• International Journal of Advanced Culture Technology
• /
• v.8 no.1
• /
• pp.188-198
• /
• 2020

In the cyber space represented by Sns, the problem of cyber verbal violence, which sends slander messages such as abusive messages through chats, bulletin boards, malicious comments, and messages, is getting worse. Leveraging the power of cyberspace's anonymity, people can't hesitate to say what they can't say in the real world. In extreme cases, cyber verbal violence can lead to the death of a person. This paper focuses on the creation of media content that helps to inform and prevent the seriousness of cyber verbal violence prevalent on the Internet through interactive art. The nature of Interact art goes beyond the work and the audience to the people in the relationship between the work and the participants, allowing participants to directly and indirectly feel the seriousness of cyber verbal viol.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.50-58
• /
• 2019

The clear and specific objective of this study is to design a false news discriminator algorithm for news articles transmitted on a text-based basis and an architecture that builds it into a system (H/W configuration with Hadoop-based in-memory technology, Deep Learning S/W design for bigdata and SNS linkage). Based on learning data on actual news, the government will submit advanced "fake news" test data as a result and complete theoretical research based on it. The need for research proposed by this study is social cost paid by rumors (including malicious comments) and rumors (written false news) due to the flood of fake news, false reports, rumors and stabbings, among other social challenges. In addition, fake news can distort normal communication channels, undermine human mutual trust, and reduce social capital at the same time. The final purpose of the study is to upgrade the study to a topic that is difficult to distinguish between false and exaggerated, fake and hypocrisy, sincere and false, fraud and error, truth and false.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.543-545
• /
• 2022

최근 악플에 대한 논란이 끊이지 않고 있어 이것을 해결하기위한 방법으로 자연어 처리를 이용하고 있다. 특히 소셜 미디어, 온라인 커뮤니티에서 많이 발생하고 있고 해당 매체에서는 한글을 그대로 사용하지 않고 그들의 은어를 섞어서 사용하며 그중에서 한글이 아닌 문자를 섞어서 만들어낸 문장도 있다. 이러한 문장은 기존의 모델에 학습된 데이터의 형태와 다르며 한글이 아닌 문장이 많을수록 모델의 예측이 부정확해진다는 단점이 있어 본 논문에서는 인공지능을 이용한 이미지 분류와 띄어쓰기, 오타 교정을 이용한 전처리 기법을 제안한다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.1
• /
• pp.285-296
• /
• 2016

Recently, as the widespread use of Facebook through a smartphone or tablet PC, it has increased the threat that contains the malicious code to post a social attacks and comments that use personal information that has been published of Facebook. To solve these problems, Facebook is, by providing a security function, but would like to address these threats, in setting the security function, the security function of the user's convenience is not considered a properly there is a problem that is not in use. Thus, in this paper, on the basis of the information obtained via the cogTool, on Facebook security features, the user experience by presenting a method that can be quantitatively measured by this, the user convenience It classifies about Facebook security features to decrease.

• The Journal of Society for e-Business Studies
• /
• v.17 no.4
• /
• pp.17-37
• /
• 2012

The evolution of the IT facilitated the social actions of the consumers by supporting social communication of the online users. At the same time it help for the consumer to post malicious comments on the Internet or to spread the unproven news for distorting the public opinion in the SNSs. Although the number of the consumer unethical behaviors and the estimated damage of the innocent companies have been increased, a few studies had investigate on this issue. Based on the Literature on the consumer unethical behaviors and the institution based trust, we had developed the defense strategies against the consumer unethical behaviors. This study would introduce the new perspective that the consumer could always not be innocent. Also, the defense strategy developed in this study could contribute to make the guideline for consumer service manual.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.6
• /
• pp.1499-1506
• /
• 2017

The use of smartphones and the launch of various apps have increased exponentially, and malicious apps have also increased. Existing app recommendation systems have been limited to operate based on static information analysis such as ratings, comments, and popularity categories of other users who are online. In this paper, we first propose a robust app recommendation system that realistically uses dynamic information of apps actually used in smartphone and considers static information and dynamic information at the same time. In other words, this paper proposes a robust Android app recommendation system by partially reflecting the time of the app, the frequency of use of the app, the interaction between the app and the app, and the number of contact with the Android kernel. As a result of the performance evaluation, the proposed method proved to be a robust and efficient app recommendation system.

• Korean journal of communication and information
• /
• v.80
• /
• pp.115-142
• /
• 2016

This study aims to reveal the content of and logic behind a recent negative public sentiment toward female idols with the example of a debate over songstress IU's fourth album that was released late last year. While previous studies on fandom have focused on the identification process towards entertainers and making community, a recent phenomenon of "anti-fandom" or "malicious comments" implies that more research is needed on negative emotions such as hostility or schadenfreude (feelings of pleasure from others' misfortunes). Schadenfreude is a social sentiment that originated in modern liberalism, which features contradictions between public equality and private ownership, and that has been intensified in neoliberalism, which features a maximization of this contradiction centering on a meritocracy. Celebrities in Korea often become the targets of schadenfreude, which is associated with the suspicion that they gain popularity not from their abilities but from "just being popular." It should also be noted that this kind of schadenfreude operates differently between male and female entertainers. Specifically, the acquisition of money and fame by modern women whose presence used to be located in the private possessions of males is considered to be due to their unjustified use of sexuality. This is also the background of the recent online misogyny culture in Korea. In this context, IU, who had been successful at building a differentiated image of "sister-like idol artist," became a valid target. Although accusing IU of utilizing pedophilia reflects a stalemate that a current politics of sexual violence faces, it rather damages the name of an individual than attracts public attention to the structural causes of childsexualabuse. This is why I see the way that pedophilia was used in the debate over IU as a schadenfreude. Consequently, the term pedophilia here contributes to an expansion of the entertainment economy that is sustained by rises and falls of the celebrities' stock prices.