• Journal of Digital Convergence
• /
• v.19 no.9
• /
• pp.9-18
• /
• 2021

Constructing the Metropolitan Railway Express (the GTX) may have an impact on consumer confidence and housing sales price located near the planned route. This study looked at how consumers' psychology and housing prices change as the large-scale transport infrastructure plane was planned. Also, it looked at the relationship between consumer sentiment and housing prices to analyze the impact of new transportation facilities inflows. Using a correlation analysis, the relationship between the consumer sentiment index and the actual transaction price of apartments was identified. The impact of GTX on the consumer sentiment index and the actual transaction price of apartments was looked at using the Difference-in-Differences methodology. Our finding shows that the construction plan of a large-scale transportation infrastructure in the metropolitan area affects the sentiment of housing consumption and actual transactions. In a situation where the government is speeding up the construction of a wide-area transportation network such as GTX with the goal of becoming a city where people can commute to downtown Seoul within 30 minutes, policies that can stabilize the housing market in transportation hubs should be suggested.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.559-568
• /
• 2014

Previous polarity classification using sentiment analysis utilizes a sentence rule by product reviews based rating points. It is difficult to be applied to blogs which have not rating of product reviews and is possible to fabricate product reviews by comment part-timers and managers who use web site so it is not easy to understand a product and store reviews which are reliability. Considering to these problems, if we analyze blogs which have personal and frank opinions and classify polarity, it is possible to understand rightly opinions for the product, store. This paper suggests that we extract high frequency vocabularies in blogs by several domains and choose topic words. Then we apply a technique of sentiment analysis and classify polarity about contents of blogs. To evaluate performances of sentiment analysis, we utilize the measurement index that use Precision, Recall, F-Score in an information retrieval field. In a result of evaluation, using suggested sentiment analysis is the better performances to classify polarity than previous techniques of using the sentence rule based product reviews.

• Journal of Families and Better Life
• /
• v.34 no.3
• /
• pp.15-26
• /
• 2016

Food is a kind of unconditional element for the health and survival of humanity. Eating is the most principle desire for humans among others, which can make humans feel stability and pleasure when the desire is well satisfied. The attention to food safety is increasing and food safety accidents are happening constantly, which makes the anxiety to food safety become more serious. Especially after the WTO, the floating of food hazards between countries are increasing, which makes the problems of food safety not just limited to inland but has become a matter of common interest internationally in this liberalization era. Therefore, institutional preparation and persistent management and supervision are necessary for increasing dietary life satisfaction as well as securing food safety. Meanwhile, the consumers also need to understand and trust the food safety information, and have the ability of personally pursuing a safe diet. In this study, sentiment index about food safety and dietary satisfaction were centered on Korean consumers and the factors having an effect on dietary satisfaction were analyzed. Moreover, whether the reliance to food safety information had a moderating effect on the sensory level of food safety and satisfaction to dietary food was also confirmed. The main results were different with those concluded by J. Yun and S. Joo (2014). The sensory level of food safety was decided by the reliance to food production distribution provision safety, anxiety to food varieties, and food token. The reliance to food production distribution provision safety was lower than the average level. The anxiety to food varieties was slightly higher than the average level. The reliance to food safety information was generally lower than the medium level which showed the distrust to food safety information. The satisfaction of diet by the consumers showed a slightly lower level than the average level. In addition, the reliance to food safety information had a moderating effect on the sentiment index about food safety and dietary satisfaction. Therefore, the consumer organizations or the government should actively expand various consumer education related to food safety in order to apprehend the concrete variables which can have effects on the satisfaction of diet and transform the precise information into accurate knowledge.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.585-592
• /
• 2017

As development of personal devices have made everyday use of internet much easier than before, it is getting generalized to find information and share it through the social media. In particular, communities specialized in each field have become so powerful that they can significantly influence our society. Finally, businesses and governments pay attentions to reflecting their opinions in their strategies. The stock market fluctuates with various factors of society. In order to consider social trends, many studies have tried making use of bigdata analysis on stock market researches as well as traditional approaches using buzz amount. In the example at the top, the studies using text data such as newspaper articles are being published. In this paper, we analyzed the post of 'Paxnet', a securities specialists' site, to supplement the limitation of the news. Based on this, we help researchers analyze the sentiment of investors by generating a domain-specific sentiment lexicon for the stock market.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.863-876
• /
• 2022

