• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.95-100
• /
• 2023

끊임없이 재생산되는 혐오 표현의 정확한 탐지를 위해서는 혐오란 무엇인가에 대한 본질적인 이해가 필요하다. 본 연구에서는 화용론에서 사용되는 적정성 조건이라는 분석 틀을 활용하여 모델이 '혐오하기' 화행을 어떻게 인식하고 있는지 평가하고자 했다. 혐오 화행의 적정성 조건을 명제 내용 조건, 예비 조건, 성실성 조건, 본질 조건으로 나누어 분석하였으며, 이를 진위형, 연결형, 단답형, 논술형 문항으로 구성했다. 그 결과 모든 문항 유형에서 50점이 넘는 점수를 받았으나 비교적 고차원인 사고 능력을 측정하는 단답형과 논술형 문항 유형의 점수가 가장 낮게 나타났다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.577-580
• /
• 2023

악성댓글은 인터넷상에서 정서적, 심리적 피해를 주는 문제로 인식되어 왔다. 본 연구는 한국어 악성댓글 탐지 분석을 위해 KcBERT 및 다양한 모델을 활용하여 성능을 비교하였다. 또한, 공개된 한국어 악성댓글 데이터가 부족한 것을 해소하기 위해 기계 번역을 이용하고, 다국어 언어 모델(Multilingual Model) mBERT를 활용하였다. 다양한 실험을 통해 KcBERT를 미세 조정한 모델의 정확도 및 F1-score가 타 모델에 비해 의미 있는 결과임을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.4
• /
• pp.349-360
• /
• 2002

In ITU H.323 teleconference system, the RTP/RTCP protocol is offered to transfer real-time multimedia stream. Both sender and receiver hate experience in packet loss and jitter which result from network congestion over Internet. Audio quality over Internet depends on the number of lost packets and on jitter between successive packets. The goal of our study is to improve the speech quality over Internet by checking the packet loss characteristics of the network and adopting the but for control management mechanism at the receiver. We suggest a dynamic redundant audio transmission mechanism which examines the packet loss rate and uses the feedback information through RTCP.

• Journal of Information Science Theory and Practice
• /
• v.10 no.1
• /
• pp.59-72
• /
• 2022

This text discusses elements and characteristics of contemporary informational reality, that is, the ways of producing, circulating, organizing, using, and appropriating information in the current context. Initially, seven terms and concepts used to describe this reality are discussed: fake news, false testimonials, hate speech, scientific negationism, disinformation, post-truth, and infodemic. Next, an attempt is made to present a framework for such phenomena as an object of study in information science. Therefore, this scenario is characterized based on the three main models of information science study: physical, cognitive, and social. The contribution of each of them to the study of contemporary informational reality is analyzed, identifying aspects such as the bubble effect, clickbaits, confirmation bias, cults of amateurism, and post-truth culture. Finally, it presents the discussion of a possible veritistic turn in the field, in order to think about elements not covered so far by information science in its task and challenge of producing adequate understanding and diagnoses of current phenomena. In conclusion, it is argued that only accurate and comprehensive diagnoses of such phenomena will allow information science to develop services and systems capable of combating their harmful effects.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.10-15
• /
• 2022

온라인상에서 발생하는 혐오 표현은 사회가 직면한 주요 문제 중 하나이다. 이러한 필요성에 입각해, 최근 인공지능을 활용하여 발화에 대한 교화 목적을 가진 대응 발화 쌍을 통해 혐오 표현에 대한 실질적인 완화를 진행하는 연구들이 생겨나고 있다. 그러나 각 혐오 표현에 적합한 대응 발화의 구축은 다수의 전문 인력이 요구되므로 데이터를 구축함에 있어 시간과 비용이 많이 소요되며 대응 발화 생성 또한 어려운 문제로 여겨진다. 해당 문제를 완화하기위해, 본 논문은 사전에 기 구축되어 있는 혐오 표현 데이터를 기반으로 의미 기반 검색을 적용하여 자동으로 데이터를 증강할 수 있는 쉽고 빠른 데이터 증강 방법론을 제안한다. 제안하는 프로세스의 타당성과 증강된 문장의 효과를 검증하기 위해 사전학습 모델을 기반으로 비교 실험을 진행하였다. 실험 결과, 제안하는 프로세스를 적용하였을 시, 그렇지 않은 모델 대비 높은 폭의 성능 향상을 보였다.

