• Journal of Information Technology Applications and Management
• /
• v.20 no.3_spc
• /
• pp.231-257
• /
• 2013

The recent rise in the unstructured data generated by social media has resulted in an increasing need to collect, store, search, analyze, and visualize it. These data cannot be managed effectively by using traditional data analysis methodologies because of their vast volume and unstructured nature. Therefore, many attempts are being made to analyze these unstructured data (e.g., text files and log files) by using commercial and noncommercial analytical tools. Especially, the attempt to discover meaningful knowledge by using text mining is being made in business and other areas such as politics, economics, and cultural studies. For instance, several studies have examined pending national issues by analyzing large volumes of texts on various social issues. However, it is difficult to create satisfactory information services that can identify R&D documents on specific national issues from among the various R&D resources. In other words, although users specify some words related to pending national issues as search keywords, they usually fail to retrieve the R&D information they are looking for. This is usually because of the discrepancy between the terms defining pending national issues and the corresponding terms used in R&D documents. We need a mediating logic to overcome this discrep 'ancy so that we can identify and package appropriate R&D information on specific pending national issues. In this paper, we use association analysis and social network analysis to devise a mediator for bridging the gap between the keywords defining pending national issues and those used in R&D documents. Further, we propose a methodology for packaging R&D information services for pending national issues by using the devised mediator. Finally, in order to evaluate the practical applicability of the proposed methodology, we apply it to the NTIS(National Science & Technology Information Service) system, and summarize the results in the case study section.

• Journal of the Korean Society for information Management
• /
• v.31 no.1
• /
• pp.231-250
• /
• 2014

Due to the recent development of Information and Communication Technologies (ICT), the amount of research publications has increased exponentially. In response to this rapid growth, the demand of automated text processing methods has risen to deal with massive amount of text data. Biomedical text mining discovering hidden biological meanings and treatments from biomedical literatures becomes a pivotal methodology and it helps medical disciplines reduce the time and cost. Many researchers have conducted literature-based discovery studies to generate new hypotheses. However, existing approaches either require intensive manual process of during the procedures or a semi-automatic procedure to find and select biomedical entities. In addition, they had limitations of showing one dimension that is, the cause-and-effect relationship between two concepts. Thus;this study proposed a novel approach to discover various relationships among source and target concepts and their intermediate concepts by expanding intermediate concepts to multi-levels. This study provided distinct perspectives for literature-based discovery by not only discovering the meaningful relationship among concepts in biomedical literature through graph-based path interference but also being able to generate feasible new hypotheses.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.11
• /
• pp.2866-2879
• /
• 2012

Among the various security threats in online games, the use of game bots is the most serious problem. Previous studies on game bot detection have proposed many methods to find out discriminable behaviors of bots from humans based on the fact that a bot's playing pattern is different from that of a human. In this paper, we look at the chatting data that reflects gamers' communication patterns and propose a communication pattern analysis framework for online game bot detection. In massive multi-user online role playing games (MMORPGs), game bots use chatting message in a different way from normal users. We derive four features; a network feature, a descriptive feature, a diversity feature and a text feature. To measure the diversity of communication patterns, we propose lightly summarized indices, which are computationally inexpensive and intuitive. For text features, we derive lexical, syntactic and semantic features from chatting contents using text mining techniques. To build the learning model for game bot detection, we test and compare three classification models: the random forest, logistic regression and lazy learning. We apply the proposed framework to AION operated by NCsoft, a leading online game company in Korea. As a result of our experiments, we found that the random forest outperforms the logistic regression and lazy learning. The model that employs the entire feature sets gives the highest performance with a precision value of 0.893 and a recall value of 0.965.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.19 no.1
• /
• pp.25-35
• /
• 2020

Since the introduction and operation of BF certification, a total of 6,432 certificates has been issued until February 2020, of which educational research facilities make 1,091 cases (754 preliminary certification, 337 main certification) out of 6,237 buildings, acquiring BF certification of about 20%. Qualitative evaluation is conducted with focus on the three items of BF-certified building evaluation index, which are medium facilities, internal facilities, and sanitary facilities, and major keywords are the deducted through the Text Mining analysis of the derived results. As a result, problems with access paths occurred in the case of the facilities, and assessment indicators for users were found to be necessary among the assessment of the steps of the internal facilities. Finally, we could see that sanitation facilities needed to improve toilets installed in residential development facilities. Based on the results obtained, the study seeks to suggest directions for improving the evaluation index required for BF-certified school facilities.

