• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.4
• /
• pp.315-334
• /
• 2013

This study performs opinion mining of newspaper articles, based on topics extracted by topic modeling. We analyze the attitudes of the news media towards a major issue of 'presidential election', assuming that newspaper partisanship is a kind of opinion. We first extract topics from a large collection of newspaper texts, and examine how the topics are distributed over the entire dataset. The structure and content of each topic are then investigated by means of network analysis. Finally we track down the chronological distribution of the topics in each of the newspapers through time serial analysis. The result reveals that both the liberal newspapers and the conservative newspapers exhibit their own tendency to report in line with their adopted ideology. This confirms that we can count on opinion mining technique based on topics in order to analyze opinion in a reliable fashion.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.1
• /
• pp.1-10
• /
• 2018

Current evaluation practices for IT projects suffer from several problems, which include the difficulty of self-explanation for the evaluation results and the improperly scaled scoring system. This study aims to develop a methodology of opinion mining to extract key factors for the causal relationship analysis and to assess the feasibility of quantifying evaluation scores from text comments using opinion mining based on big data analysis. The research has been performed on the domain of publicly procured IT proposal evaluations, which are managed by the National Procurement Service. Around 10,000 sets of comments and evaluation scores have been gathered, most of which are in the form of digital data but some in paper documents. Thus, more refined form of text has been prepared using various tools. From them, keywords for factors and polarity indicators have been extracted, and experts on this domain have selected some of them as the key factors and indicators. Also, those keywords have been grouped into into dimensions. Causal relationship between keyword or dimension factors and evaluation scores were analyzed based on the two research models-a keyword-based model and a dimension-based model, using the correlation analysis and the regression analysis. The results show that keyword factors such as planning, strategy, technology and PM mostly affects the evaluation result and that the keywords are more appropriate forms of factors for causal relationship analysis than the dimensions. Also, it can be asserted from the analysis that evaluation scores can be composed or calculated from the unstructured text comments using opinion mining, when a comprehensive dictionary of polarity for Korean language can be provided. This study may contribute to the area of big data-based evaluation methodology and opinion mining for IT proposal evaluation, leading to a more reliable and effective IT proposal evaluation method.

• Hwankyungkyoyuk
• /
• v.18 no.1 s.26
• /
• pp.70-81
• /
• 2005

The importance of classes aiming at enhancing students ability in problem solving and decision making has been being recognized as chances of individual citizen for taking part in social decision making processes. This study was intended to find whether teachers' opinion presentation have effects on students' decision making in a class introducing environmental issues. Total of 6 classes, 202 middle school students have participated in a series of experiments including 4 different environmental issues. Only two issues had been addresses in classes as experimental issues and other two issues not addressed as control issues. For each of the two experimental issues, the teacher researcher applied three different approaches to his students that included positive, negative, or no opinion. The results of this study can be summarized as follows; First, the results showed that students changed their decisions on environmental issues more frequently when dealing with those issues in a class than when not dealing with them. Second, as examining the relationship between patterns in which students make decisions and whether a teacher proposed his opinions or not, it is shown that the rates of students whose opinions is not changed nearly have no difference, while when teachers propose their opinions, it is shown that students who haven't yet chosen their positions easily make their decisions into pros or cons, compared with the opposite case. Third, the results of this study partly supported the third hypothesis that teachers opinion presentation would effect on decision-making of students. It was found that there has been a significant effect in the case of car free day system issue, but no statistically meaningful result in the case of no pets in the national park issue. However, in the issue of car free day system, it seems pretty clear that the students followed the direction of teachers' opinion no matter what it was pros or cons.

• Korean Journal of Human Ecology
• /
• v.2 no.1
• /
• pp.53-61
• /
• 1993

The purpose of this research was to find out relationships between the use of fashion information, preference of fashion advertising and fashion leadership. This research was carried out by both the theoretical and empirical study. For the theoretical study, the research of Fashion Leadership was based on the fashion opinion leadership and innovativeness. The study include the analysis of variables influencing fashion leadership, such as use of fashion information preference of fashion advertising, and demographic variables. For the empirical study, fashion leadership was measured by fashion opinion leadership and innovativeness. The variables influencing on the fashion leadership were measured by use of fashion information (marketer-dominated information, consumer-dominated information, neutral information), preference of fashion advertising (dramatic type, feeling type, goods demonstration type), demorgraphic variables (age, years of education, family income, job, marriage). Data were obtained from 313 female in chungbuk area by self-administered questionaire. The datacollected through the questionaire were analyzed by the stastical technique - ANOVA and Duncantest, t-test, stepwise multiple-regression. The results of the study were as follows; 1. There were significant differences on the fashion leadership, fashion innovativeness, fashion opinionleadership according to the marketer dominated information and neutral information. There were significant differences on the fashion leadership, fashion innovativeness, fashion opinion leadership according to the preference of dramatic type. There were significant differences on the fashion opinion leadership according to the preference of goods demonstration type. 2. 30 percent of the total variance of fashion leadership was explained by the six variables: fashion magazines, TV & Radio advertising, clothing of TV talent & singer, years of education, dramatic type, catalogue. 3. When the subjects were divided into five groups(innovative communicators, innovators, opinion leaders, followers, indifferents) according to their innovativeness scores and opinion leadership scores, there were significant differences among groups in most of use of fashion information, preference of fashion advertising variables and in some of demographic variables. 4. There were significant interactions between marketer-dominated information and dramatic type and were significant interactions in goods demonstration type, marketer-dominated information and dramatic type. There were significant interactions between consumer-dominated information and dramatic type. This ariables has the effect on Fashion Leadership by the interactions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.225-230
• /
• 2012

