• The KIPS Transactions:PartB
• /
• v.12B no.7 s.103
• /
• pp.811-822
• /
• 2005

Automated text categorization is to classify free text documents into predefined categories automatically and whose main goals is to reduce considerable manual process required to the task. The researches to improving the text categorization performance(efficiency) in recent years, focused on enhancing existing classification models and algorithms itself, but, whose range had been limited by feature based statistical methodology. In this paper, we propose RTPost system of different style from i.ny traditional method, which takes fault tolerant system approach and data mining strategy. The 2 important parts of RTPost system are reinforcement training and post-processing part. First, the main point of training method deals with the problem of defining category to be classified before selecting training sample documents. And post-processing method deals with the problem of assigning category, not performance of classification algorithms. In experiments, we applied our system to documents getting low classification accuracy which were laid on a decision boundary nearby. Through the experiments, we shows that our system has high accuracy and stability in actual conditions. It wholly did not depend on some variables which are important influence to classification power such as number of training documents, selection problem and performance of classification algorithms. In addition, we can expect self learning effect which decrease the training cost and increase the training power with employing active learning advantage.

• The KIPS Transactions:PartB
• /
• v.11B no.2
• /
• pp.227-232
• /
• 2004

When we extract a representative term from text for information retrieval system or a special information for information retrieval and text milling system, we often need to solve the anaphora resolution problem. The antecedent decision problem of a pronoun is one of the major issues for anaphora resolution. In this paper, we are suggesting a method of deciding an antecedent of the third personal pronouns, such as “he/she/they” to analyze the contents of documents precisely. Generally, the antecedent of the third personal Pronouns seem to be the subject of the current statement or previous statement, and also it occasionally happens more than twice. Based on these characteristics, we have found rules for deciding an antecedent, by investigating a case of being an antecedent from the personal pronouns, which appears in the current statement and the previous statements. Since the heuristic rule differs on the case of the third personal pronouns, we described it as subjective case, objective case, and possessive case based on the case of the pronouns. We collected 300 sentences that include a pronoun from the newspaper articles on political issues. The result of our experiment shows that the recall and precision ratio on deciding the antecedent of the third personal pronouns are 79.0% and 86.8%, respectively.

• Journal of the Korean Society for information Management
• /
• v.35 no.4
• /
• pp.141-164
• /
• 2018

Recently, as the amount of academic literature has increased rapidly and complex researches have been actively conducted, researchers have difficulty in analyzing trends in previous research. In order to solve this problem, it is necessary to classify information in units of academic papers. However, in Korea, there is no academic database in which such information is provided. In this paper, we propose an automatic classification system that can classify domestic academic literature into multiple classes. To this end, first, academic documents in the technical science field described in Korean were collected and mapped according to class 600 of the DDC by using K-Means clustering technique to construct a learning set capable of multiple classification. As a result of the construction of the training set, 63,915 documents in the Korean technical science field were established except for the values in which metadata does not exist. Using this training set, we implemented and learned the automatic classification engine of academic documents based on deep learning. Experimental results obtained by hand-built experimental set-up showed 78.32% accuracy and 72.45% F1 performance for multiple classification.

• Knowledge Management Research
• /
• v.22 no.1
• /
• pp.243-267
• /
• 2021

Sentiment represents one's own state through the process of change to stimulus, and emotion represents a simple psychological state felt for a certain phenomenon. These two terms tend to be used interchangeably, but their meaning and usage are different. In this study, we try to find out how it affects the helpfulness of reviews by classifying sentiment and emotion through online reviews written by online consumers after purchasing and using various products and services. Recently, online reviews have become a very important factor for businesses and consumers. Helpful reviews play a key role in the decision-making process of potential customers and can be assessed through review helpfulness. The helpfulness of reviews is becoming increasingly important in practice as it is utilized in marketing strategies in business as well as in purchasing decision-making issues of consumers. And academically, the importance of research to find the factors influencing the helpfulness of reviews is growing. In this study, Yelp.com secured reviews on restaurants and conducted a study on how the sentiment and emotion of online reviews affect the helpfulness of reviews. Based on the prior research, a research model including sentiment and emotions for online reviews was built, and text mining analyzes how the sentiment and emotion of online reviews affect the helpfulness of online reviews, and the difference in the effects on emotions It was verified. The results showed that negative sentiment and emotion had a greater effect on review helpfulness, which was consistent with the negative bias theory.

• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.7-15
• /
• 2022

With the aim of an intelligent world in the age of individual customization through decentralization of information and technology, sharing/opening, and connection, we often see a tendency to cross expectations and concerns in the technological discourse and interest in artificial intelligence more than ever. Recently, it is easy to find claims by futurists that AI singularity will appear before and after 2045. Now, as part of preparations to create a paradigm of coexistence that coexists and prosper with AI in the coming age of artificial intelligence, a standard framework for setting up more correct AI ethics and regulations is required. This is because excluding the risk of omission of setting major guidelines and methods for evaluating reasonable and more reasonable guideline items and evaluation standards are increasingly becoming major research issues. In order to solve these research problems and at the same time to develop continuous experiences and learning effects on AI ethics and regulation setting, we collect guideline data on AI ethics and regulation of international organizations / countries / companies, and research and suggest ways to set up a standard framework (SF: Standard Framework) through a setting research model and text mining exploratory analysis. The results of this study can be contributed as basic prior research data for more advanced AI ethics and regulatory guidelines item setting and evaluation methods in the future.

• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.1
• /
• pp.93-114
• /
• 2023

Information extraction can facilitate the intensive analysis of documents by providing semantic triples which consist of named entities and their relations recognized in the texts. However, most of the research so far has been carried out separately for named entity recognition and relation extraction as individual studies, and as a result, the effective performance evaluation of the entire information extraction systems was not performed properly. This paper introduces two models of end-to-end information extraction that can extract various entity names in clinical records and their relationships in the form of semantic triples, namely pipeline and joint models and compares their performances in depth. The pipeline model consists of an entity recognition sub-system based on bidirectional GRU-CRFs and a relation extraction module using multiple encoding scheme, whereas the joint model was implemented with a single bidirectional GRU-CRFs equipped with multi-head labeling method. In the experiments using i2b2/VA 2010, the performance of the pipeline model was 5.5% (F-measure) higher. In addition, through a comparative experiment with existing state-of-the-art systems using large-scale neural language models and manually constructed features, the objective performance level of the end-to-end models implemented in this paper could be identified properly.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.133-142
• /
• 2023

National parks are one of the important types of protected area management systems established by IUCN and a management model for implementing effective conservation and sustainable use of natural and cultural heritage in countries around the world, and they assume important roles in conservation, scientific research, education, recreation and driving community development. In the context of big data, this study takes China's Liaohe National Park, a typical representative of global coastal wetlands, as a case study, and using Python technology to collect tourists' travelogues and reviews from major OTA websites in China as a source. The text spans from 2015 to 2022 and contains 2998 reviews with 166,588 words in total. The results show that wildlife resources, natural landscape, wetland ecology and the fishing and hunting culture of northern China are fully reflected in the perceptions of visitors to Liaohe National Park; visitors have strong positive feelings toward Liaohe National Park, but there is still much room for improvement in supporting services and facilities, public education and visitor experience and participation.

• Journal of the Korean Society of Systems Engineering
• /
• v.20 no.spc1
• /
• pp.12-29
• /
• 2024

