• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.631-634
• /
• 2008

인터넷을 이용한 사람들의 사회 참여가 확대되면서 다양한 의견(Opinion)들이 급속도로 증가하고 있으며 이러한 의견을 분석하여 유용한 정보로 활용하기 위한 연구가 활발히 진행되고 있다. 그 중에서도 상품리뷰는 기업에서 연구, 개발, 마케팅의 주요 자료로 사용되고 있으며 사용자가 상품의 구매를 결정하는 중요한 요인 중 하나로 작용하고 있다. 본 논문에서는 한국어로 이루어진 상품 리뷰를 분석하여 의견 자질(Feature)을 추출하고 분류(Classification)하는 시스템을 설계하고 구현하였다. 한글 의견 자질 추출을 위하여 먼저 한글 상품 리뷰를 분석하여 의견 사전을 구축하였다. 의견 사전으로는 의견 자질과 의견 어휘, 독립의견어휘, 의견 숙어, 부정어 등의 각기 다른 세부 사전을 구축하여 리뷰 분석 시 단계적으로 적용하여 정확도를 높일 수 있도록 설계하였다. 이렇게 구현된 시스템을 평가하기 위하여 각기 다른 3개의 도메인에서 실제 한국어 리뷰를 수집하여 실험을 수행하였으며 자질 추출에서는 평균 78.86% 정확률, 61.41% 재현율을, 극성 분류에서는 평균 69.46% 정확률, 42.26% 재현율을 나타냈다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.11a
• /
• pp.373-375
• /
• 2011

최근 많은 연구가 되고 있는 오피니언 마이닝은 의견어 사전의 구축이 가장 기본적으로 선행되어야 하는 연구이다. 오피니언 마이닝의 의견어 사전 구축 연구는 영어를 중심으로 많은 연구가 진행 되었다. 하지만 형용사 위주의 의견어 사전 구축으로 많은 부분의 문제들이 해결되는 영어에 비해서 한국어는 여러 가지 품사와 문장구조를 고려하여 의견어 사전을 구축해야한다. 이것을 실험으로 밝히기 위하여 형용사로만 구성되어진 의견어 사전을 구축하고 영화평에 적용하여 분석해 봄으로써 형용사로만 구성되어진 의견어 사전의 한계점을 확인한다. 실험은 세종계획 말뭉치에서 나타나는 형용사로 구성된 의견어 사전을 구축하고 네이버 랩에서 제공하는 영화평을 형용사로 구성된 의견어 사전으로 의견 분석하여 시행하였다. 분석 결과 재현율 약 50%, 정확률 약 60%정도의 성능을 보였다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.11
• /
• pp.21-29
• /
• 2010

Opinion retrieval which searches the opinions expressed in documents by users cannot outperform significantly yet traditional topical retrieval which searches the facts. Therefore, the focus of this paper is to identify the statistical characteristics which can be applied to opinion retrieval by comparing and analyzing the term statistics of opinion and non-opinion documents in the blog domain. The TREC Blogs06 collection and 150 TREC topics are used in the experiments. The difference between term probability distributions in opinion documents is measured by JS divergence, and the difference according to the topic types and topic domains is also investigated. Moreover, the term probabilities of opinion terms are analyzed comparatively. The main findings of this study include the following: it is necessary to consider the topic-specific characteristics for the opinion detection; it is effective to extract positive and negative opinion terms according to the topics; the topic types are complementary to the topic domains; and special attention has to be given to the usage of the positive opinion terms.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.3070-3075
• /
• 2010

Through Web 2.0 days, the end users express their opinions and thoughts for blogs and community spaces on the Internet. These opinions and thoughts are used to purchase products, however, users only refer to a few comments not overall opinions. Opinion Analysis System is an opinion search, developed from a natural language search, which analyzes the product's positive or negative evaluations using opinions of products and services on the Internet. In this paper, we suggest a syntactic analysis and inverse processing system that studies and processes 'Positive', 'Negative', 'Neutral' in addition to 'Inverse' information to analyze 'positive' or 'negative' for the core of sentences in Opinion Analysis Service.