The opinion mining is that to use the existing data mining technology also uploaded blog to web, to use product comment, the opinion mining can extract the author's opinion therefore it not judge text's subject, only judge subject's emotion. In this paper, published opinion mining algorithms and the text using speech recognition API for non-voice data to judge the emotions suggested. The system is open and the Subject associated with Google Voice Recognition API sunwihwa algorithm, the algorithm determines the polarity through improved design, based on this interview, speech recognition, which implements the model.

• The Journal of the Convergence on Culture Technology
• /
• v.6 no.1
• /
• pp.111-120
• /
• 2020

As an application of big data and artificial intelligence techniques, this study proposes an atypical language-based sentimental opinion poll methodology, unlike conventional opinion poll methodology. An alternative method for the sentimental classification model based on existing statistical analysis was to collect real-time Twitter data related to parliamentary elections and perform empirical analyses on the Polarity and Intensity of public opinion using attribute-based sensitivity analysis. In order to classify the polarity of words used on individual SNS, the polarity of the new Twitter data was estimated using the learned Lasso and Ridge regression models while extracting independent variables that greatly affect the polarity variables. A social network analysis of the relationships of people with friends on SNS suggested a way to identify peer group sensitivity. Based on what voters expressed on social media, political opinion sensitivity analysis was used to predict party approval rating and measure the accuracy of the predictive model polarity analysis, confirming the applicability of the sensitivity analysis methodology in the political field.

• The KIPS Transactions:PartD
• /
• v.18D no.4
• /
• pp.237-244
• /
• 2011

Opinion Mining summarizes with classifying sensitive opinions of customers in huge online customer reviews for the attributes of products or services by positive and negative opinions. Because the customers represent their interests through subjective opinions as well as objective facts, the existing opinion mining techniques, which can analyze just the sensitive opinions, need to be expanded.. In this paper, We propose the novel entity association network model which expands the existing opinion mining techniques. The entity association model can not only represent positive and negative degree of the sensitive opinions, but also can represent the degree of the associations and relative importances between entities. We designed and implemented the customer reviews analysis system based on the entity association network model. We recognized that the system can represent more abundant information than the existing opinion mining techniques.

• International Area Studies Review
• /
• v.15 no.3
• /
• pp.493-511
• /
• 2011

This study investigate the impacts of Chinese consumers' cultural dispositions on the WOM behaviors in SNS. Specifically, cultural dispositions in the individual-level, collectivism and uncertainty avoidance, were examined as potential predictors of eWOM behaviors in SNSs. Hypotheses are tested with a sample of 164 university students in Shanghai, China. The results of the structural equation analysis reveal that chinese consumers' collectivism in the individual-level positively affects the opinion seeking behavior. And chinese consumers' uncertainty avoidance in the individual-level positively affects the opinion seeking behavior and negatively affects the opinion giving behavior. Lastly, the opinion giving behavior positively affects the pass along behavior. Theoretical and managerial implications for Internet marketers in China were presented and discussed.

• Korean Journal of Forensic Psychology
• /
• v.13 no.1
• /
• pp.23-52
• /
• 2022

In this study, focused group interviews with 24 incumbent judges were conducted on how they conceptualize public opinion and what attitude they take toward it in relation to judicial trials. The contents of the interviews were analyzed through grounded theory and topic modeling (STM). According to the grounded theory results, judges distinguished concepts such as social rules, socially accepted ideas, legal emotion, and public mood from public opinion, and subdivided public opinion into temporary and emotional reactions to specific legal cases and consistent attitudes toward law and policies. In addition, it was found that judges' attitudes toward public opinion and social norms differed depending on the type of cases or legal issues. Topic modeling results significantly corresponded to the grounded theory results. In this model, the effects of the types of cases dedicated to participants on topical prevalence were statistically significant.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1800-1808
• /
• 2022

During the election period, many polling agencies survey and distribute the approval ratings for each candidate. In the past, public opinion was expressed through the Internet, mobile SNS, or community, although in the past, people had no choice but to survey the approval rating by relying on opinion polls. Therefore, if the public opinion expressed on the Internet is understood through natural language analysis, it is possible to determine the candidate's approval rate as accurately as the result of the opinion poll. Therefore, this paper proposes a method of inferring the approval rate of candidates during the election period by synthesizing the political comments of users through internet community posting data. In order to analyze the approval rate in the post, I would like to suggest a method for generating the model that has the highest correlation with the actual opinion poll by using the KoBert, KcBert, and KoELECTRA models.