• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.1825-1844
• /
• 2019

Political campaigns circulate manipulative opinions in online communities to implant false beliefs and eventually win elections. Not only is this type of manipulation unfair, it also has long-lasting negative impacts on people's lives. Existing tools detect political manipulation based on a supervised classifier, which is accurate when trained with large labeled data. However, preparing this data becomes an excessive burden and must be repeated often to reflect changing manipulation tactics. We propose a practical detection system that requires moderate groundwork to achieve a sufficient level of accuracy. The proposed system groups opinions with similar properties into clusters, and then labels a few opinions from each cluster to build a classifier. It also models each opinion with features deduced from raw data with no additional processing. To validate the system, we collected over a million opinions during three nation-wide campaigns in South Korea. The system reduced groundwork from 200K to nearly 200 labeling tasks, and correctly identified over 90% of manipulative opinions. The system also effectively identified transitions in manipulative tactics over time. We suggest that online communities perform periodic audits using the proposed system to highlight manipulative opinions and emerging tactics.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.165-175
• /
• 2023

Boryeong Mud Festival has become a representative local festival that both domestic and foreign tourists can enjoy together. In addition, it is one of the usual hands-on marine festivals in Korea that can be enjoyed with one mind at the Boryeong Mud Festival, regardless of race, age, and language. This study explored the overall perception and trends of the Boryeong Mud Festival using big data extracted online from the Boryeong Mud Festival. First, keywords such as Chungnam, hosting, summer, reporter, experience, opening ceremony, performance, operation, news, tourist, opening, event, and festival were frequently exposed online. Second, due to centrality analysis, the centrality of festival experience programs and performances, opening ceremonies, and Boryeong mayor was high. Third, due to the CONCOR analysis, five clusters of meaningful keywords related to the Boryeong Mud Festival were formed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.1022-1034
• /
• 2023

Various aspects of artificial intelligence (AI) have become of significant interest to academia and industry in recent times. To satisfy these academic and industrial interests, it is necessary to comprehensively investigate trends in AI-related changes of diverse areas. In this study, we identified and predicted emerging convergences with the help of AI-associated research abstracts collected from the SCOPUS database. The bidirectional encoder representations obtained via the transformers-based topic discovery technique were subsequently deployed to identify emerging topics related to AI. The topics discovered concern edge computing, biomedical algorithms, predictive defect maintenance, medical applications, fake news detection with block chain, explainable AI and COVID-19 applications. Their convergences were further analyzed based on the shortest path between topics to predict emerging convergences. Our findings indicated emerging AI convergences towards healthcare, manufacturing, legal applications, and marketing. These findings are expected to have policy implications for facilitating the convergences in diverse industries. Potentially, this study could contribute to the exploitation and adoption of AI-enabled convergences from a practical perspective.

• Journal of Information Technology Applications and Management
• /
• 제21권4_spc호
• /
• pp.415-429
• /
• 2014

With the advent of smart devices, users are able to connect to each other through the Internet without the constraints of time and space. Because the Internet has become increasingly important to users in their everyday lives, reliance on it has grown. As a result, the number of web sites constantly increases and the competition between these sites becomes more intense. Even those sites that operate successfully struggle to establish new strategies for customer retention and customer development in order to survive. Many companies use various customer information in order to establish marketing strategies based on customer group segmentation A method commonly used to determine the customer groups of individual sites is to infer customer characteristics based on the customers' demographic information. However, such information cannot sufficiently represent the real characteristics of customers. For example, users who have similar demographic characteristics could nonetheless have different interests and, therefore, different buying needs. Hence, in this study, customers' interests are first identified through an analysis of their Internet news inquiry records. This information is then integrated in order to identify each web category. The study then analyzes the possibilities for the practical use of the proposed methodology through its application to actual Internet news inquiry records and web site browsing histories.

• 응용통계연구
• /
• 제27권1호
• /
• pp.159-168
• /
• 2014

Engle과 Ng (1993)가 제안한 뉴스 임팩트 커브(NIC)는 표준적인 GARCH 모형에 적용되는 대칭 커브이다. 최근들어 금융시계열의 변동성이 비대칭 성질을 가지는 경향이 있으며 이에 따라 분계점(threshlod) GARCH, 이중선형(bilinear) GARCH 등의 비대칭 모형이 연구되고 있다. 본 논문은 비대칭 모형의 변동성 커브에 대해 연구하고 있으며 LASSO를 통한 방법론을 제안하고 있다. 제시된 방법론을 국내 KOSDAQ 자료분석을 통해 예시해 보았다.

