• Journal of the Korea Convergence Society
• /
• v.11 no.5
• /
• pp.199-207
• /
• 2020

Recently, big data analysis has drawn attention in various fields as it can generate value from large amounts of data and is also used to run political campaigns or predict results. However, existing research had limitations in compiling information about candidates at a high-level by analyzing only specific SNS data. Therefore, this study analyses news trends, topics extraction, sentiment analysis, keyword analysis, comment analysis for the 2017 presidential election of South Korea. The results show that various topics had been generated, and online opinions are extracted for trending keywords of respective candidates. This study also shows that portal news and comments can serve as useful tools for predicting the public's opinion on social issues. This study will This paper advances a building strategic course of action by providing a method of analyzing public opinion across various fields.

• Journal of Elementary Mathematics Education in Korea
• /
• v.18 no.3
• /
• pp.399-424
• /
• 2014

Although teacher preparation programs are important for prospective teachers to build a foundation of teaching expertise, there has been lack of research in this area. This paper analyzed in what ways prospective teachers' ability in describing and commenting on elementary mathematics instruction has been changed while they were taking in the course of teaching elementary school mathematics. The results of this study showed that in late description the teachers tended to notice the core flow of a lesson and the use of instructional strategies appropriate to the mathematical content to be taught. They also tended to comment on instructional strategies and mathematical discourse from the teacher's perspective and evaluated them without alternative approaches. A noticeable change occurred in late comments wherein prospective teachers considered both the teacher and students, supported their comments by theories they had learned through the course, and interpreted the classroom events they had noticed. Building on these results, this paper closes with implications of teacher education programs to enhance prospective teachers' ability to analyze elementary mathematics lessons.

• The KIPS Transactions:PartD
• /
• v.16D no.5
• /
• pp.817-824
• /
• 2009

In recent years, Weblog has become the most typical social media for citizens to share their opinions. And, many Weblogs reflect several social issues. There are many internet users who actively express their opinions for internet news or Weblog articles through the replying comments on online community. Hence, we can easily find internet blogs including more than 10 thousand replying comments. It is hard to search and explore useful messages on weblogs since most of weblog systems show articles and their comments to the form of sequential list. In this paper, we propose a visualizing and clustering system called TRIB (Telescope for Responding comments for Internet Blog) for a large set of responding comments for a Weblog article. TRIB clusters and visualizes the replying comments considering their contents using pre-defined user dictionary. Also, TRIB provides various personalized views considering the interests of users. To show the usefulness of TRIB, we conducted some experiments, concerning the clustering and visualizing capabilities of TRIB, with articles that have more than 1,000 comments.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.407-420
• /
• 2019

The purpose of this study is to explore the possibility of measuring advertising effectiveness through the ad evaluation text. The 384 university students were asked to evaluate the positive and negative evaluation ads of high and low involvement products by self-report method and to write ad evaluation text online. The written ad evaluation text were analyzed by KLIWC and to examine the difference between the comment of positive and negative advertising. The results of the analysis are as follows. First, there were differences between positive and negative ads in 17 psychosocial variables. Second, there were differences between positive and negative ads in 9 linguistic variables. Third, there was a significant correlation between KLIWC variables(Positive & negative emotions, inhibition, conviction, physical condition & function and sleep/dreams) and advertising effect variables. This study suggests that the advertising evaluation comment reflects the consumer's psychological reaction to advertising and the possibility of measuring the advertising effectiveness using advertising evaluation text.

• 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.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1880-1889
• /
• 2022

The online portal platform provides online news with online comments, but the anonymity of comments causes incivility, and online comments are considered social problems. While there are many foreign language-based incivility detection studies, in-depth research is not being conducted in Korea since there has not been implemented Korean language dataset which is labeled detailed criteria of incivility. In this study, the incivility notation of comments was conducted in a total of 13 items, uncivil words were summarized. Furthermore, Attention algorithm was applied to each comment and summary to extract embedding vectors. 2-d CNN followed at the end to detect incivility in given data. As a result, we showed that the proposed algorithm is useful for anti-citizen detection such as name-calling and offensive tones. This study is expected to contribute to the formation of a healthy online comment culture by detecting uncivil comments which hinder democratic discourse.

• Journal of Contemporary Eastern Asia
• /
• v.19 no.1
• /
• pp.123-143
• /
• 2020

This study examines the interplay between the reactions of YouTube users and North Korean propaganda. Interesting enough, the study has noticed changes in the strict media environment under young leader Kim. Messages delivered by the communist regime to the outside world appeared to resemble those of 'normal' countries. Although North Korean YouTube was led mainly by the account operator, visitors from different nations do comment on the channel, which suggests the possibility of building international communities for propaganda purposes. Overall, the study observed a sparsely connected social network among ordinary commenters. However, the operator did not exercise tight control over peer-to-peer communication but merely answered questions and tried to facilitate mass participation. In contrast to the many news clips, the documentary content on North Korea's YouTube channel did not explicitly advocate for North Korea's current political positions.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.23-38
• /
• 2017

In order to identify effective approaches for creating more viral Facebook posts, this research conducted an empirical content analysis of leading Korean brands' Facebook fan-pages (Samsung Mobile, SK Telecom, Kia Motors, and POSCO). Their distinctive visual storytelling and communication patterns were investigated as effective user engagement triggers. Through analysis of the research results, it was statistically proved that the different industrial attributes of the four brands, which are primarily characterized by their product (or service) types, affect their Facebook posting patterns by showing different engaging rates (measured by like, comment, and share metrics). In addition, the user engagement rates of the posts were influenced by their visual storytelling factors (i.e. ad objective, value scale, and visual media types). In line with these statistical findings, the distinctive visual storytelling strategies of the four brands were identified. Moreover, competitive and uncompetitive visual storytelling tactics were suggested according to the ad objectives and visual media types on Facebook.

• Communications for Statistical Applications and Methods
• /
• v.22 no.6
• /
• pp.639-646
• /
• 2015

We propose simultaneous tests for mean and variance under the normality assumption. After formulating the null hypothesis and its alternative, we construct test statistics based on the individual p-values for the partial tests with combining functions and derive the null distributions for the combining functions. We then illustrate our procedure with industrial data and compare the efficiency among the combining functions with individual partial ones by obtaining empirical powers through a simulation study. A discussion then follows on the intersection-union test with a combining function and simultaneous confidence region as a simultaneous inference; in addition, we discuss weighted functions and applications to the statistical quality control. Finally we comment on nonparametric simultaneous tests.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.488-492
• /
• 2006

An annotation is a marking made on a document at a particular place. Digital annotation is composed of a user comment, highlighter ink and star etc. In this paper, we study navigation techniques which applies annotation techniques of electronic document environmental in 3D virtual environment.