• Journal of Internet Computing and Services
• /
• v.13 no.5
• /
• pp.33-43
• /
• 2012

Semantic web is utilized to construct advanced information service by using semantic relationships between entities. Text mining can be applied to generate semantic relationships from unstructured data resources. In this study, ontology schema guideline, ontology instance generation, disambiguation of same name by text mining and advanced historical people finding service by reasoning have been proposed. Various relationships between historical event, organization, people, which are created by domain experts, are linked to literatures of National Institute of Korean History (NIKH). It improves the effectiveness of user access and proposes advanced people finding service based on relationships. In order to distinguish between people with the same name, we compares the structure and edge, nodes of personal social network. To provide additional information, external resources including thesaurus and web are linked to all of internal related resources as well.

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.575-588
• /
• 2012

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

• The Journal of Korean Association of Computer Education
• /
• v.22 no.3
• /
• pp.67-78
• /
• 2019

The purpose of this study is to explore information ethics issues based on academic big data from Web of Science (WoS) and to provide implications for information ethics education in informatics subject. To this end, 318 published papers from WoS related to information ethics were text mined. Specifically, this paper analyzed the frequency of key-words(TF, DF, TF-IDF), information ethics issues using topic modeling, and frequency of appearances by year for each issue. This paper used 'tm', 'topicmodel' package of R for text mining. The main results are as follows. First, this paper confirmed that the words 'digital', 'student', 'software', and 'privacy' were the main key-words through TF-IDF. Second, the topic modeling analysis showed 8 issues such as 'Professional value', 'Cyber-bullying', 'AI and Social Impact' et al., and the proportion of 'Professional value' and 'Cyber-bullying' was relatively high. This study discussed the implications for information ethics education in Korea based on the results of this analysis.

• Journal of Korea Game Society
• /
• v.18 no.6
• /
• pp.69-82
• /
• 2018

The need of high quality VR contents has been steadily raised in recent years. Therefore, this study investigated the user's interest factors of VR game which is receiving the most attention among VR contents. We used STEAM review data and applied Text mining and Network analysis to perform this research. As a result, it was possible to confirm 4 word clusters related VR game users. Each cluster is named by 'presence', 'first person view game', 'auditory factor' and 'interaction'. This study has its meaning. First, user related research would be very helpful to develop high quality VR game. Second, it confirms that review data of VR game users can be structured, analyzed and used.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.1-10
• /
• 2019

Since big-data text mining extracts many features and data, clustering and classification can result in high computational complexity and low reliability of the analysis results. In particular, a term document matrix obtained through text mining represents term-document features, but produces a sparse matrix. We designed an advanced genetic algorithm (GA) to extract features in text mining for detection model. Term frequency inverse document frequency (TF-IDF) is used to reflect the document-term relationships in feature extraction. Through a repetitive process, a predetermined number of features are selected. And, we used the sparsity score to improve the performance of detection model. If a spam mail data set has the high sparsity, detection model have low performance and is difficult to search the optimization detection model. In addition, we find a low sparsity model that have also high TF-IDF score by using s(F) where the numerator in fitness function. We also verified its performance by applying the proposed algorithm to text classification. As a result, we have found that our algorithm shows higher performance (speed and accuracy) in attack mail classification.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.4
• /
• pp.817-824
• /
• 2003

We employed a hierarchical document classification method to classify a massive collection of electronic medical records(EMR) written in both Korean and English. Our experimental system has been learned from 5,000 records of EMR text data and predicted a newly given set of EMR text data over 68% correctly. We expect the accuracy rate can be improved greatly provided a dictionary of medical terms or a suitable medical thesaurus. The classification system might play a key role in some clinical decision support systems and various interpretation systems for clinical data.