• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• 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 the Korean association of regional geographers
• /
• v.2 no.2
• /
• pp.75-92
• /
• 1996

Geography education is one of the best ways to improve the understanding of other countries. By analyzing Korean and Japanese textbooks on world geography, I tried to find out how well they explain the other country and to set forth guiding principles for geography education. To achieve these aims, weight analysis are used. The major findings in this study can be summarised as follow. The contents of Korean and Japanese geography textbooks were analyzed deviding into 2 major topics, 6 minor topics, and 20 key concepts. (1) By analyzing Korean geography textbook of the 5th curriculum the weight percentages which had been given to each minor topics were found. They are as follow: resource problem(57.7%), human right problem(21.4%), population problem (9.0%), mutual dependence(6.0%), environmental problem(3.3%), international competition(2.6%). (2) By analyzing Korean geography text-book of the 6th curriculum the weight percentages which had been give to each minor topics were found. They are as follow: resource problem(42.7%), human right problem(21.7%), mutual dependence (20.9%), environmental problem(7.7%), population problem(4.6%), international competition(2.4%) (3) By analyzing Japanise geography text-book of 5th curriculum ammendment the weight percentages which had been give to each minor topics were found. They are as follows: resource problem(49.9%) human right problem(21.7%), mutual dependence(15.5%), population problem (7.1%), international competition(6.2%), environmental problem(3.8%) (4) By analyzing Japanise geography textbook of 6th curriculum ammendment the weight percentages which had been give to each minor topics were found. They are as follows human right problem (31.6%), mutual dependence(22.8%), resource problem(20.7%), population problem(12.7%), environmental problem(8.6%), international competition(3.6%). We can see that in the field of dependence Korea and Japan put the similar weight but in the field of common problem they put the fairly different weight. It can be viewed as the difference of curriculum. That is to say Korea used both the systematic method on the basis of unit but Japan used only topical method on the basis of unit. Therefore Korean geography textbook introduce agriculture, forestry, fishery, mining industry and manufacturing industry. Japanese textbook, however gives a detailed account about residents' lives in specific area. For that reason in Korean textbook, resource was stressed, while in Japanese textbook, culture was stressed.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.11
• /
• pp.5227-5237
• /
• 2011

Technology roadmap is a powerful tool that considers relationships of technology, product and market and referred as a supporting technology strategy and planning. There are numerous studies that have attempted to develop technology roadmap and case studies on specific technology areas. However, a number of studies have been dependant on brainstorming and discussion of expert group, delphi technique as qualitative analysis rather than systemic and quantitative analysis. To overcome the limitation, patent analysis considered as quite quantitative analysis is employed in this paper. Therefore, this paper proposes new technology roadmapping based on patent citation network considering technology life cycle and suggests planning for undeveloped technology but considered as promising. At first, patent data and citation information are collected and patent citation network is developed on the basis of collected patent information. Secondly, we investigate a stage of technology in the life cycle by considering patent application year and the technology life cycle, and duration of technology development is estimated. In addition, subsequent technologies are grouped as nodes of a super-level technology to show the evolution of the technology for the period. Finally, a technology roadmap is drawn by linking these technology nodes in a technology layer and estimating the duration of development time. Based on technology roadmap, technology planning is conducted to identify undeveloped technology through text mining and this paper suggests characteristics of technology that needs to be developed in the future. In order to illustrate the process of the proposed approach, technology for hydrogen storage is selected in this paper.

• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.49-58
• /
• 2019

In the era of the 4th industrial revolution, the development of information technology brought various benefits, but it also increased social interest in privacy issues. As the possibility of personal privacy violation by big data increases, academic discussion about privacy management has begun to be active. While the traditional view of privacy has been defined at various levels as the basic human rights, most of the recent research trends are mainly concerned only with the information privacy of online privacy protection. This limited discussion can distort the theoretical concept and the actual perception, making the academic and social consensus of the concept of privacy more difficult. In this study, we analyze the privacy concept that is exposed on the internet based on 12,000 news data of the portal site for the past one year and compare the difference between the theoretical concept and the socially accepted concept. This empirical approach is expected to provide an understanding of the changing concept of privacy and a research direction for the conceptualization of privacy for current situations.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.33-42
• /
• 2021