Purpose: The purpose of this study is to propose the product quality satisfaction index based on multiple linear regression using customer reviews. Methods: The proposed framework is composed of four steps. First, we collect online reviews and divide it into insight phrases. The insight phrases are classified using product attribute dictionary and sentiment analysis is conducted. Second, the importance of attributes is calculated in consideration of both regression coefficient and frequency. Third, the positive rate is calculated concerning sentiment analysis result. Therefore, the quality satisfaction index is measured by the weighted sum of importance and positive rate in the last step. Results: We conduct a case study using 2-years(2020, 2021) of Samsung TV reviews to confirm the effectiveness of the proposed methodology. As a result, we found that Picture quality is the most crucial attribute in TV evaluation. The importance of Gaming and content has grown up as the positive rate has also increased. Therefore, the overall satisfaction of TV has increased in 2021 compared to 2020. Conclusion: The result of this study shows that the proposed index reveals the customer's mind efficiently and can be explained by the importance and positive rate of each attribute. By using the proposed index, companies are able to improve and the priority of improvement can be determined.

• The Pure and Applied Mathematics
• /
• v.24 no.4
• /
• pp.227-241
• /
• 2017

The study investigates the stock market using emotion index calculated from SMD based on investors' emotion. In the VAR anlaysis, we find that the correlation between the KOSPI200 return and emotion score sum is highest in 2- or 3- day lag. This study concludes that explanatory power of the SMD emotion index is limited in explaining the Korean stock market yet.

• Proceedings of the Safety Management and Science Conference
• /
• 2009.04a
• /
• pp.109-121
• /
• 2009

In these OECD countries, left-wingers Government focus on unemployment, but right -wingers Government cares more about inflation. It is that inflation and unemployment don't have differential effects across rich and poor and the happiness levels of these two groups are unaffected by identity of the Government in power. The poor people choose to left-wingers Government, but rich people prefer to right -wingers Government. I estimate whether above opinion is correct or not. Especially I check how my results change when I control for aggregate economy activity and government consumption, two variables that could be correlated with inflation and unemployment and affect each Government's happiness differentially. This paper, and I believe much of the happiness literature, can be understood as an application of experienced utility, a conception that emphasis the pleasures derived from private consumption and sentiment of it. In Granger Causality test, private consumption sentiment index related with industrial production interactively in Korea. The business cycles affect on private consumption sentiment index.

• Convergence Security Journal
• /
• v.18 no.1
• /
• pp.103-110
• /
• 2018

Modern society is increasingly demanding in many areas of big data processing technology to collect, aggregate, and analyze large amounts of data over the Internet and SNS. A typical application is to evaluate the reputation of a company or college. To measure and quantify a reputation, fair and precise data and efficient data processing are very important. For this purpose, a quantitative quotient was obtained using public data, a qualitative quotient was obtained through sentiment analysis using news articles, and a complex college reputation quotient was calculated. In this paper, a complex college reputation quotient was calculated based on the quantitative index, reflecting the sentimental reputation, and based on the proposed mixed university system. In this paper, the Complex College Reputation System(CCRS) was proposed, which produced the Complex College Reputation Quotient with an objective quantitative quotient and qualitative quotient reflecting the sentimental reputation to measure the college reputation.

• Fashion & Textile Research Journal
• /
• v.22 no.1
• /
• pp.38-54
• /
• 2020

This study examines the time causal relationship between the operation profit of the listed fashion companies and the macro variables. Operating profit data of 36 listed fashion companies from 2000 to 2017 has been used. Macro variables include household income, household expenditure, number of Korean overseas travelers, number of foreigner travelers and sentiment index. The study results are as follows. First, the number of outbound travelers from Korea has a negative effect on the operating profit of listed fashion companies; however the number of foreigner visiting Korea has a positive effect at 0 time lag. Second, the consumer sentiment index had a positive effect on the sales and the operating profits of the listed fashion companies with a time difference between the 3rd and the 4th quarter. Third, a disposable income has a positive effect on the operating profit of listed fashion companies. Last, educational expenses have a negative effect on operating profit with a time lag between the first and the second quarter. The findings can be used as useful information to analyze the fashion industry and help fashion companies improve their financial performances.