• Information Systems Review
• /
• v.22 no.4
• /
• pp.59-74
• /
• 2020

This paper investigates the asymmetric effect of social sentimental on an individual stock price return. For this purpose, four companies such as POSCO, Korean Electricity, AMORE PACIFIC, KIA Motors are chosen from KOSPI listed companies in terms of dataperspective. The main estimation results are as follows: the positive opinions affect only the stock prices return of three companies while the negative opinions affect all of the companies. It shows that positive or negative texts give asymmetric effect on stock price return and the effect of negative opinions is bigger than that of positive opinions. The results imply that investors are more sensitive to the negatives since they have the tendency of loss aversion. Also, it indicates that subjective opinion on SNS can be used as the proxy for the investment sentiment.

• Korean journal of communication and information
• /
• v.42
• /
• pp.168-204
• /
• 2008

According to the spiral of silence theory, perception of opinion climates influences willingness to express one's opinion. This study examines the relationship between opinion perception and opinion expression in different regions and issues. The results show that one's opinion and the intensity of opinion affect the expression of opinion about national and regional issues in Busan and Gwangju. People who perceive their opinions as majority are more willing to express theirs about national and regional issues in Gwangju, but not in Busan. Regression analyses show that perceived public opinion does not predict the expression of opinion in both cities. People who perceive their opinions more favorable about regional issue have lower intention to express their opinions than people who perceive their opinions same as others'. In summary, one's opinion and perception bias about controversial issues are important variables influencing expression of opinion, and the influence of perceived public opinion on opinion expression varies in different regions with different distribution of public opinion. This study found 'new hardcores' who perceive their own opinion as minor but more valuable and have the intention to speak out in places more difficult to express.

• Journal of Science Education
• /
• v.45 no.3
• /
• pp.304-316
• /
• 2021

The purpose of this study is to analyze high school students' critical opinions on others' inquiries in small group open inquiry. Forty-one high school students participated in these activities at the inquiry planning stage and the intermediate stage of inquiry. In the two activities, 595 and 233 opinions were presented respectively, and analyzed into categories based on the inquiry process. The main research results are as follows: first, many opinions were presented in the areas of 'problem recognition and hypothesis setting' and 'design of inquiry' in the feedback on the inquiry plan, especially related to 'revision and addition of research problems,' 'research targets and conditions,' and 'control of variables.' Second, in the feedback on the results of the inquiry, there were many opinions related to 'report preparation' and 'design of inquiry' area. Based on the research results, implications related to the application of critical opinion activity were discussed.

• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.93-101
• /
• 2020

Although concerns about the opinion shopping have been continuously raised in the audit market, there has been little research on empirical evidence on the existence of audit opinions. For this reason, this study empirically confirmed whether the opinion shopping exists. At first, we measured thresholds of audit opinion issuing of two groups(changed or not-changed auditors). After that, the difference analysis was conducted to verify whether the thresholds of the audit opinion issuing was significant difference between two groups. As a result of the study, there was no significant difference in the thresholds of audit opinion issuing between two groups. This result can be interpreted that the audit opinion shopping is not a general phenomenon in the external audit market. The contribution of this study is to empirically confirmed that audit opinion shopping does not exist in the external audit market.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1681-1684
• /
• 2003

정보시스템의 위험분석은 평가결과의 신뢰성을 위해 전문지식을 가진 여러 명의 평가자에 의해 실시된다. 위험분석은 평가자의 주관적인 관점이 많이 작용하며 평가결과들 간에 편차가 생긴다. 따라서, 평가자 간에 의견을 조정하고 절충하는 절차가 필요하다. 하지만 일반적인 면대면(面對面) 의견조정 방법은 여러 가지 부작용이 있다. 본 연구에서는 비대면(非對面) 전문가 의견조정 방법인 델파이 방법을 연구하고 이를 위험분석 도구에 적용하기 위하여 웹기반 델파이의견조정시스템을 설계 및 구현해 보인다.

• 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.