• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.39-58
• /
• 2014

As the importance of big data and related technologies continues to grow in the industry, it has become highlighted to visualize results of processing and analyzing big data. Visualization of data delivers people effectiveness and clarity for understanding the result of analyzing. By the way, visualization has a role as the GUI (Graphical User Interface) that supports communications between people and analysis systems. Usually to make development and maintenance easier, these GUI parts should be loosely coupled from the parts of processing and analyzing data. And also to implement a loosely coupled architecture, it is necessary to adopt design patterns such as MVC (Model-View-Controller) which is designed for minimizing coupling between UI part and data processing part. On the other hand, big data can be classified as structured data and unstructured data. The visualization of structured data is relatively easy to unstructured data. For all that, as it has been spread out that the people utilize and analyze unstructured data, they usually develop the visualization system only for each project to overcome the limitation traditional visualization system for structured data. Furthermore, for text data which covers a huge part of unstructured data, visualization of data is more difficult. It results from the complexity of technology for analyzing text data as like linguistic analysis, text mining, social network analysis, and so on. And also those technologies are not standardized. This situation makes it more difficult to reuse the visualization system of a project to other projects. We assume that the reason is lack of commonality design of visualization system considering to expanse it to other system. In our research, we suggest a common information model for visualizing text data and propose a comprehensive and reusable framework, TexVizu, for visualizing text data. At first, we survey representative researches in text visualization era. And also we identify common elements for text visualization and common patterns among various cases of its. And then we review and analyze elements and patterns with three different viewpoints as structural viewpoint, interactive viewpoint, and semantic viewpoint. And then we design an integrated model of text data which represent elements for visualization. The structural viewpoint is for identifying structural element from various text documents as like title, author, body, and so on. The interactive viewpoint is for identifying the types of relations and interactions between text documents as like post, comment, reply and so on. The semantic viewpoint is for identifying semantic elements which extracted from analyzing text data linguistically and are represented as tags for classifying types of entity as like people, place or location, time, event and so on. After then we extract and choose common requirements for visualizing text data. The requirements are categorized as four types which are structure information, content information, relation information, trend information. Each type of requirements comprised with required visualization techniques, data and goal (what to know). These requirements are common and key requirement for design a framework which keep that a visualization system are loosely coupled from data processing or analyzing system. Finally we designed a common text visualization framework, TexVizu which is reusable and expansible for various visualization projects by collaborating with various Text Data Loader and Analytical Text Data Visualizer via common interfaces as like ITextDataLoader and IATDProvider. And also TexVisu is comprised with Analytical Text Data Model, Analytical Text Data Storage and Analytical Text Data Controller. In this framework, external components are the specifications of required interfaces for collaborating with this framework. As an experiment, we also adopt this framework into two text visualization systems as like a social opinion mining system and an online news analysis system.

• Korean Journal of Cognitive Science
• /
• v.13 no.3
• /
• pp.33-46
• /
• 2002

Recently, unstructured random data such as website logs, texts and tables etc, have been flooding in the internet. Among these unstructured data there are potentially very useful data such as bulletin boards and e-mails that are used for customer services and the output from search engines. Various text mining tools have been introduced to deal with those data. But most of them lack accuracy compared to traditional data mining tools that deal with structured data. Hence, it has been sought to find a way to apply data mining techniques to these text data. In this paper, we propose a text mining system which can incooperate existing data mining methods. We use text mining as a preprocessing tool to generate formatted data to be used as input to the data mining system. The output of the data mining system is used as feedback data to the text mining to guide further categorization. This feedback cycle can enhance the performance of the text mining in terms of accuracy. We apply this method to categorize web sites containing adult contents as well as illegal contents. The result shows improvements in categorization performance for previously ambiguous data.

• Journal of Computing Science and Engineering
• /
• v.5 no.2
• /
• pp.150-160
• /
• 2011

Automatic text classification has a long history and many studies have been conducted in this field. In particular, many machine learning algorithms and information retrieval techniques have been applied to text classification tasks. Even though much technical progress has been made in text classification, there is still room for improvement in text classification. In this paper, we will discuss remaining issues in improving text classification. In this paper, three improvement issues are presented including automatic training data generation, noisy data treatment and term weighting and indexing, and four actual studies and their empirical results for those issues are introduced. First, the semi-supervised learning technique is applied to text classification to efficiently create training data. For effective noisy data treatment, a noisy data reduction method and a robust text classifier from noisy data are developed as a solution. Finally, the term weighting and indexing technique is revised by reflecting the importance of sentences into term weight calculation using summarization techniques.

• Korean Journal of Clinical Pharmacy
• /
• v.27 no.4
• /
• pp.221-227
• /
• 2017

Background: As personalized healthcare industry has attracted much attention, big data analysis of healthcare data is essential. Lots of healthcare data such as product labeling, biomedical literature and social media data are unstructured, extracting meaningful information from the unstructured text data are becoming important. In particular, text mining for adverse drug reactions (ADRs) reports is able to provide signal information to predict and detect adverse drug reactions. There has been no study on text analysis of expert opinion on Korea Adverse Event Reporting System (KAERS) databases in Korea. Methods: Expert opinion text of KAERS database provided by Korea Institute of Drug Safety & Risk Management (KIDS-KD) are analyzed. To understand the whole text, word frequency analysis are performed, and to look for important keywords from the text TF-IDF weight analysis are performed. Also, related keywords with the important keywords are presented by calculating correlation coefficient. Results: Among total 90,522 reports, 120 insulin ADR report and 858 tramadol ADR report were analyzed. The ADRs such as dizziness, headache, vomiting, dyspepsia, and shock were ranked in order in the insulin data, while the ADR symptoms such as vomiting, 어지러움, dizziness, dyspepsia and constipation were ranked in order in the tramadol data as the most frequently used keywords. Conclusion: Using text mining of the expert opinion in KIDS-KD, frequently mentioned ADRs and medications are easily recovered. Text mining in ADRs research is able to play an important role in detecting signal information and prediction of ADRs.

• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.418-434
• /
• 2018

With the increasing use of the Internet and electronic documents, automatic text categorization becomes imperative. Several machine learning algorithms have been proposed for text categorization. The k-nearest neighbor algorithm (kNN) is known to be one of the best state of the art classifiers when used for text categorization. However, kNN suffers from limitations such as high computation when classifying new instances. Instance selection techniques have emerged as highly competitive methods to improve kNN through data reduction. However previous works have evaluated those approaches only on structured datasets. In addition, their performance has not been examined over the text categorization domain where the dimensionality and size of the dataset is very high. Motivated by these observations, this paper investigates and analyzes the impact of instance selection on kNN-based text categorization in terms of various aspects such as classification accuracy, classification efficiency, and data reduction.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.3
• /
• pp.112-121
• /
• 2020

Recently, as the internet usage is increasing, accordingly generated text data is also increasing. Because this text data on the internet includes users' comments, the text data on the Internet can help you get users' opinion more efficiently and effectively. The topic of text mining has been actively studied recently, but it primarily focuses on either the content analysis or various improving techniques mostly for the performance of target mining algorithms. The objective of this study is to propose a novel method of analyzing the user's requirements by utilizing the text-mining technique. To complement the existing survey techniques, this study seeks to present priorities together with efficient extraction of customer requirements from the text data. This study seeks to identify users' requirements, derive the priorities of requirements, and identify the detailed causes of high-priority requirements. The implications of this study are as follows. First, this study tried to overcome the limitations of traditional investigations such as surveys and VOCs through text mining of online text data. Second, decision makers can derive users' requirements and prioritize without having to analyze numerous text data manually. Third, user priorities can be derived on a quantitative basis.

• Journal of Korea Multimedia Society
• /
• v.23 no.9
• /
• pp.1181-1190
• /
• 2020

Detection of an anomaly pattern deviating normal data distribution in streaming data is an important technique in many application areas. In this paper, a method for detection of an newly emerging pattern in text streaming data which is an ordered sequence of texts is proposed based on text embedding and anomaly pattern detection. Using text embedding methods such as BOW(Bag Of Words), Word2Vec, and BERT, the detection performance of the proposed method is compared. Experimental results show that anomaly pattern detection using BERT embedding gave an average F1 value of 0.85 and the F1 value of 1 in three cases among five test cases.

• Journal of Information Technology Applications and Management
• /
• v.26 no.3
• /
• pp.43-59
• /
• 2019

The goal of this paper is to investigate changes in North Korea's domestic and foreign policies through automated text analysis over North Korean new year addresses, one of most important and authoritative document publicly announced by North Korean government. Based on that data, we then analyze the status of text mining research, using a text mining technique to find the topics, methods, and trends of text mining research. We also investigate the characteristics and method of analysis of the text mining techniques, confirmed by analysis of the data. We propose a procedure to find meaningful tendencies based on a combination of text mining, cluster analysis, and co-occurrence networks. To demonstrate applicability and effectiveness of the proposed procedure, we analyzed the inaugural addresses of Kim Jung Un of the North Korea from 2017 to 2019. The main results of this study show that trends in the North Korean national policy agenda can be discovered based on clustering and visualization algorithms. We found that uncovered semantic structures of North Korean new year addresses closely follow major changes in North Korean government's positions toward their own people as well as outside audience such as USA and South Korea.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.113-124
• /
• 2015

Unlike structured data which are gathered and saved in a predefined structure, unstructured text data which are mostly written in natural language have larger applications recently due to the emergence of web 2.0. Text mining is one of the most important big data analysis techniques that extracts meaningful information in the text because it has not only increased in the amount of text data but also human being's emotion is expressed directly. In this study, we used R program, an open source software for statistical analysis, and studied algorithm implementation to conduct analyses (such as Frequency Analysis, Cluster Analysis, Word Cloud, Social Network Analysis). Especially, to focus on our research scope, we used keyword extract method based on a Data Dictionary. By applying in real cases, we could find that R is very useful as a statistical analysis software working on variety of OS and with other languages interface.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.1085-1089
• /
• 2015

Text-mining technique in the past had difficulty in realizing the analysis algorithm due to text complexity and degree of freedom that variables in the text have. Although the algorithm demanded lots of effort to get meaningful result, mechanical text analysis took more time than human text analysis. However, along with the development of hardware and analysis algorithm, big data technology has appeared. Thanks to big data technology, all the previously mentioned problems have been solved while analysis through text-mining is recognized to be valuable as well. However, applying text-mining to Korean text is still at the initial stage due to the linguistic domain characteristics that the Korean language has. If not only the data searching but also the analysis through text-mining is possible, saving the cost of human and material resources required for text analysis will lead efficient resource utilization in numerous public work fields. Thus, in this paper, we compare and evaluate the public document classification by handwork to public document classification where word frequency(TF-IDF) in a text-mining-based text and Cosine similarity between each document have been utilized in big data environment.