• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.655-665
• /
• 2018

Social network services (SNS) have become the most common tool for the communication of public and private opinions as well as public issues; consequently, one may form or drive public opinions to advocate by spreading positive content using SNS. Controversy for survey data based opinion poll accuracy continues in relation to response rate or sampling methodology. This study suggests complementary measures that additionally consider the sentiment analysis results of unstructured data on a social network by data crawling and sentiment dictionary adjustment process. The suggested method shows the improvement of prediction accuracy by decreasing error rates.

• Journal of Korean Society for Quality Management
• /
• v.48 no.3
• /
• pp.421-431
• /
• 2020

Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

• Journal of Korean Institute of Industrial Engineers
• /
• v.43 no.1
• /
• pp.62-71
• /
• 2017

In order to attract foreign tourists, it is important to understand what factors on domestic tour spots are critically considered and how they are evaluated after visit. However, most of the researches on tour business have collected information from tourists through survey on a small number of tourists, which leads to inaccurate and biased conclusion. In this paper, we suggest a data-driven methodology to figure out tourists' satisfaction factors and estimate sentiment scores on them. To do so, we collected review comments data from popular web site. Latent dirichlet allocation is employed to extract key factors and elastic net is used to estimate sentiment scores. Then, an aggregated evaluation score is generated by combining the factors and the sentiment scores per topics. Our proposed method can be used to recommend travel schedules with themes and discover new spots.

• Journal of Distribution Science
• /
• v.16 no.9
• /
• pp.5-11
• /
• 2018

Purpose - In recent, Japanese retailers have expanded their business into Korea, although Korean customers have anti-Japan sentiment in their mind, It is, thus, necessary to investigate how Korean customers react to Japanese retailers, when selecting a shopping place. Research design, data, and methodology - The authors have developed a research model with five hypotheses, based on the literature review process, and used confirmative factor analysis(CFA) as well as a structural equation model(SEM) as a research technique, in order to verify hypotheses. Results - All of hypotheses are accepted. Anti-Japan sentiment significantly influences consumer ethnocentrism and animosity. Interestingly, consumer ethnocentricity affects the formation process of animosity. Rather than ethnocentrism, animosity relatively influences customer attitudes towards Japanese retailers, when Korean customers choose a retailer. Conclusions - The authors found that anti-Japan sentiment has significantly affected Korean customer attitudes. In order for Japanese retailers to increase their market shares in the Korean market, they have to make a significant effort to alleviate the degree of anti-Japan sentiment, together with Japanese government. In contrast with research findings, Japanese retailers have done their business very well in Korea. Considering that Japanese retailers target younger customers in Korea, demographic elements should be involved in the future research.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.117-126
• /
• 2013

Recently, as Social Network Services(SNS), such as Twitter, Facebook, are becoming more popular, much research has been doing on opinion mining. However, current related researches are mostly focused on sentiment classification or feature selection, but there were few studies about opinion document retrieval. In this paper, we propose a new retrieval method of short opinion documents. Proposed method utilizes previous sentiment classification methodology, and applies several features of documents for evaluating the quality of the opinion documents. For generating the retrieval model, we adopt Learning-to-rank technique and integrate sentiment classification model to Learning-to-rank. Experimental results show that proposed method can be applied successfully in opinion search.

• Journal of Korean Critical Care Nursing
• /
• v.11 no.1
• /
• pp.1-14
• /
• 2018

Purpose : As the intensive care unit (ICU) survival rate increases, interest in the lives of ICU survivors has also been increasing. The purpose of this study was to identify the sentiment of ICU survivors. Method : The author analyzed the quotations from previous qualitative studies related to ICU survivors; a total of 1,074 sentences comprising 429 quotations from 25 relevant studies were analyzed. A word cloud created in the R program was utilized to identify the most frequent adjectives used, and sentiment and emotional scores were calculated using the Artificial Intelligence (AI) program. Results : The 10 adjectives that appeared the most in the quotations were 'difficult', 'different', 'normal', 'able', 'hard', 'bad', 'ill', 'better', 'weak', and 'afraid', in order of decreasing occurrence. The mean sentiment score was negative ($-.31{\pm}.23$), and the three emotions with the highest score were 'sadness'($.52{\pm}.13$), 'joy'($.35{\pm}.22$), and 'fear'($.30{\pm}.25$). Conclusion : The natural language processing of AI used in this study is a relatively new method. As such, it is necessary to refine the methodology through repeated research in various nursing fields. In addition, further studies on nursing interventions that improve the coherency of ICU memory of survivors and familial support for the ICU survivors are needed.

