• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.199-219
• /
• 2018

With the everyday use of the Internet and the spread of various smart devices, users have been able to communicate in real time and the existing communication style has changed. Due to the change of the information subject by the Internet, data became more massive and caused the very large information called big data. These Big Data are seen as a new opportunity to understand social issues. In particular, text mining explores patterns using unstructured text data to find meaningful information. Since text data exists in various places such as newspaper, book, and web, the amount of data is very diverse and large, so it is suitable for understanding social reality. In recent years, there has been an increasing number of attempts to analyze texts from web such as SNS and blogs where the public can communicate freely. It is recognized as a useful method to grasp public opinion immediately so it can be used for political, social and cultural issue research. Text mining has received much attention in order to investigate the public's reputation for candidates, and to predict the voting rate instead of the polling. This is because many people question the credibility of the survey. Also, People tend to refuse or reveal their real intention when they are asked to respond to the poll. This study collected comments from the largest Internet portal site in Korea and conducted research on the 19th Korean presidential election in 2017. We collected 226,447 comments from April 29, 2017 to May 7, 2017, which includes the prohibition period of public opinion polls just prior to the presidential election day. We analyzed frequencies, associative emotional words, topic emotions, and candidate voting rates. By frequency analysis, we identified the words that are the most important issues per day. Particularly, according to the result of the presidential debate, it was seen that the candidate who became an issue was located at the top of the frequency analysis. By the analysis of associative emotional words, we were able to identify issues most relevant to each candidate. The topic emotion analysis was used to identify each candidate's topic and to express the emotions of the public on the topics. Finally, we estimated the voting rate by combining the volume of comments and sentiment score. By doing above, we explored the issues for each candidate and predicted the voting rate. The analysis showed that news comments is an effective tool for tracking the issue of presidential candidates and for predicting the voting rate. Particularly, this study showed issues per day and quantitative index for sentiment. Also it predicted voting rate for each candidate and precisely matched the ranking of the top five candidates. Each candidate will be able to objectively grasp public opinion and reflect it to the election strategy. Candidates can use positive issues more actively on election strategies, and try to correct negative issues. Particularly, candidates should be aware that they can get severe damage to their reputation if they face a moral problem. Voters can objectively look at issues and public opinion about each candidate and make more informed decisions when voting. If they refer to the results of this study before voting, they will be able to see the opinions of the public from the Big Data, and vote for a candidate with a more objective perspective. If the candidates have a campaign with reference to Big Data Analysis, the public will be more active on the web, recognizing that their wants are being reflected. The way of expressing their political views can be done in various web places. This can contribute to the act of political participation by the people.

• Journal of the Korean association of regional geographers
• /
• v.20 no.3
• /
• pp.315-333
• /
• 2014

The study was carried out to analyze election regionalism and to find out the spatial pattern of party support drawn in the 18th general election. Strongly biased pattern found to be caused by party strategies and voting behaviour preferring for the local party. Each party employed the strategies such as tactical and nepotic nomination, regional development pledges, and local instigation of regionalism. In consciousness survey done by the National Election Commission, primarily people tend to choose the representative by his(her) party and secondly, they consider their carrier and occupation. They vote for the same party in the local district and proportional representation. While election regionalism strongly found in voting behaviour of each party's main strongholds based on spatial pattern of major party support, voters of Seoul and Chungbuk tend to vote for their interests due to regional development pledges such as 'Newtown' Development and 'Multifunctional Administrative City' construction.

• Journal of Contemporary Eastern Asia
• /
• v.8 no.2
• /
• pp.27-43
• /
• 2009

A ban on political podcasting during the General Elections 2006 in Singapore was justified by the Singaporean government on the grounds that the new medium had a greater power to influence voters than traditional modes of political discourse. A between-subjects controlled experiment was conducted to test whether podcasts of political speeches had a greater power to influence voters' evaluations of political candidates and likelihood of voting for them than online text-based transcripts of the same speeches. The study also examined whether mere exposure to political speeches online, irrespective of the modality, had an effect on voters' more general political preferences, i.e. the likelihood of support and voting for the opposition. The findings suggest that political podcasts were no more persuasive than text-based websites and that the effects on political preferences, if any, were likely due the exposure to political content online, not because of the nature of the medium. The implications of the findings are discussed.

• The Research Journal of the Costume Culture
• /
• v.25 no.6
• /
• pp.893-912
• /
• 2017

Crowdsourcing models in which organizaions obtain needed product ideas and services from a crowd in a network-based society are rising as a global industry trend. The purpose of this study was to figure out the types and characteristics of crowdsourcing design shown in the domestic fashion brands, and to provide implications for design strategies using crowdsourcing. This study was based on qualitative research which was brand case studies on crowdsourcing design in the fashion industry from January 2006 to July 2017. Also, quantitative analysis using frequency and percentage was applied. The results were as follows: First, crowdsourcing design was used in almost all types of fashion brands, such as sports and outdoor wear, men's wear, women's wear, men's and women's casual wear, shoes, bags, school uniforms, jeans, accessories, etc. Crowdsourcing design in the fashion industry was classified into three types: crowdsourcing graphics and artwork; crowdsourcing customized designs; and crowdsourcing product designs. Of the three types, crowdsourcing graphics and artwork was used most. There were four methods to choose the best crowsourced design: review only by experts, voting by crowd and review by experts, crowdvoting, and crowdfunding. Second, the characteristics of crowdsourcing design were openness, participation, reward and acknowledgement, sharing and interaction, and individualized collective intelligence. Crowdsourcing design could be used as an open innovation strategy in the fashion industry, which could collect new and creative design ideas for product development, resulting in the satisfaction of consumers and benefitting the company.

