• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.563-569
• /
• 2012

The studies of opinion mining or sentiment analysis have been the focus with social web proliferation. Sentiment analysis requires sentiment resources to decide its polarity. In the existing sentiment analysis, they have been built resources designed with intensity of sentiment polarity and decided polarity of opinion using the ones. In this paper, I will present sentiment categories for not only polarity of opinion but also the basis of positive/negative opinion. I will define psychological emotions to primary sentiments for the reasonable classification. And I will extract the informations of sentiment from social web texts for the actual distribution of sentiments in social web. Re-classifying primary sentiments based on extracted sentiment information, I will organize sentiment categories for the social web. In this paper, I will present 23 categories of sentiment by using proposed method.

• 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.

• Asian Journal for Public Opinion Research
• /
• v.8 no.3
• /
• pp.180-196
• /
• 2020

This paper considers Japanese political interviews to integrate conversation and facial expression analysis. The behaviors of political leaders will be disclosed by analyzing questions and responses by using the turn-taking system in conversation analysis. Additionally, audiences who cannot understand verbal expressions alone will understand the psychology of political leaders by analyzing their facial expressions. Integral analyses promote understanding of the types of facial and verbal expressions of politicians and their effect on public opinion. Politicians have unique techniques to convince people. If people do not know these techniques and ways of various expressions, they will become confused, and politics may fall into populism as a result. To avoid this, a complete understanding of verbal and non-verbal behaviors is needed. This paper presents two analyses. The first analysis is a qualitative analysis that deals with Prime Minister Shinzō Abe and shows that differences between words and happy facial expressions occur. That result indicates that Abe expresses disgusted facial expressions when faced with the same question from an interviewer. The second is a quantitative multiple regression analysis where the dependent variables are six facial expressions: happy, sad, angry, surprised, scared, and disgusted. The independent variable is when politicians have a threat to face. Political interviews that directly inform audiences are used as a tool by politicians. Those interviews play an important role in modelling public opinion. The audience watches political interviews, and these mold support to the party. Watching political interviews contributes to the decision to support the political party when they vote in a coming election.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.4
• /
• pp.181-191
• /
• 2021

The aim of the study is to empirically investigate and analyze the influence of public welfare, audit findings, and follow-up of audit recommendations on audit opinion with the disclosure level of financial reports as an intervening variable using agency theory and signaling theory. To achieve this purpose, a quantitative research method was employed. Population of this study is Provincial Government Financial Reports in Indonesia for fiscal years 2016 to 2018. There were 84 financial reports that met the criteria of purposive sampling. The data were gathered from the websites of the Audit Board of the Republic of Indonesia and the Indonesian Central Bureau of Statistics. In this study, the hypothesis-testing tool is path analysis using the Statistical Package for Social Sciences version 15. Based on the multiple regression analysis, the results show that audit findings, public income, and the disclosure level of financial reports significantly influenced audit opinion. Besides, the follow-up of audit recommendations and public health significantly influenced audit opinion through the disclosure level of financial reports. This study suggests that, in order to have better audit opinion, local governments need to improve public welfare, follow-up audit finding, and disclose more details in financial report.

• International Journal of Advanced Culture Technology
• /
• v.11 no.3
• /
• pp.1-8
• /
• 2023

International public opinion on King Sejong Institute (KSI) is one of the most important factors influencing its overseas development as a worldwide non-profit educational service organization. China is one of the overseas strategic regions for KSI to spread the Korean Language. This paper intends to assess KSI's current public opinion environment in China. With content analysis of 87 news reports related to KSI in WeChat Official Accounts from 2014 to 2022, this paper attempts to assess the public opinion environment of KSI in China. In this paper, we show that the Chinese media' s current attention to KSI is generally lacking. The current reports focus more on activity narrations, and the main report factors come from local media and universities' oncampus news, which have relatively weak dissemination power and limited influences. On one side, the reasons are related to the characteristics of Chinese media, while the KSI establishment method in China also accounts for a lot. Therefore, it is necessary for the KSI to timely adjust the cooperation mode and publicity strategies according to the Chinese political and cultural characteristics to promote the sustainable development of KSI in China by continuously improving the public opinion environment.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.259-266
• /
• 2023

In this paper, we propose an algorithm that can improve the accuracy performance of collaborative filtering using attribute-based opinion mining (ABOM). For the experiment, a total of 1,227 online consumer review data about smartphone apps from domestic smartphone users were used for analysis. After morpheme analysis using the KKMA (Kkokkoma) analyzer and emotional word analysis using KOSAC, attribute extraction is performed using LDA topic modeling, and the topic modeling results for each weighted review are used to add up the ratings of collaborative filtering and the sentiment score. MAE, MAPE, and RMSE, which are statistical model performance evaluations that calculate the average accuracy error, were used. Through experiments, we predicted the accuracy of online customers' app ratings (APP_Score) by combining traditional collaborative filtering among the recommendation algorithms and the attribute-based opinion mining (ABOM) technique, which combines LDA attribute extraction and sentiment analysis. As a result of the analysis, it was found that the prediction accuracy of ratings using attribute-based opinion mining CF was better than that of ratings implementing traditional collaborative filtering.

