• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.3169-3181
• /
• 2015

Nowadays, online word-of-mouth has become a powerful influencer to marketing and sales in business. Opinion mining and sentiment analysis is frequently adopted at market research and business analytics field for analyzing word-of-mouth content. However, there still remain several challengeable areas for 1) sentiment analysis aiming for Korean word-of-mouth content in film market, 2) availability of machine learning models only using linguistic features, 3) effect of the size of the feature set. This study took a sample of 10,000 movie reviews which had posted extremely negative/positive rating in a movie portal site, and conducted sentiment analysis with four machine learning algorithms: naïve Bayesian, decision tree, neural network, and support vector machines. We found neural network and support vector machine produced better accuracy than naïve Bayesian and decision tree on every size of the feature set. Besides, the performance of them was boosting with increasing of the feature set size.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.344-345
• /
• 2017

Opinion mining and sentiment analysis(OMSA) as a research discipline has emerged during last 15 years and provides a methodology to computationally process the unstructured data mainly to extract opinions and identify their sentiments. The relatively new but fast growing research discipline has changed a lot during these years. This paper presents a scientometric analysis of research work done on OMSA during 2007-2016. For the literature analysis, research publications indexed in Web of Science (WoS) database are used as input data. The publication data is analyzed computationally to identify year-wise publication pattern, rate of growth of publications, research areas.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.538-547
• /
• 2013

In this paper, we propose a bias detection method that is based on personal and social opinions that express contrasting views on competing topics on Twitter. We used unsupervised polarity classification is conducted for learning social opinions on targets. The $tf{\cdot}idf$ algorithm is applied to extract targets to reflect sentiments and features of tweets. Our method addresses there being a lack of a sentiment lexicon when learning social opinions. To evaluate the effectiveness of our method, experiments were conducted on four issues using Twitter test collection. The proposed method achieved significant improvements over the baselines.

• English Language & Literature Teaching
• /
• v.15 no.2
• /
• pp.121-150
• /
• 2009

This paper deals with contrastive analysis and interlanguage with respect to adjective ordering. It aimed to investigate how similar and different the orders of descriptive adjectives are in English and Korean, and how Korean EFL learners perceive the sequences of English descriptive adjectives. Data were collected from native English speakers and native Korean speakers and Korean EFL learners. The contrastive analysis showed that the order of English adjectives was size, opinion, condition, age, color, shape, material, and origin, whereas the Korean order was condition, age, opinion, color, size, shape, material, and origin. The relative order of the interlanguage was shown to be age, size, opinion, shape, condition, color, origin, and material, with the exceptions of the order of condition preceding age and that of size being the same position as condition. The interlanguage data manifested different aspects of ordering when compared with English and Korean: Some adjective combinations were similar to both English and Korean; Some were different from English or Korean; Some were different from both English and Korean. These ordering patterns are discussed in terms of such principles as the nouniness principle, the subjectivity/objectivity principle, the iconic principle, etc. On the basis of these results, some helpful suggestions are made.

• Journal of Information Technology Applications and Management
• /
• v.18 no.1
• /
• pp.41-53
• /
• 2011

The rapid development and widespread application of Internet has provided a platform for people to participate and discuss social hotspot events. In the meantime, social events may be spread throughout the Internet more quickly and widely than they did ever before, and possibly lead to serious social problems due to opinion violence or seditious rumour. This paper analyzed the Internet spread of social events, and presented a five-stage model to describe the evolution process of that spread. Furthermore, the improved IBF algorithm was applied to extract a pruned connected graph aiming to find the key nodes and the shortest spread path for the control of that spread. After analyzing the different factors that may cause the netizens' attention, this paper concluded BBS type, the visit quantity and the opinion leader are key factors which affect the Internet spread. Based on those researches, a life-cycle emergency management methodology and the related strategies were proposed for the achievement of healthy spreading environment on Internet.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.7-8
• /
• 2018

This study proposes an analysis of the Word2vec-based machine learning classifiers for the sake of opinion mining tasks. As a bench-marking method, BOW (Bag-of-Words) was adopted. On the basis of utilizing the Word2vec and BOW as feature extraction methods, we applied Laptop and Restaurant dataset to LR, DT, SVM, RF classifiers. The results showed that the Word2vec feature extraction yields more improved performance.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2009.05b
• /
• pp.185-188
• /
• 2009

Recently clients requirements and social requirements are complex and large sized in construction projects. Futhermore, processes and steps are more complexed than before. Unsuitable reflection of clients brings mistaken opinions. A phase of middle change makes delay and change. It brings problems of waste expense and time. 80, first stage of planning and schematic design processes have to reflect of clients opinion actively. by increasing of constructions project competitiveness. Recently, BIM(Building Information Modeling is being researched frequently. Through visualization of information proceed step by step and it helps cognition of adapting information. 80, this paper finds and suggests solution of reflecting clients opinion and requirements and non professional clients and positively support of client participation watching based on BIM.

• Nuclear Engineering and Technology
• /
• v.29 no.1
• /
• pp.25-34
• /
• 1997

This study presents a new approach for expert opinion elicitation process to assess an uncertainty inherent in accident management. The need to work with rare event and limited data in accident management leads analysis to use expert opinions extensively. Unlike the conventional approach using point-valued probabilities, the study proposes the concept of fuzzy probability to represent expert opinion. The use of fuzzy probability has an advantage over the conventional approach when an expert's judgment is used under limited dat3 and imprecise knowledge. The study demonstrates a method of combining and propagating fuzzy probabilities. finally, the proposed methodology is applied to the evaluation of the probability of a bottom head failure for the flooded case in the Peach Bottom BWR nuclear power plant.

• International Area Studies Review
• /
• v.20 no.2
• /
• pp.215-233
• /
• 2016

In 2003, the differing stances about the war in Iraq created a major diplomatic crisis among European countries. Considering various clues which have steadily emerged, this paper refutes the relevance of the debate about weapons of mass destruction and analyses the real motivations for these distinct positions through Europe: the role of the US in the transatlantic relationship, expectations towards the EU and the weight of public opinion. Then, it examines how these intrinsic divergences of political views and interests explain the difficulties encountered in implementing the European Security and Defence Policy and concludes on the keys issues which need to be addressed.

• Asian Journal for Public Opinion Research
• /
• v.8 no.4
• /
• pp.453-477
• /
• 2020

This research is a combination of qualitative and quantitative methods. It analyzed reputation factors for the personal branding of journalists in Thailand. Research tools were in-depth interviews and an online questionnaire with 33 variables. Eleven journalists and informed sources were interviewed. A total of 1,262 survey respondents were divided into three groups including 586 recipients, 416 news people, and 260 academics. Data were analyzed using content analysis and factor analysis. It was found that the reputation factors for the personal branding of journalists in Thailand consisted of 1) the professionalism in rich and reliable news reporting, 2) the ability to use communication technology that increases prominence and career opportunities 3) the social responsibility in reporting news events, 4) the key opinion leaders who speak up for people to monitor in the government for peace in society, and 5) the use of experience in developing news reporting capabilities.