• International journal of advanced smart convergence
• /
• v.12 no.1
• /
• pp.82-91
• /
• 2023

In 2020 when the COVID-19 pandemic began in full-scale, the WHO Director-General warned of the dangers of an infodemic. The infodemic is a phenomenon in which false information spreads rapidly like an epidemic and causes chaos, and it was noted that the COVID-19 pandemic is not just limited to health problems, but also linked to a variety of issues such as human rights, economic inequality, various discrimination, hate speech, fake news, global governance etc. In the field of education, it is necessary to think about how to connect this global situation with school classes. Accordingly, this study suggested the direction for global citizenship education by analyzing how the infodemic spreads on Korean social media with the case of the recent global COVID-19 pandemic. According to the research results, the rate of negative emotions was higher than positive ones in the emotions that generate infodemic, while anxiety and anger were focused among negative emotions. In addition, the infodemic tended to spread widely with the feelings of anger rather than anxiety, and the feelings of anger led to advocating aggressive policies against certain country and regions. Therefore, global citizenship education is required to focus on a sense of duty and responsibility as a citizen, not on the level of national identity based on an exclusive sense of belonging. Furthermore, global citizenship education needs to lead to presenting a blueprint for education in a way that can enhance the awareness of the global community for joint response to global challenges and realize common prosperity based on sustainability and justice.

• Informatization Policy
• /
• v.30 no.2
• /
• pp.3-21
• /
• 2023

The recent Internet environment demands a new approach to Internet content regulation. The need for regulation on the Internet has been recognized due to the rise of digital sex crimes, illegal information such as drugs and suicide, fake news, hate speech, false consumer reviews, and harmful content for young people. This article attempts to analyze the legislative, judicial, and administrative aspects of Internet content regulation in Korea. It covers the current status and characteristics of the Internet content regulation law, the judicial judgment on KCSC's communications deliberation and regulation, and the process and characteristics of KCSC's communications deliberation. Problems in Korea's communications deliberation system were addressed through legislative, judicial, and administrative approaches. This article concludes with policy suggestions for improving Internet content regulation in Korea.

• 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.

• Smart Media Journal
• /
• v.10 no.4
• /
• pp.71-79
• /
• 2021

One of the social aspects that changes as the use of the Internet becomes widespread is communication in online space. In the past, only one-on-one conversations were possible remotely, except when they were physically in the same space, but nowadays, technology has been developed to enable communication with a large number of people remotely through bulletin boards, communities, and social network services. Due to the development of such information and communication networks, life becomes more convenient, and at the same time, the damage caused by rapid information exchange is also constantly increasing. Recently, cyber crimes such as sending sexual messages or personal attacks to certain people with recognition on the Internet, such as not only entertainers but also influencers, have occurred, and some of those exposed to these cybercrime have committed suicide. In this paper, in order to reduce the damage caused by malicious comments, research a method for improving the performance of discriminate malicious comments through feature extraction based on parts-of-speech.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.320-326
• /
• 2022

The use of the Internet has become commonplace for billions of people on the planet. The rapid development of technology, in particular, mobile gadgets, has provided access to communication anywhere, anytime. At the same time, there are growing concerns about the behavior of people on the Internet, in particular, towards each other and social groups in general. This raises the issue of human rights in today's information society. In this study, we focused on human rights such as the right to privacy, confidentiality, freedom of expression, the right to be forgotten, etc. We point to some differences in this regard, in particular between the EU, etc. In addition, we describe the latest legal regulation in this aspect in European countries. Such methods as systemic, factual, formal and legal, to show the factors of formation and development of human rights in the context of digitalization were used. The authors indicate which of them deserve the most attention due to their prevalence and relevance. Thus, we concluded that the technological development of social communications has laid the groundwork for a legal settlement of privacy and opinion issues on the Internet. Simultaneously, jurisdictions address issues on every aspect of human rights on the Internet, based on previous norms, case law, and principles of law. It is concluded that human rights legislation on the Internet will continue to be actively developed to ensure a balance of private and public interests, safe online access and unimpeded access to it.