를 운용함에 있어서 사용자의 효율적인 검색을 지원하기 위한 연구가 활발히 진행되고 있다. 본 논문에서는 MPEG으로로 압축된 뉴스 영상에서 내용기반 검색을 위한 효율적인 텍스트 프레임 추출방법을 제시한다. 제시하는 방법은 문자가 있는 프레임을 탐색하는 데 있어서 압축된 데이터에 최소한의 복호화만을 함으로써 탐색시간을 줄이고, 뉴스 영상에서의 문자의 특성을 고려하여 중복 추출을 줄이고 시간을 단축한다.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.923-932
• /
• 2017

Based on the metadata of BIGkids, a news big data system, this study analyzed the trends of news coverage by the major fields and topics related to Deoksugung Doldam-gil in mass media. In addition, we tried to interpret the space discourse of Deoksugung Doldam-gil which has been formed in contemporary period through the analysis of data related to BIGKinds, the contents of related reports and context. As a result of the analysis, the coverage of Deoksugung Doldam-gil was mostly reported in the field of 'Culture', and the news related to 'Cooking_Travel', 'Exhibition_Performance' and 'Broadcasting Entertainment.' Deoksugung Doldam-gil was categorized as the pedestrian freindly street, the cultural and artistic street, and the historical street, and interpreted the spatial discourse with related news contents.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.194-196
• /
• 2019

본 연구에서는 재난문자에 대한 뉴스양과 주요 이슈에 대해 알아보았다. 뉴스 빅데이터 서비스인 빅카인즈를 통해 분석을 실시한 결과, '재난문자' 관련 뉴스가 2016년에 186건으로 전년대비 약 18.6배 증가하는 급격한 성장세를 보였다. 이후 '재난문자' 관련 뉴스는 높은 수치를 유지하는 것으로 나타났다. 지진이 다른 재난에 비해 많은 비중을 차지하였지만 지진이 다수를 차지한 2016년 대비 2017년과 2018년은 지진 외에 다양한 재난에 대해 다루어졌다. 그리고 '재난문자' 연관어 중 행정안전부(국가안전처, 행안부 용어 포함)가 가장 비중 있게 다루어졌고, 기상청과 국민도 비중 있게 다루어진 용어로 나타났다.