• ETRI Journal
• /
• v.29 no.2
• /
• pp.179-188
• /
• 2007

We propose a multi-strategic concept-spotting approach for robust spoken language understanding of conversational Korean in a hostile recognition environment such as in-car navigation and telebanking services. Our concept-spotting method adopts a partial semantic understanding strategy within a given specific domain since the method tries to directly extract predefined meaning representation slot values from spoken language inputs. In spite of partial understanding, we can efficiently acquire the necessary information to compose interesting applications because the meaning representation slots are properly designed for specific domain-oriented understanding tasks. We also propose a multi-strategic method based on this concept-spotting approach such as a voting method. We present experiments conducted to verify the feasibility of these methods using a variety of spoken Korean data.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.360-376
• /
• 2020

Many heuristic attribute reduction algorithms have been proposed to find a single reduct that functions as the entire set of original attributes without loss of classification capability; however, the proposed reducts are not always perfect for these multiclass datasets. In this study, based on a probabilistic rough set model, we propose the class-oriented attribute reduction (COAR) algorithm, which separately finds a reduct for each target class. Thus, there is a strong dependence between a reduct and its target class. Consequently, we propose a type of ensemble constructed on a group of classifiers based on class-oriented reducts with a customized weighted majority voting strategy. We evaluated the performance of our proposed algorithm based on five real multiclass datasets. Experimental results confirm the superiority of the proposed method in terms of four general evaluation metrics.

• Journal of Contemporary Eastern Asia
• /
• v.15 no.2
• /
• pp.191-210
• /
• 2016

While general belief is that the military alliances are stable and rigid, the authors argue that the states are far more flexible in their behavior and often act against their alliances. This paper looks at states' behavior in the UN GA and looks how it is reflected in participation in military alliances during three periods of history since 1976 to this day. The authors illustrate the need to consider the network representation of co-sponsoring groups in General Assembly votes. They find significant support for their argument, indicating that social aspects can be extended beyond alliances. An application of social network analysis shows some unexpected affiliations in UN GA. If the UN GA is the "true" nature of these countries' alliance strategies, then it might suggest some significant defections and interesting association.

• Survey Research
• /
• v.12 no.1
• /
• pp.31-63
• /
• 2011

This study is to make an effective forecasting model for turn-out rates of the candidates with their visibilities, which are measured in their names on the media during the election period. I make a regressive model, with the data of 2010 gubernatorial election in Korea, where turn-out rate is dependent variable and each candidate's visibility, incumbency effect, local control party effect, corruption effect, strategy voting effect, restrain effect as a mid-term evaluation, and policy effect are independent variables. I got the model, T = -4.65 + 1.02V + 16.90 I + 16.78L - 9.12 R, where T is turn-out rate, V is candidate's visibility, I is incumbent effect, L is local control party effect, and R is restrain effect. This function can be used to predict turn-out rates of the candidates in the forthcoming gubernatorial election in Korea at a small outlay.

• Journal of Gastric Cancer
• /
• v.10 no.3
• /
• pp.141-148
• /
• 2010

We have always attempted to create a standard treatment protocol for patients with gastric cancer. However, many debates still exist regarding gastric cancer treatment. For the past 2 years, at the Annual Congress of the Korean Gastric Cancer Association, we have presented a grand symposium on the "Debates on the strategy for treating gastric cancer". In 2008, four major topics were discussed and voted on after discussion. The four major topics were proximal location treatment for early gastric cancer, management choices for pyloric obstruction with advanced gastric cancer, management of liver metastasis, and reconstruction methods after a distal gastrectomy. The opinions of the audience for six minor topics were expressed by an electronic voting system. In 2009, the four main topics were treatment for submucosal tumor sized around 2 cm, laparoscopic gastrectomy in T2N1 gastric cancer, choices for managing gastric lymphoma, and application of a pylorus preserving procedure for early gastric cancer at the antrum. The opinions of the audience for these six minor topics were expressed by an electronic voting system, as was conducted in 2008. It was good opportunity to identify a point of contact about the debates on managing gastric cancer. The results of these debates and studies will identify the best methods to treat patients with gastric cancer.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.1
• /
• pp.1-10
• /
• 2019

In terms of realizing the future e-government such as intelligent government, this paper attempts to provide an earnest and insightful reflection and suggests desirable strategies with regard to the four different crucial elements including electronic voting, electronic contract, resident registration/electronic document management, and real-estate registration as an operating strategy of intelligent government and the fourth industrial revolution regarding. The 4th industrial revolution is aimed at concentrating information or data characterized with sharing, opening, communicating and releasing in cloud computing system, analyzing big data, collecting information, and flourishing people's well-being by information and communications technology with utilizing the smart devices. Therefore, reliability of the pivotal information or data is critical and it is important for the participants being transparently shared, without the data or information being forged. In this respect, introduction or application of block chain technology is essential. This paper will review preceding studies, discuss the aspect of the 4th industrial revolution and intelligent government, then suggest operating strategies in the field of electronic voting, electronic contract, management of resident registration and electronic document and real-estate registration.