• Knowledge Management Research
• /
• v.22 no.3
• /
• pp.31-53
• /
• 2021

As a communication channel for individuals, social media is affecting various areas such as business, economy, politics, and society. One of the less-studied areas is the law. Therefore, this study collected various information from social media and analyzed its impacts on the legal decisions, especially the Supreme Court decisions in Korea. This study was conducted by compiling information from Internet news articles and public responses. We found that when the negative reactions from the public got higher, the trial duration until the supreme court making the final decisions became shorter. However, we were not able to find the significant relationship between social media reactions and dismissal of appeal nor annulment. Our study would contribute to the information systems and knowledge management research in a sense that the social analytics is applied to the area of legal decisions, instead of using conventional qualitative study methodology. Our study is also meaningful to the practitioners because that big data analytical business can be applied to the field of law by creating a new database for the emerging legal technology. Finally, law makers can think of a better way to standardize the legal decision process to minimize the reverse effects from social media.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.48 no.5
• /
• pp.28-41
• /
• 2020

This study selects two linear parks representing each culture and reveals the differences between them using a visitor survey as small data and social media analytics as big data based on the three components of the model of landscape perception. The 606 in Chicago, U.S., and the Gyeongchun Line in Seoul, Korea, are representative parks built on railroads. A total of 505 surveys were collected from these parks. The responses were analyzed using descriptive statistics, principal component analysis, and linear regression. Also, more than 20,000 tweets which mentioned two linear parks respectively were collected. By using those tweets, the authors conducted the clustering analysis and draw the bigram network diagram for identifying and comparing the placeness of each park. The result suggests that more diverse design concept links to less diversity in behavior; that half of the park users use the park as a shortcut; and that same physical exercise provides different benefits depending on the park. Social media analysis showed the 606 is more closely related to the neighborhoods rather than the Gyeongchun Line Forest. The Gyeongchun Line Forest was a more event-related place than the 606.

• Journal of The Korean Association of Information Education
• /
• v.26 no.6
• /
• pp.553-566
• /
• 2022

This study collects social data and academic research data from portal sites and RISS, and analyzes TF-IDF, N-Gram, semantic network analysis, and CONCOR analysis to analyze the social awareness and current aspects of 'AI Literacy' and 'AI Convergence Education'. Through this, we tried to understand the social awareness aspect and the current situation, and to suggest implications and directions. In the social data, the collection of 'AI Convergence Education' was more than twice that of 'AI Literacy', indicating that awareness of 'AI Literacy' was relatively low. In 'AI Literacy', the keyword 'human' in social data showed no cluster to which it belonged, indicating a lack of philosophical interest in and awareness of humanities and AI. In addition, the keyword 'Ministry of Education' showed high frequency, importance, and centrality of connection only in the social data of 'AI convergence education', confirming that 'AI convergence education' is closely related to government policy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.801-801
• /
• 2012

최근 과학 IT 패러다임은 기존 하드웨어, 소프트웨어 중심에서 폭발적으로 증가하는 데이터를 활용하여 정치 사회 경제 등 제반 이슈와 연계된 분석 예측으로 진화하고 있으며, 모바일 인터넷과 소셜 미디어 등장으로 데이터가 경제적 자산이 되는 빅데이터 시대가 도래하였다. 급속히 변화하고 복잡해진 사회구조와 재난환경으로 인해 인력에만 의존한 재난관리의 사각지대가 대형재난으로 이어질 우려가 크므로 다양한 재난전조(前兆)를 체계적으로 관리하여 선제적으로 예방하는 체계가 필요하다. 본 연구는 인터넷에 존재하는 재난관련 언론보도, 민원, 제보, 소셜 미디어 등의 비정형 데이터와 재난관련 정형 데이터(DB)를 융합 분석하여 재난전조를 사전에 감지하고 위험요소를 신속히 제거하는 빅데이터 기반 재난전조감지 체계를 제안한다. 최근 피해가 급증하고 있는 도시내수침수 피해 위험 예방을 위해 제안한 재난전조감지 체계를 적용하여 피해발생 위험요소 및 전조, 긴급 이슈 등을 감지하는데 활용하는 방안을 제안한다. 이는 전조를 감지하고 사전 침수 피해를 예측하여 피해 최소화 및 복구비용 절감, 저감능력 강화의 효과뿐만 아니라 위험요인 사전 차단 및 확산방지가 가능할 것으로 기대된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.438-440
• /
• 2014

Recently it is used commercially to actively move the data from the SNS service. Therefore, we propose a method that can accurately analyze the information related to the reputation of companies and products in real time SNS environment in this paper.Identify the relationship between words by performing morphological analysis on the text data gathered by crawling the SNS scheme. In addition, it shows the visualization to analyze statistically through a established emotional dictionary morphemes are extracted from the sentence. Here, if the extracted word is not exist in sentimental dictionary. Also, we propose the algorithm that add the word to emotional dictionary automatically.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.10
• /
• pp.2439-2446
• /
• 2013