• The Journal of Bigdata
• /
• v.3 no.1
• /
• pp.13-20
• /
• 2018

Stock market prediction has been long dream for researchers as well as the public. Forecasting ever-changing stock market, though, proved a Herculean task. This study proposes a novel stock market sentiment lexicon acquisition system that can predict the growth (or decline) of stock market index, based on economic news. For this purpose, we have collected 3-year's economic news from January 2015 to December 2017 and adopted Word2Vec model to consider the context of words. To evaluate the result, we performed sentiment analysis to collected news data with the automated constructed lexicon and compared with closings of the KOSPI (Korea Composite Stock Price Index), the South Korean stock market index based on economic news.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.731-738
• /
• 2013

We analyze public opinion via a sentiment analysis of tweets collected by using recent topic keywords extracted from newspaper articles. Newspaper articles collected within a certain period of time are clustered by using K-means algorithm and topic keywords for each cluster are extracted by using term frequency. A sentiment analyzer learned by a machine learning method can classify tweets according to their polarity values. We have an assumption that tweets collected by using these topic keywords deal with the same topics as the newspaper articles mentioned if the tweets and the newspapers are generated around the same time. and we tried to verify the validity of this assumption.

• Journal of Korea Trade
• /
• v.24 no.6
• /
• pp.61-81
• /
• 2020

Purpose - This paper examines how the consumer animosity of partner country influences the purchase of foreign products. We analyzed news sentiment to determine whether Chinese consumer's animosity affect the purchase of the products made in Korea around the time when the U.S. Terminal High Altitude Area Defense missile system was deployed in South Korea. Design/methodology - To measure the tone of Chinese consumer animosity more carefully, we utilized a text mining technique of the Chinese language to read the public's opinion. Using Chinese news paper's editorials of 2015.1-2018.10, we analyzed the sentiment toward Korea and regressed it with Korean export to China. Findings - Empirical results report that Chinese consumers tended to reduce their purchase of consumer goods from Korea when the animosity increased, that is, the sentiments of Chinese news editorials were negative. In contrast, the animosity did not affect the purchase of Korean intermediates or raw materials. We further analyzed the effect by dividing the animosity into three categories; politics, economics, and culture. Among these groups, political news exhibits a unique effect on Chinese purchase on consumer goods from Korea. Originality/value - Existing literature on animosity models has measured the animosity by collecting the consumers' opinions through survey at a given time point, whereas it is measured by analyzing the tone of the press release by sentiment analysis during the time period around the event occurrence in this study.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.187-200
• /
• 2019

Bankruptcy prediction model is an issue that has consistently interested in various fields. Recently, as technology for dealing with unstructured data has been developed, researches applied to business model prediction through text mining have been activated, and studies using this method are also increasing in bankruptcy prediction. Especially, it is actively trying to improve bankruptcy prediction by analyzing news data dealing with the external environment of the corporation. However, there has been a lack of study on which news is effective in bankruptcy prediction in real-time mass-produced news. The purpose of this study was to evaluate the high impact news on bankruptcy prediction. Therefore, we classify news according to type, collection period, and analyzed the impact on bankruptcy prediction based on sentiment analysis. As a result, artificial neural network was most effective among the algorithms used, and commentary news type was most effective in bankruptcy prediction. Column and straight type news were also significant, but photo type news was not significant. In the news by collection period, news for 4 months before the bankruptcy was most effective in bankruptcy prediction. In this study, we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.