• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.25-34
• /
• 2022

With the development of online services, the ripple effect of negative comments is increasing, and the damage of cyber violence is rising. Various methods such as filtering based on forbidden words and reporting systems prevent this, but it is challenging to eradicate negative comments. Therefore, this study aimed to increase the accuracy of the classification of negative comments using deep learning and blur the parts corresponding to profanity. Two different conditional training helped decide the number of deep learning layers and filters. The accuracy of 88% confirmed with 90% of the dataset for training and 10% for tests. In addition, Grad-CAM enabled us to find and blur the location of swear words in negative comments. Although the accuracy of classifying comments based on simple forbidden words was 56%, it was found that blurring negative comments through the deep learning model was more effective.

• (The)Study of the Eastern Classic
• /
• no.70
• /
• pp.9-31
• /
• 2018

Houshan's Comments on Poets and Poetry by Chen Shidao, one of the most famous comments on poets and poetry in the Northern Song Dynasty, is regarded as the early masterpiece of the literary critic genre called comments on poets an poetry. In particular, the theory on poetry of Houshan's Comments on Poets and Poetry reflected the overall literature fashion of the Song Dynasty, and captured the typical arguments of poetics in the Song Dynasty. The poet's character-building and accumulation of knowledge, the study of Du Fu and other poets and a quest for "No Trace" reveal the practice and aesthetics of the poets in the Northern Song Dynasty. So far, Chen Shidao has been known as a formalist poet, and he has actually focused on learning the rules of verse and learning classical poetry. But the final goal of his theory on poetry was a free creation, not the strict rules. He just thought that he could get the freedom of creation by constantly learning rules and building a poem. Therefore, his comments in Houshan's Comments on Poets and Poetry can not be regarded as simply formalist views. Because he wanted to achieve his ideal freedom of creation with elaborate formats and content.

• Journal of Information Technology Services
• /
• v.11 no.2
• /
• pp.69-91
• /
• 2012

The purpose of the study is to investigate the effects of direction of comments about online reviews and the credibility of web sites on brand attitudes toward restaurants. Also, the study compared two study results using Korean and Chinese on-line users to assess the feasibility of the application of on-line marketing developed in Korea to Chinese internet user contexts. The results show that the credibility of web sites and the direction of comments influence the brand attitude as hypothesized. Overall, the results from two country consumer groups are similar. However, there are unique results including the significant interaction effects between the direction of comments and the credibility of web sites only for Chinese on-line users on the brand evaluation tasks and for Korean on-line users on the purchase intention. The cultural value might cause these different results across the nations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3023-3036
• /
• 2019

This study investigated the television (TV) content viewers' behavior influenced by online communication at the choice of new TV series on a terrestrial streaming platform. For exploring the impact of the anchoring effect on the TV content consumption, this study analyzed the correlation between the first episode's TV ratings and the data of online comments or reactions. These data were potential audiences' communication, which were generated on the online article three weeks before the first broadcasting began. To avoid the crucial influence by external factors, such as season and social issue, the test was done with eight (8) TV series which have same genre (drama), similar core audience targeting (20-49's women), similar broadcasting period (Jun-Oct 2016), same scheduling (10.00 to 11.00 pm, weekdays) and aired on terrestrial TV platforms. This research found that not only the amount of comments and reactions, but also the attitude about the comments created before broadcasting, positively influence the audiences' decision-making behavior for new TV content choices. This investigation contributes to the literature on media economics and management by exploring the media content users' consuming behavior with behavioral economics perspectives (anchoring effect) and making a first step for finding a new effect on the media content consumption.

• Asia pacific journal of information systems
• /
• v.31 no.1
• /
• pp.1-16
• /
• 2021

Cyberbullying has become a social problem as malicious text messages and online comments among teenagers have increased in the late 2000s. Some serious reporting has attempted to impress on us the need to pay more attention to reducing malicious online content as a typical type of cyberbullying. Meanwhile, despite environmental changes that have made it easier to report perpetrators of such messages, it is often the case that the crime occurs in a public place and is tolerated. However, there is a growing tendency for people to exhibit the bystander effect, the problem of personal indifference to witnessing or knowing about crimes, but individuals do not offer any means of help to a victim when other people are present. This effect is rampant in the case of cybercrimes. This study aims to extract the motivations behind posting malicious comments through in-depth interviews and to suggest recommendations for relative issues by demonstrating how the bystander effect can be reduced using causal relationship diagrams of the system dynamics methodology. Hopefully, this work will contribute to a better understanding of factors that could cause a decrease in malicious online comments.