As smartphone-based tourism platforms have become active, policy establishment and service enhancement using review data are being made in various fields. In the case of the preceding studies using tourism review data, most of the studies centered on domestic tourists were conducted, and in the case of foreign tourist studies, studies were conducted only on data collected in some languages and text mining techniques. In this study, 3,515 review data written by foreigners were collected by designating the "Daegu attractions" keyword through the online review site. And LDA-based topic modeling was performed to derive tourism topics. The spatial approach through global and local spatial autocorrelation analysis for each topic can be said to be different from previous studies. As a result of the analysis, it was confirmed that there is a global spatial autocorrelation, and that tourist destinations mainly visited by foreigners are concentrated locally. In addition, hot spots have been drawn around Jung-gu in most of the topics. Based on the analysis results, it is expected to be used as a basic research for spatial analysis based on local government foreign tourism policy establishment and topic modeling. And The limitations of this study were also presented.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.1-28
• /
• 2021

FinTech has been discussed as an important business area towards technology-driven financial innovation. The term fintech is a combination of finance and technology, which means ICT technology currently associated with all finance areas. The popularity of the fintech industry has significantly increased over time, with full investment and support for numerous startups. Therefore, both academia and practice tried to analyze the trend of the fintech area. Despite the fact, however, previous research has limitations in terms of collecting relevant databases for fintech and identifying proper application areas. In response, this study proposed a new method for analyzing the trend of Fintech fields by expanding Fintech's terminology and using network analysis and topic modeling. A new Fintech terminology list was created and a total of 18,341 patents were collected from USPTO for 10 years. The co-classification analysis and network analysis was conducted to identify the technological trends of patent classification. In addition, topic modeling was conducted to identify the trends of fintech in order to analyze the contents of fintech. This study is expected to help both managers and investors who want to be involved in technology-driven financial services seize new FinTech technology opportunities.

• Journal of Korean Society of Rural Planning
• /
• v.30 no.2
• /
• pp.13-24
• /
• 2024

This study conducts an analysis of social media big data pertaining to island tourism resources, aiming to discern the diverse forms and categories of island tourism favored by consumers, ascertain predominant resources, and facilitate objective decision-making grounded in scientific methodologies. To achieve this objective, an examination of blog posts published on Naver from 2022 to 2023 was undertaken, utilizing keywords such as 'Island tourism', 'Island travel', and 'Island backpacking' as focal points for analysis. Text mining techniques were applied to sift through the data. Among the resources identified, the port emerged as a significant asset, serving as a pivotal conduit linking the island and mainland and holding substantial importance as a focal point and resource for tourist access to the island. Furthermore, an analysis of the disparity between existing island tourism resources and those acknowledged by tourists who actively engage with and appreciate island destinations led to the identification of 186 newly emerging resources. These nascent resources predominantly clustered within five regions: Incheon Metropolitan City, Tongyeong/Geoje City, Jeju Island, Ulleung-gun, and Shinan-gun. A scrutiny of these resources, categorized according to the tourism resource classification system, revealed a notable presence of new resources, chiefly in the domains of 'rural landscape', 'tourist resort/training facility', 'transportation facility', and 'natural resource'. Notably, many of these emerging resources were previously overlooked in official management targets or resource inventories pertaining to existing island tourism resources. Noteworthy examples include ports, beaches, and mountains, which, despite constituting a substantial proportion of the newly identified tourist resources, were not accorded prominence in spatial information datasets. This study holds significance in its ability to unearth novel tourism resources recognized by island tourism consumers through a gap analysis approach that juxtaposes the existing status of island tourism resource data with techniques utilizing social media big data. Furthermore, the methodology delineated in this research offers a valuable framework for domestic local governments to gauge local tourism demand and embark on initiatives for tourism development or regional revitalization.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.1-23
• /
• 2013

