• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권4호
• /
• pp.149-156
• /
• 2022

최근 전 세계적으로 COVID-19이 유행하는 상황 속에서 이와 관련된 가짜뉴스가 심각한 사회적 혼란을 야기하고 있다. 이러한 배경에서 가짜뉴스를 정확하게 탐지하기 위해, 뉴스가 소셜 미디어를 통해 파급되는 과정과 같은 소셜 컨텍스트 정보를 활용하는 소셜 컨텍스트 기반 탐지 기법들이 널리 사용되고 있다. 그러나 대부분의 기 구축된 가짜뉴스 탐지를 위한 데이터들은 뉴스 자체의 내용 정보 위주로 구성되어, 소셜 컨텍스트 정보를 거의 포함하지 않는다. 즉, 이 데이터들에는 소셜 컨텍스트 기반 탐지 기법을 적용할 수 없으며, 이러한 데이터의 한계는 가짜뉴스 탐지 연구 분야의 발전을 저해하는 방해 요소이다. 본 논문은 이러한 한계를 극복하기 위해, 기존의 저명한 가짜뉴스 데이터인 CoAID 데이터를 기반으로, 소셜 컨텍스트 정보를 추가적으로 수집하여, CoAID 데이터의 뉴스 내용 정보와 해당 뉴스들의 소셜 컨텍스트 정보를 모두 포함하는 CoAID⁺ 데이터를 구축한다. 본 논문에서 구축한 CoAID⁺ 데이터는 기존의 대부분의 소셜 컨텍스트 기반 탐지 기법들에 적용될 수 있으며, 향후 새로운 소셜 컨텍스트 기반 탐지 기법들에 대한 연구도 더욱 활성화시킬 수 있을 것으로 기대된다. 마지막으로, 본 논문은 다양한 관점에서 CoAID⁺ 데이터를 분석하여 진짜뉴스와 가짜뉴스의 파급 패턴 및 키워드에 따른 파급 패턴도 파악하여 소개한다.

• 보건교육건강증진학회지
• /
• 제24권4호
• /
• pp.181-200
• /
• 2007

Objectives: A content analysis was conducted to examine whether the current school textbooks providing smoking information are effective or not. Methods: The authors reviewed 111 qualified textbooks using elementary through high schools during 2006-2007 academic year in Korea. Educational components were coded with an analysis tool developed through the present research. Result: Tobacco education components were narrowly focused on long-term physiological consequences of tobacco use, addictiveness, and harmful ingredients and they were repetitively shown in the textbooks. Negative health consequences such as lung cancer were emphasized 10 times among 12 smoking-related textbooks. Educational messages or contents are mainly based on medical knowledge (72%) rather than psycho-social components. The US school-based smoking prevention programs, however, employ psycho-social approach with cognitive and life-skill components and they contain only 7-17% of smoking-related medical knowledge. In order to increase psycho-social smoking prevention components in Korean textbooks, the present study identified social subjects of textbooks (and relating core sessions) for elementary, middle, and high school. It also provided guidelines for school instructors to use. Conclusion: Adolescent smoking behavior is not caused by the deficit of health information, but mostly by social influences including media and peer pressure. School textbooks proving smoking information need to increase psycho-social context. One of the most effective ways as a psycho-social smoking prevention program is to use social subjects (or curriculum) of textbooks such as social studies, ethics, social cultures, social environment, and home management.

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

• Journal of Information Processing Systems
• /
• 제15권5호
• /
• pp.1119-1130
• /
• 2019

With the wide spread of Social Network Services (SNS), fake news-which is a way of disguising false information as legitimate media-has become a big social issue. This paper proposes a deep learning architecture for detecting fake news that is written in Korean. Previous works proposed appropriate fake news detection models for English, but Korean has two issues that cannot apply existing models: Korean can be expressed in shorter sentences than English even with the same meaning; therefore, it is difficult to operate a deep neural network because of the feature scarcity for deep learning. Difficulty in semantic analysis due to morpheme ambiguity. We worked to resolve these issues by implementing a system using various convolutional neural network-based deep learning architectures and "Fasttext" which is a word-embedding model learned by syllable unit. After training and testing its implementation, we could achieve meaningful accuracy for classification of the body and context discrepancies, but the accuracy was low for classification of the headline and body discrepancies.