• Asian Journal for Public Opinion Research
• /
• v.8 no.3
• /
• pp.393-406
• /
• 2020

The discourse on the lockdown in Indonesia is getting stronger due to the increasing number of positive cases of the coronavirus and the death rate. As of August 12, 2020, the confirmed number of COVID-19 cases in Indonesia reached 130,718. There were 85,798 victims who have recovered and 5,903 who have died. Data show a significant increase in cases of COVID-19 every day. For this reason, there needs to be an evaluation of the government policy of the Republic of Indonesia in dealing with the COVID-19 pandemic in Indonesia. An evaluation of policies for handling the pandemic must include public opinion to determine any weaknesses of this policy. The development of public opinion about the lockdown policy can be understood through social media. During the COVID-19 pandemic, measuring public opinion through traditional methods (surveys) was difficult. For this reason, we utilized big data on social media as research data. The main purpose of this study is to understand public opinion on the lockdown policy in overcoming the COVID-19 pandemic in Indonesia. The things observed included: volume of Twitter users, top influencers, top tweets, and communication networks between Twitter users. For the methodological development of future public opinion research, the researchers outline the obstacles faced in researching public opinion based on big data from Twitter. The research results show that the lockdown policy is an interesting issue, as evidenced by the number of active users (79,502) forming 133,209 networks. Posts about the lockdown on Twitter continued to increase after the implementation of the lockdown policy on April 10, 2020. The lockdown policy has caused various reactions, seen from the word analysis showing 14.8% positive sentiment, 17.5% negative, and 67.67% non-categorized words. Sources of information who have played the roles of top influencers regarding the lockdown policy include: Jokowi (the president of the Republic of Indonesia), online media, television media, government departments, and governors. Based on the analysis of the network structure, it shows that Jokowi has a central role in controlling the lockdown policy. Several challenges were found in this study: 1) choosing keywords for downloading data, 2) categorizing words containing public opinion sentiment, and 3) determining the sample size.

• Proceedings of KOSOMES biannual meeting
• /
• 2005.11a
• /
• pp.79-84
• /
• 2005

This paper proposes an analysis to image of inchon port using fuzzy theory. After analysis, positive opinion is mean membership function 0.73 and positive membership function 0.27, negative opinion is mean membership function 0.69, negative membership function 0.31 about inchon port development. therefore, for port development need to accomodation of each opinion postive opinion is maximum decrease from 20 age to 30 age. and negative opinion is maximum increase from 10 age to 20 age. According to the results, port development need to high positive image and low negative image.

• Journal of Information Science Theory and Practice
• /
• v.1 no.1
• /
• pp.10-26
• /
• 2013

Domain transfer is a widely recognized problem for machine learning algorithms because models built upon one data domain generally do not perform well in another data domain. This is especially a challenge for tasks such as opinion classification, which often has to deal with insufficient quantities of labeled data. This study investigates the feasibility of self-training in dealing with the domain transfer problem in opinion classification via leveraging labeled data in non-target data domain(s) and unlabeled data in the target-domain. Specifically, self-training is evaluated for effectiveness in sparse data situations and feasibility for domain adaptation in opinion classification. Three types of Web content are tested: edited news articles, semi-structured movie reviews, and the informal and unstructured content of the blogosphere. Findings of this study suggest that, when there are limited labeled data, self-training is a promising approach for opinion classification, although the contributions vary across data domains. Significant improvement was demonstrated for the most challenging data domain-the blogosphere-when a domain transfer-based self-training strategy was implemented.

• Korean journal of communication and information
• /
• v.39
• /
• pp.284-323
• /
• 2007

This study aims to examine the relation between opinion perception and opinion expression by issue types by analyzing online poll results and respective bulletin boards. To find out how opinion poll results affect the public opinion perception cues and opinion expression through the internet, the study applied a method of content analysis to the online contents provided by Naver.com, one of the most popular portal sites in Korea. A total of four issue types, along with 2,250 messages were chosen for analysis. The study results revealed that internet users perceived opinion atmosphere through the poll results and expressed their opinions depending on the issue types. In case of an issue where majority views are manifested as online poll results, users tended to follow that majority views by retaining their initial opinion. Majority opinion by the poll results held a dominant position in bulletin board. The results partially support Noelle-Neuman(1994)'s spiral of silence theory in the context of computer-mediated communication contrary to the belief that anonymity in the cyberspace tends to encourage participation of minority opinion group. According to the findings, people when they perceive their opinion as that of minority are discouraged to express their views even when they are online.