To discover significant social issues such as unemployment, economy crisis, social welfare etc. that are urgent issues to be solved in a modern society, in the existing approach, researchers usually collect opinions from professional experts and scholars through either online or offline surveys. However, such a method does not seem to be effective from time to time. As usual, due to the problem of expense, a large number of survey replies are seldom gathered. In some cases, it is also hard to find out professional persons dealing with specific social issues. Thus, the sample set is often small and may have some bias. Furthermore, regarding a social issue, several experts may make totally different conclusions because each expert has his subjective point of view and different background. In this case, it is considerably hard to figure out what current social issues are and which social issues are really important. To surmount the shortcomings of the current approach, in this paper, we develop a prototype system that semi-automatically detects social issue keywords representing social issues and problems from about 1.3 million news articles issued by about 10 major domestic presses in Korea from June 2009 until July 2012. Our proposed system consists of (1) collecting and extracting texts from the collected news articles, (2) identifying only news articles related to social issues, (3) analyzing the lexical items of Korean sentences, (4) finding a set of topics regarding social keywords over time based on probabilistic topic modeling, (5) matching relevant paragraphs to a given topic, and (6) visualizing social keywords for easy understanding. In particular, we propose a novel matching algorithm relying on generative models. The goal of our proposed matching algorithm is to best match paragraphs to each topic. Technically, using a topic model such as Latent Dirichlet Allocation (LDA), we can obtain a set of topics, each of which has relevant terms and their probability values. In our problem, given a set of text documents (e.g., news articles), LDA shows a set of topic clusters, and then each topic cluster is labeled by human annotators, where each topic label stands for a social keyword. For example, suppose there is a topic (e.g., Topic1 = {(unemployment, 0.4), (layoff, 0.3), (business, 0.3)}) and then a human annotator labels "Unemployment Problem" on Topic1. In this example, it is non-trivial to understand what happened to the unemployment problem in our society. In other words, taking a look at only social keywords, we have no idea of the detailed events occurring in our society. To tackle this matter, we develop the matching algorithm that computes the probability value of a paragraph given a topic, relying on (i) topic terms and (ii) their probability values. For instance, given a set of text documents, we segment each text document to paragraphs. In the meantime, using LDA, we can extract a set of topics from the text documents. Based on our matching process, each paragraph is assigned to a topic, indicating that the paragraph best matches the topic. Finally, each topic has several best matched paragraphs. Furthermore, assuming there are a topic (e.g., Unemployment Problem) and the best matched paragraph (e.g., Up to 300 workers lost their jobs in XXX company at Seoul). In this case, we can grasp the detailed information of the social keyword such as "300 workers", "unemployment", "XXX company", and "Seoul". In addition, our system visualizes social keywords over time. Therefore, through our matching process and keyword visualization, most researchers will be able to detect social issues easily and quickly. Through this prototype system, we have detected various social issues appearing in our society and also showed effectiveness of our proposed methods according to our experimental results. Note that you can also use our proof-of-concept system in http://dslab.snu.ac.kr/demo.html.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.45-67
• /
• 2016

Given the recent development of smart devices, users are producing, sharing, and acquiring a variety of information via the Internet and social network services (SNSs). Because users tend to use multiple media simultaneously according to their goals and preferences, domestic SNS users use around 2.09 media concurrently on average. Since the information provided by such media is usually textually represented, recent studies have been actively conducting textual analysis in order to understand users more deeply. Earlier studies using textual analysis focused on analyzing a document's contents without substantive consideration of the diverse characteristics of the source medium. However, current studies argue that analytical and interpretive approaches should be applied differently according to the characteristics of a document's source. Documents can be classified into the following types: informative documents for delivering information, expressive documents for expressing emotions and aesthetics, operational documents for inducing the recipient's behavior, and audiovisual media documents for supplementing the above three functions through images and music. Further, documents can be classified according to their contents, which comprise facts, concepts, procedures, principles, rules, stories, opinions, and descriptions. Documents have unique characteristics according to the source media by which they are distributed. In terms of newspapers, only highly trained people tend to write articles for public dissemination. In contrast, with SNSs, various types of users can freely write any message and such messages are distributed in an unpredictable way. Again, in the case of newspapers, each article exists independently and does not tend to have any relation to other articles. However, messages (original tweets) on Twitter, for example, are highly organized and regularly duplicated and repeated through replies and retweets. There have been many studies focusing on the different characteristics between newspapers and SNSs. However, it is difficult to find a study that focuses on the difference between the two media from the perspective of supply and demand. We can regard the articles of newspapers as a kind of information supply, whereas messages on various SNSs represent a demand for information. By investigating traditional newspapers and SNSs from the perspective of supply and demand of information, we can explore and explain the information dilemma more clearly. For example, there may be superfluous issues that are heavily reported in newspaper articles despite the fact that users seldom have much interest in these issues. Such overproduced information is not only a waste of media resources but also makes it difficult to find valuable, in-demand information. Further, some issues that are covered by only a few newspapers may be of high interest to SNS users. To alleviate the deleterious effects of information asymmetries, it is necessary to analyze the supply and demand of each information source and, accordingly, provide information flexibly. Such an approach would allow the value of information to be explored and approximated on the basis of the supply-demand balance. Conceptually, this is very similar to the price of goods or services being determined by the supply-demand relationship. Adopting this concept, media companies could focus on the production of highly in-demand issues that are in short supply. In this study, we selected Internet news sites and Twitter as representative media for investigating information supply and demand, respectively. We present the notion of News Value Index (NVI), which evaluates the value of news information in terms of the magnitude of Twitter messages associated with it. In addition, we visualize the change of information value over time using the NVI. We conducted an analysis using 387,014 news articles and 31,674,795 Twitter messages. The analysis results revealed interesting patterns: most issues show lower NVI than average of the whole issue, whereas a few issues show steadily higher NVI than the average.