• The Journal of Asian Finance, Economics and Business
• /
• 제6권4호
• /
• pp.45-52
• /
• 2019

The current study aims to investigate the relationship between tax avoidance and firm risk in an emerging market called Iran. The study population consists of 400 observations and 80 companies listed on the Tehran Stock Exchange (TSE) over a five-year period during 2012 and 2016. The statistical model used in this study is a multivariate regression model; besides, the statistical technique used to test the hypotheses proposed in this research is panel data. The results showed that low effective tax rate (tax avoidance) is more consistent than the higher effective tax rate. Moreover, there is no significant relationship between tax avoidance and future tax rate volatility. The findings also proved that lower effective tax rates are positively associated with future stock price volatility. This implies that since Iranian firms have many financial problems because of economic sanctions, they have a tendency to delay the disclosure of bad news about their firms. Needless to say, when a huge number of negative news reaches its peak, they immediately will enter the market and lead to a remarkable fluctuation in stock prices.

• 한국언론정보학보
• /
• 제16권
• /
• pp.108-135
• /
• 2001

This study examines the structure of the problems of Korean newspaper reporting raised by the civil society. Based on the differences in the mode of presentation, the problems of newspaper reporting were classified into three types; prominent, associated, and isolate problem. The relations among these problems were defined as the degree of co-occurrence in the monitoring articles. A network analysis was conducted to examine the structure of the problems in Korean newspaper reporting. A $33{\times}33$ similarity matrix of the problems was created by analyzing the data from one monitoring report and two weekly media critics newspapers. The results showed that of the 33 problems, most of them were mentioned as prominent or associated problems. The problems related to the news contents were mostly treated as prominent ones, while the problems about the news writing and reporting styles were frequently treated as associated ones. The network structure of newspaper criticism based on the co-occurrence of 33 problems were divided into six clusters. Among them, the most central was the group including the problems of "unfairness,' "biased interpretation," and "vagueness". In addition, the problems were found to have different roles in the network. Of the 33 problems, two were liaisons and four were attached isolates, indicating the hierarchical structure of problems in newspaper reporting. These results were discussed in the light of two viewpoints; the absence of objective criteria in media criticism, and the need for the comparisons of the current study's results with the opinions of newspaper readers and journalists. finally, the implications for the future studies were presented.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권8호
• /
• pp.51-59
• /
• 2020

The objective of this study is to enrich the literature by investigating the impact of introduction of index future trading on spot market returns and trading volume in Vietnam. Data used in this study mainly consist of daily VN30-Index and market trading volume series during the period from February 6^th, 2012 to December 31^st, 2019. Using OLS, GARCH(1,1) and EGARCH(1,1) models, the empirical findings consistently confirm that the introduction of index future trading has no impact on the spot market returns. In addition, the results of the EGARCH(1,1) model indicate that the leverage effect on the spot market volatility is existence in HOSE. Specifically, bad news has a greater effect on the market volatility than good news of the same size. Moreover, our empirical findings reveal that the introduction of index future contracts has the positive impact on the underlying market trading volume. Specifically, the trading volume of the post-index futures introduction increases by 7.5 percent compared with the pre-index futures introduction. Finally, the results obtained from the Granger causality test for the relationship between the spot market returns and the future trading activity confirm that only uni-directional causality running from the market returns to the future trading activity exists in HOSE.

• 수산경영론집
• /
• 제46권3호
• /
• pp.119-127
• /
• 2015

This study is to analyse the causality and volatility spillover between farming fish species in consumption replacement relation using flatfish(oliver flounder) and rockfish's wholesale market price data from September 2006 to July 2015. For the analysis, VAR(5) model and bivariate asymmetric GARCH-BEKK model are employed. The empirical results of this study are summarized as follows: First, the price volatility of flatfish and rockfish is very large without the trend during the sample period. Second, the correlation coefficient between flatfish and rockfish wholesale markets has positive 0.1059 value. Third, causality relation is unidirectional from rockfish market to flatfish market. Fourth, conditional volatility spillover effect is unidirectional from rockfish market to flatfish market, but asymmetric volatility effect is bidirectional between flatfish and rockfish markets that implies the bad news arising from flatfish wholesale market impact on rockfish market's volatility and the bad news arising from rockfish wholesale market impact on flatfish market's volaltilty. Consequently, based on the thus results, the volatility spillover effect interacts and is bidirectional between flatfish and rockfish wholesale markets.

• Journal of Information Technology Applications and Management
• /
• 제14권3호
• /
• pp.179-197
• /
• 2007

This paper analyzed the effects of interactions among participants on the satisfaction and commitment of cyber education. Even if the quality of interactions in cyber education may not be so good as that of interactions in face to face education. various kinds of interactions could be introduced in cyber education. An email or Q/A between lecturer and students could be a good way to compensate the deficiency of cyber education. Common News Boards or Discussion Rooms among students themselves are also a powerful means to learn each other in cyber space. The result of this study shows that as interactions among participants increase. satisfaction and commitment of the lecture also increase. This study also analyzed how cyber educational effects differs as interaction type changes in space dimension and time dimension. The result shows interactions in the same cyber space such as News Board brings more desirable outcome than those in the different cyber space. But the effects of interactions classified by time dimension does not show statistically significant differences.