Recently, SNS (Social Network Service) such as Twitter and Facebook has grown dramatically because of smart phones. Since development of IT has created massive information, social big data extremely increased. Competition between corporations is getting more intense, so they need customer feedback in order to fulfill an effective management. Because social big data plays an important role for getting customer feedback, a lot of corporations are interested in analyzing and applying of social big data. Collecting and analyzing social big data is operated by Buzz monitoring system. This paper demonstrates the research of buzz monitoring system that analyzes big data, and presents examples of customer reputation using buzz monitoring. In the paper, after all, it would analyze the result from the customer reputation, and research the implication.

• Journal of the HCI Society of Korea
• /
• v.12 no.2
• /
• pp.13-19
• /
• 2017

Various life-logging based on cloud service have developed social network according to the advanced technology of smartphone and wearable device. Daily digital life on social networks has been shared information and emotion and developed new social relationships. Recent life-logging has required social relationships beyond extension of personal memory and anonymity for privacy protection. This study is to determine social network group by using life-logging data obtained in daily lives and to categorize emotion behavior with anonymity guarantee. Social network group was defined by grouping similar representative emotional behavior. The public's patterns and trends was able to be inferred by analyzing representative emotion and behavior of the social groups network.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.343-344
• /
• 2018

온라인 쇼핑몰에서 소비자들이 원하는 상품을 노출시켜 정보를 제공하기 위해서는 상품의 트렌드 분석에 대한 연구가 필요하다. 본 논문에서는 대량의 SNS 데이터와 서비스 내 사용자 데이터를 결합하여 보다 효율적인 상품 트렌드 분석 기법을 제안한다. 온라인 소셜 네트워크의 대중화로 소비자들은 시공간에 구애받지 않고 상품에 대한 정보를 SNS로 교류할 수 있다. 제안하는 기법은 이 과정에서 발생한 SNS 데이터와 사용자 성향 데이터에 시간 속성을 고려하여 상품 트렌드를 분석한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.519-522
• /
• 2020

1989년에 WWW(World Wide Web)이 도입 되면서 세계적으로 인터넷의 보급이 시작되었다. 정보화 시대라고 알려진 3차 산업혁명 이후로 대량의 정보들이 소셜 미디어를 통하여 생산되었다. 소셜미디어는 2007년에 인터넷 사용자들 중 56%의 이용률을 보였지만 2008년 2분기에는 75%의 이용률로 증가함에 따라 대부분의 사용자들이 많이 사용하며 의존하게 되었다. 또한 소셜 미디어를 통해 발생 되는 데이터들을 이용하여 기업들은 이윤 창출을 할 수 있다. 하지만 이러한 소셜 미디어는 악의적인 목적을 통해 주가 조작, 정치적 선동 등을 할 수 있는 가짜 뉴스와 허위 정보들을 생성할 수 있으며 이에 따라 대책이 시급하다. 또한 가짜 뉴스는 사람이 글을 작성할 수도 있지만 최근 인공지능 기술의 발달에 따라 프로그램을 통해 자동적으로 생성 될 수도 있다. 본 논문에서는 이와 같은 실제 뉴스와 인공지능을 기반으로 한 뉴스를 분석한다. Kaggle에서 실제 뉴스 데이터를 수집하여 헤드라인을 OpenAI의 GPT-2 언어 모델을 통해 뉴럴 가짜 뉴스를 생성 하였다. 파이썬의 NLTK 모듈을 이용하여 전처리를 진행하였고 t-검정과 박스 플롯을 활용하여 분석을 진행하였다. 분석된 주요 속성들을 의사결정트리를 통해 모델 검증을 하였고 k-fold 교차검증을 통해 분류 모델을 평가하였다. 결과로 전체 분류 정확도 평균 89%의 성능을 보여주었다.

• Journal of the Korean Society for information Management
• /
• v.36 no.4
• /
• pp.207-226
• /
• 2019

Depression is a serious psychological disease that is expected to afflict an increasing number of people. And studies on depression have been conducted in the context of social media because social media is a platform through which users often frankly express their emotions and often reveal their mental states. In this study, large amounts of Korean text were collected and analyzed to determine whether such data could be used to detect depression in users. This study analyzed data collected from Twitter users who had and did not have depressive tendencies between January 2016 and February 2019. The data for each user was separately analyzed before and after the appearance of depressive tendencies to see how their expression changed. In this study the data were analyzed through co-occurrence word analysis, topic modeling, and sentiment analysis. This study's automated data collection method enabled analyses of data collected over a relatively long period of time. Also it compared the textual characteristics of users with depressive tendencies to those without depressive tendencies.