• Journal of Information Processing Systems
• /
• 제20권2호
• /
• pp.200-214
• /
• 2024

Amid the flood of data, social network analysis is beneficial in searching for its hidden context and verifying several pieces of information. This can be used for detecting the spread model of infectious diseases, methods of preventing infectious diseases, mining of small groups and so forth. In addition, community detection is the most studied topic in social network analysis using graph analysis methods. The objective of this study is to examine signed attributed social networks and identify the maximal balanced cliques that are both absolute and fair. In the same vein, the purpose is to ensure fairness in complex networks, overcome the "information cocoon" bottleneck, and reduce the occurrence of "group polarization" in social networks. Meanwhile, an empirical study is presented in the experimental section, which uses the personal information of 77 employees of a research company and the trust relationships at the professional level between employees to mine some small groups with the possibility of "group polarization." Finally, the study provides suggestions for managers of the company to align and group new work teams in an organization.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• 한국HCI학회논문지
• /
• 제6권1호
• /
• pp.35-42
• /
• 2011

최근 모바일 장치를 통한 마이크로 블로그 활용이 늘고 있지만, 모바일 장치가 지닌 하드웨어 제약으로 인해 여전히 모바일 정보 브라우징에 어려움이 있다. 이를 해결하기 위해 모바일 사용자의 컨텍스트 정보를 활용하여 사용자의 관심 정보를 추론하는 연구가 활발히 진행되고 있다. 본 논문에서는 모바일 사용자의 컨텍스틀 이용하여 마이크로 블로그의 토픽을 추천하는 방법을 제안한다. 마이크로 블로그에서 사용자와 연관된 토픽을 추출하기 위해 제안한 방법은 사용자 위치, 행동, 기존에 작성한 블로그 그리고 사회적 관계 등의 사용자 컨텍스트를 모바일 장치로 부터 얻어 활용한다. 모바일 장치로부터 얻어온 컨텍스트는 마이크로 블로그 검색 범위를 줄이는데 뿐만 아니라 사용자의 관심을 추론하는 경우에도 활용된다. 추론된 사용자의 선호도를 기반으로 검색된 결과의 우선순위를 다시 결정한다. 제안한 방법을 통해 모바일 사용자들은 사용자가 관심을 가질만한 토픽의 마이크로 블로그 정보를 얻을 수 있을 것으로 기대한다.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.312-318
• /
• 2021

Lack of knowledge and digital skills is a threat to the information security of the state and society, so the formation and development of organizational culture of information security is extremely important to manage this threat. The purpose of the article is to assess the state of information security of the state and society. The research methodology is based on a quantitative statistical analysis of the information security culture according to the EU-27 2019. The theoretical basis of the study is the theory of defense motivation (PMT), which involves predicting the individual negative consequences of certain events and the desire to minimize them, which determines the motive for protection. The results show the passive behavior of EU citizens in ensuring information security, which is confirmed by the low level of participation in trainings for the development of digital skills and mastery of basic or above basic overall digital skills 56% of the EU population with a deviation of 16%. High risks to information security in the context of damage to information assets, including software and databases, have been identified. Passive behavior of the population also involves the use of standard identification procedures when using the Internet (login, password, SMS). At the same time, 69% of EU citizens are aware of methods of tracking Internet activity and access control capabilities (denial of permission to use personal data, access to geographical location, profile or content on social networking sites or shared online storage, site security checks). Phishing and illegal acquisition of personal data are the biggest threats to EU citizens. It have been identified problems related to information security: restrictions on the purchase of products, Internet banking, provision of personal information, communication, etc. The practical value of this research is the possibility of applying the results in the development of programs of education, training and public awareness of security issues.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권16호
• /
• pp.6863-6870
• /
• 2015

Background: Breast cancer accounted for almost 25% of all cancers in women globally in 2012. Although breast cancer is the most prevalent cancer in India, there is no organised national breast cancer screening programme. Local studies on the burden of breast cancer are essential to develop effective context-specific strategies for an early detection breast cancer programme, considering the cultural and ethnic heterogeneity in India. This study examined the knowledge, attitudes, and practices about breast cancer in rural women in Central India. Materials and Methods: This community-based cross sectional study was conducted in Wardha district, located in Maharashtra state in Central India in 2013. The sample included 1000 women (609 rural, 391 urban) aged 13-50 years, selected as representative from each of the eight development blocks in the district, using stratified cluster sampling. Trained social workers interviewed women and collected demographic and socio-economic data. The instrument also assessed respondents' knowledge about breast cancer and its symptoms, risks, methods of screening, diagnosis and treatment, as well as their attitudes towards breast cancer and selfreported practices of breast cancer screening. Chi-square and t-test were applied to assess differences in the levels of knowledge, attitude, and practice (the outcome variables) between urban and rural respondents. Multivariable linear regression was conducted to analyse the relationship between socio-demographic factors and the outcome variables. Results: While about two-thirds of rural and urban women were aware of breast cancer, less than 7% in rural and urban areas had heard about breast self-examination. Knowledge about breast cancer, its symptoms, risk factors, diagnostic modalities, and treatment was similarly poor in both rural and urban women. Urban women demonstrated more positive attitudes towards breast cancer screening practices than their rural counterparts. Better knowledge of breast cancer symptoms, risk factors, diagnosis, and treatment correlated significantly with older age, higher levels of education, and being office workers or in business. Conclusions: Women in rural Central India have poor knowledge about breast cancer, its symptoms and risk factors. Breast self-examination is hardly practiced, though the willingness to learn is high. Positive attitudes towards screening provide an opportunity to promote breast self-examination.