The purpose of this study is to identify the social issues discussed in Korea regarding Maritime Autonomous Surface Ships (MASS), the most advanced ICT field in the shipbuilding industry, and to suggest policy implications. In recent years, it has become important to reflect social issues of public interest in the policymaking process. For this reason, an increasing number of studies use media data and social media to identify public opinion. In this study, we collected 2,843 domestic media articles related to MASS from 2017 to 2022, when MASS was officially discussed at the International Maritime Organization, and analyzed them using text mining techniques. Through term frequency-inverse document frequency (TF-IDF) analysis, major keywords such as 'shipbuilding,' 'shipping,' 'US,' and 'HD Hyundai' were derived. For LDA topic modeling, we selected eight topics with the highest coherence score (-2.2) and analyzed the main news for each topic. According to the combined analysis of five years, the topics '1. Technology integration of the shipbuilding industry' and '3. Shipping industry in the post-COVID-19 era' received the most media attention, each accounting for 16%. Conversely, the topic '5. MASS pilotage areas' received the least media attention, accounting for 8 percent. Based on the results of the study, the implications for policy, society, and international security are as follows. First, from a policy perspective, the government should consider the current situation of each industry sector and introduce MASS in stages and carefully, as they will affect the shipbuilding, port, and shipping industries, and a radical introduction may cause various adverse effects. Second, from a social perspective, while the positive aspects of MASS are often reported, there are also negative issues such as cybersecurity issues and the loss of seafarer jobs, which require institutional development and strategic commercialization timing. Third, from a security perspective, MASS are expected to change the paradigm of future maritime warfare, and South Korea is promoting the construction of a maritime unmanned system-based power, but it emphasizes the need for a clear plan and military leadership to secure and develop the technology. This study has academic and policy implications by shedding light on the multidimensional political and social issues of MASS through news data analysis, and suggesting implications from national, regional, strategic, and security perspectives beyond legal and institutional discussions.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.109-131
• /
• 2014

As the demand of nuclear power plant equipment is continuously growing worldwide, the importance of handling nuclear strategic materials is also increasing. While the number of cases submitted for the exports of nuclear-power commodity and technology is dramatically increasing, preadjudication (or prescreening to be simple) of strategic materials has been done so far by experts of a long-time experience and extensive field knowledge. However, there is severe shortage of experts in this domain, not to mention that it takes a long time to develop an expert. Because human experts must manually evaluate all the documents submitted for export permission, the current practice of nuclear material export is neither time-efficient nor cost-effective. Toward alleviating the problem of relying on costly human experts only, our research proposes a new system designed to help field experts make their decisions more effectively and efficiently. The proposed system is built upon case-based reasoning, which in essence extracts key features from the existing cases, compares the features with the features of a new case, and derives a solution for the new case by referencing similar cases and their solutions. Our research proposes a framework of case-based reasoning system, designs a case-based reasoning system for the control of nuclear material exports, and evaluates the performance of alternative keyword extraction methods (full automatic, full manual, and semi-automatic). A keyword extraction method is an essential component of the case-based reasoning system as it is used to extract key features of the cases. The full automatic method was conducted using TF-IDF, which is a widely used de facto standard method for representative keyword extraction in text mining. TF (Term Frequency) is based on the frequency count of the term within a document, showing how important the term is within a document while IDF (Inverted Document Frequency) is based on the infrequency of the term within a document set, showing how uniquely the term represents the document. The results show that the semi-automatic approach, which is based on the collaboration of machine and human, is the most effective solution regardless of whether the human is a field expert or a student who majors in nuclear engineering. Moreover, we propose a new approach of computing nuclear document similarity along with a new framework of document analysis. The proposed algorithm of nuclear document similarity considers both document-to-document similarity (${\alpha}$) and document-to-nuclear system similarity (${\beta}$), in order to derive the final score (${\gamma}$) for the decision of whether the presented case is of strategic material or not. The final score (${\gamma}$) represents a document similarity between the past cases and the new case. The score is induced by not only exploiting conventional TF-IDF, but utilizing a nuclear system similarity score, which takes the context of nuclear system domain into account. Finally, the system retrieves top-3 documents stored in the case base that are considered as the most similar cases with regard to the new case, and provides them with the degree of credibility. With this final score and the credibility score, it becomes easier for a user to see which documents in the case base are more worthy of looking up so that the user can make a proper decision with relatively lower cost. The evaluation of the system has been conducted by developing a prototype and testing with field data. The system workflows and outcomes have been verified by the field experts. This research is expected to contribute the growth of knowledge service industry by proposing a new system that can effectively reduce the burden of relying on costly human experts for the export control of nuclear materials and that can be considered as a meaningful example of knowledge service application.