• Journal of the Korea Convergence Society
• /
• v.11 no.6
• /
• pp.23-28
• /
• 2020

A comment system is essential for communication on the Internet. However, there are also malicious comments such as inappropriate expression of others by exploiting anonymity online. In order to protect users from malicious comments, classification of malicious / normal comments is necessary, and this can be implemented as text classification. Text classification is one of the important topics in natural language processing, and studies using pre-trained models such as BERT and graph structures such as GCN and GAT have been actively conducted. In this study, we implemented a comment classification system using BERT, GCN, and GAT for actual published comments and compared the performance. In this study, the system using the graph-based model showed higher performance than the BERT.

• Smart Media Journal
• /
• v.11 no.2
• /
• pp.18-24
• /
• 2022

Problems caused by malicious comments occur on many social media. In particular, YouTube, which has a strong character as a medium, is getting more and more harmful from malicious comments due to its easy accessibility using mobile devices. In this paper, we designed and implemented a YouTube malicious comment detection system to identify malicious comments in YouTube contents through LSTM-based natural language processing and to visually display the percentage of malicious comments, such commentors' nicknames and their frequency, and we evaluated the performance of the system. By using a dataset of about 50,000 comments, malicious comments could be detected with an accuracy of about 92%. Therefore, it is expected that this system can solve the social problems caused by malicious comments that many YouTubers faced by automatically generating malicious comments statistics.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.197-206
• /
• 2018

The harmful effects of online malicious comments are continuously increasing. Many previous studies have confirmed that neutralization of malicious comments is a key predictor. Neutralization is theoretically composed of seven multidimensional concepts, and the significance of neutralization factors varies depending on the type of deviant behavior. This study focuses on the fact that the malicious comment researches have considered the neutralization techniques in a single dimension as opposed to demonstrating the multidimensional neutralization techniques in the deviant behavior research. On the other hand, the role of arbitrator in deviant behavior can contribute to restraining deviant behavior, but the research of intervention intention is relatively lacking in malicious comments research. This study, composed of two complementary studies, tried to find out the related factors of malicious comments and intervention intention. As a result of study, This study revealed that malicious commentator uses the neutralization techniques of condemn the condemners and denial of responsibility. In addition, we found that affective empathy has a significant effect on the intervention intention in malicious comments.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.45-56
• /
• 2009

There are many internet users who collect the public opinions and express their opinions for internet news or blog articles through the replying comment on online community. But, it is hard to search and explore useful messages on web blogs since most of web blog systems show articles and their comments to the form of sequential list. Also, spam and malicious comments have become social problems as the internet users increase. In this paper, we propose a clustering and visualizing system for responding comments on large-scale weblogs, namely 'Daum AGORA,' using similarity analysis. Our system shows the comment clustering result as a simple screen view. Our system also detects spam comments using Needleman-Wunsch algorithm that is a well-known algorithm in bioinformatics.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.103-110
• /
• 2023

With the spread of the Internet, anonymous communities emerged along with the activation of communities for communication between people, and many users are doing harm to others, such as posting aggressive posts and leaving comments using anonymity. In the past, administrators directly checked posts and comments, then deleted and blocked them, but as the number of community users increased, they reached a level that managers could not continue to monitor. Initially, word filtering techniques were used to prevent malicious writing from being posted in a form that could not post or comment if a specific word was included, but they avoided filtering in a bypassed form, such as using similar words. As a way to solve this problem, deep learning was used to monitor posts posted by users in real-time, but recently, the community uses words that can only be understood by the community or from a human perspective, not from a general Korean word. There are various types and forms of characters, making it difficult to learn everything in the artificial intelligence model. Therefore, in this paper, we proposes a preprocessing technique in which each character of a sentence is imaged using a CNN model that learns the consonants, vowel and spacing images of Korean word and converts characters that can only be understood from a human perspective into characters predicted by the CNN model. As a result of the experiment, it was confirmed that the performance of the LSTM, BiLSTM and CNN-BiLSTM models increased by 3.2%, 3.3%, and 4.88%, respectively, through the proposed preprocessing technique.

• The Journal of the Korea Contents Association
• /
• v.15 no.4
• /
• pp.391-406
• /
• 2015

As the individual participation in online news sites proliferates, the importance of online news comments has been increasing. Social comment services which help people leave comments on news articles using their own SNS (social networking site) accounts have gained popularity recently. Using data gathered from an online news site, this study, therefore, (1) identifies factors differentiating social comments from general comments, (2) examines how social comments are significantly different from general comments in terms of each factor, (3) and further validates how the social comments' characteristics vary among different type of SNS. Then, we investigated this study by applying t-test, ANOVA, and Duncan test of SPSS Statistics. Our results provide insights on the significant differences in all the factors between general and social comments. We also found that there is a significant difference between Facebook and Twitter groups among three types of SNS. The findings of this study would help assess the actual benefit of social comment services as they may provide us with several valuable leads to solve the malicious comments issue. Moreover, they would suggest the need to apply this service to other areas, such as online environments in private and public sectors.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.775-778
• /
• 2021

악성 댓글은 언어폭력이며 사이버 범죄의 일종으로 인터넷상에서 상대방이 올린 글에 비방이나 험담을 하는 악의적인 댓글을 말한다. 악성 댓글을 단순히 차단하는 다른 프로그램들과는 달리 해당 영상의 악성 댓글의 비율을 알려주고 악플러들의 닉네임과 그 빈도를 나타내주는 것으로 차별화를 두었다. 따라서 많은 유튜버들이 겪는 악성 댓글 문제들을 탐지하여 유튜브에 달리는 악성 댓글들을 탐지하고 시각화하여 제공한다.