• Asian Journal for Public Opinion Research
• /
• v.7 no.3
• /
• pp.169-198
• /
• 2019

This study focused on the increase in refugee-related discourse in Korean society with the recent inflow of asylum seekers to Jeju Island. The purpose of our study was to understand the trends in public opinion concerning the acceptance of refugees by analyzing the content of refugee-related video commentary on YouTube. Topic modeling was conducted to analyze the main points, context, and ideas in the comments. The results indicated that the media mainly focus on the pros and cons of refugees, restricting the refugee issue to the problem of acceptance with a narrow focus on the case of Jeju Island. Refugee acceptance was treated as overwhelmingly unacceptable in the comments. We found that commenters often used negative discourse in the comments as a device for reproducing and amplifying hate speech.

• The Journal of the Korea Contents Association
• /
• v.10 no.8
• /
• pp.38-50
• /
• 2010

In recent years, the number of users who are actively express their opinions about Internet articles is more and more growing up, as the use of cyber community such as weblog or Internet discussion board increases. In fact, it is not difficult to find an article with hundreds of comments in famous Internet discussion boards. Most of the weblogs or Internet discussion boards present comments in the form of list and do not yet support even the basic operation such as searching comments. In this paper, we analysed large sets of comments in Internet discussion board named AGORA. It was found that from the result that the distribution of comment writers follows power-law. So we suppose a new search structure of comments using skip lists. The main idea of our approach is to reflect the probabilistic distribution properties of the commenters following the power-law to the data structure. Our empirical results show that the proposed method performs more efficient in searching the nodes with fewer number of comparison operations than logN, which is the theoretical time complexity of general indexed structure such as B-trees or typical skip lists.

• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.513-524
• /
• 2020

Recently, YouTube's growth started drawing attention. YouTube is not only a content-consumption channel but also provides a space for consumers to express their intention. Consumers share their opinions on YouTube through comments. The study focuses on the text of global entrepreneurs' speeches and the comments in response to those speeches on YouTube. A content analysis was conducted for each speech and comment using the text mining software Leximancer. We analyzed the theme of each entrepreneurial speech and derived topics related to the propensity and characteristics of individual entrepreneurs. In the comments, we found the theme of money, work and need to be common regardless of the content of each speech. Talking into account the different lengths of text, we additionally performed a Prominence Index analysis. We derived time, future, better, best, change, life, business, and need as common keywords for speech contents and viewer comments. Users who watched an entrepreneur's speech on YouTube responded equally to the topics of life, time, future, customer needs, and positive change.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.1
• /
• pp.434-445
• /
• 2015

In reading news stories online, people are exposed to others' comments to a news story. In spite of popularity of comments to a news story online, the understanding of why and who posts a comment is still lacking. To complement scarcity and have a better understanding of comment-posting online, this study examined psychological factors which affect the likelihood of posting a comment to a news story online. In particular, three variables were considered: The first variable was communication efficacy, that is, an individual's belief about communication practices and systems, under the supposition that the people who have greater levels of communication efficacy are more likely to post a comment. The second variable was perception of public opinion, to test that when and if people judge their position of the issue as favored by the majority, they tend to post a comment. And finally, the tone of existing comments was included, to test if the tone of comments affects the willingness to post a comment. The results showed that firstly, people at a high level of communication efficacy are more likely to post a comment compared to people at the low level of communication efficacy. Secondly, the perception of public opinion partly influenced the willingness to post a comment. Especially, when people believe communication systems contribute to develop society and also when judged that their opinion is the majority's opinion, they are more likely to post a comment. Finally, the tone of the comments influenced the willingness to post a comment only on the condition that people are confident of the communication practice and are exposed to emotional comments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.2
• /
• pp.260-267
• /
• 2016

The Internet has brought lots of changes to us sharing information mutually. However, as all social symptom have double-sided character, it has serious social problem. Vicious users have been taking advantage of anonymity on the Internet, stating comments aggressively for defamation, personal attacks, privacy violation and more. Malicious comments on the Internet are creating the biggest problem regarding unlawful acts and insults which occur on the Internet. In order to solve the issues, several studies have been done to efficiently manage the comments. However, there are limitations to recognize modified malicious vocabulary in previous research. So, in this paper, we propose a malicious comments detection technique by improving limitation of previous studies. The experimental result has shown accuracy of 87.8% providing higher accuracy as compared to previous studies done.