• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

• Journal of Intelligence and Information Systems
• /
• v.18 no.1
• /
• pp.23-38
• /
• 2012

There is a large difference between purchasing patterns in an online shopping mall and in an offline market. This difference may be caused mainly by the difference in accessibility of online and offline markets. It means that an interval between the initial purchasing decision and its realization appears to be relatively short in an online shopping mall, because a customer can make an order immediately. Because of the short interval between a purchasing decision and its realization, an online shopping mall transaction usually contains fewer items than that of an offline market. In an offline market, customers usually keep some items in mind and buy them all at once a few days after deciding to buy them, instead of buying each item individually and immediately. On the contrary, more than 70% of online shopping mall transactions contain only one item. This statistic implies that traditional data mining techniques cannot be directly applied to online market analysis, because hardly any association rules can survive with an acceptable level of Support because of too many Null Transactions. Most market basket analyses on online shopping mall transactions, therefore, have been performed by expanding the co-occurrence criteria of traditional association rule mining. While the traditional co-occurrence criteria defines items purchased in one transaction as concurrently purchased items, the expanded co-occurrence criteria regards items purchased by a customer during some predefined period (e.g., a day) as concurrently purchased items. In studies using expanded co-occurrence criteria, however, the criteria has been defined arbitrarily by researchers without any theoretical grounds or agreement. The lack of clear grounds of adopting a certain co-occurrence criteria degrades the reliability of the analytical results. Moreover, it is hard to derive new meaningful findings by combining the outcomes of previous individual studies. In this paper, we attempt to compare expanded co-occurrence criteria and propose a guideline for selecting an appropriate one. First of all, we compare the accuracy of association rules discovered according to various co-occurrence criteria. By doing this experiment we expect that we can provide a guideline for selecting appropriate co-occurrence criteria that corresponds to the purpose of the analysis. Additionally, we will perform similar experiments with several groups of customers that are segmented by each customer's average duration between orders. By this experiment, we attempt to discover the relationship between the optimal co-occurrence criteria and the customer's average duration between orders. Finally, by a series of experiments, we expect that we can provide basic guidelines for developing customized recommendation systems. Our experiments use a real dataset acquired from one of the largest internet shopping malls in Korea. We use 66,278 transactions of 3,847 customers conducted during the last two years. Overall results show that the accuracy of association rules of frequent shoppers (whose average duration between orders is relatively short) is higher than that of causal shoppers. In addition we discover that with frequent shoppers, the accuracy of association rules appears very high when the co-occurrence criteria of the training set corresponds to the validation set (i.e., target set). It implies that the co-occurrence criteria of frequent shoppers should be set according to the application purpose period. For example, an analyzer should use a day as a co-occurrence criterion if he/she wants to offer a coupon valid only for a day to potential customers who will use the coupon. On the contrary, an analyzer should use a month as a co-occurrence criterion if he/she wants to publish a coupon book that can be used for a month. In the case of causal shoppers, the accuracy of association rules appears to not be affected by the period of the application purposes. The accuracy of the causal shoppers' association rules becomes higher when the longer co-occurrence criterion has been adopted. It implies that an analyzer has to set the co-occurrence criterion for as long as possible, regardless of the application purpose period.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.61-83
• /
• 2012

A knowledge map describes the network of related knowledge into the form of a diagram, and therefore underpins the structure of knowledge categorizing and archiving by defining the relationship of the referential navigation between knowledge. The referential navigation between knowledge means the relationship of cross-referencing exhibited when a piece of knowledge is utilized by a user. To understand the contents of the knowledge, a user usually requires additionally information or knowledge related with each other in the relation of cause and effect. This relation can be expanded as the effective connection between knowledge increases, and finally forms the network of knowledge. A network display of knowledge using nodes and links to arrange and to represent the relationship between concepts can provide a more complex knowledge structure than a hierarchical display. Moreover, it can facilitate a user to infer through the links shown on the network. For this reason, building a knowledge map based on the ontology technology has been emphasized to formally as well as objectively describe the knowledge and its relationships. As the necessity to build a knowledge map based on the structure of the ontology has been emphasized, not a few researches have been proposed to fulfill the needs. However, most of those researches to apply the ontology to build the knowledge map just focused on formally expressing knowledge and its relationships with other knowledge to promote the possibility of knowledge reuse. Although many types of knowledge maps based on the structure of the ontology were proposed, no researches have tried to design and implement the referential navigation-enabled knowledge map. This paper addresses a methodology to build the ontology-based knowledge map enabling the referential navigation between knowledge. The ontology-based knowledge map resulted from the proposed methodology can not only express the referential navigation between knowledge but also infer additional relationships among knowledge based on the referential relationships. The most highlighted benefits that can be delivered by applying the ontology technology to the knowledge map include; formal expression about knowledge and its relationships with others, automatic identification of the knowledge network based on the function of self-inference on the referential relationships, and automatic expansion of the knowledge-base designed to categorize and store knowledge according to the network between knowledge. To enable the referential navigation between knowledge included in the knowledge map, and therefore to form the knowledge map in the format of a network, the ontology must describe knowledge according to the relation with the process and task. A process is composed of component tasks, while a task is activated after any required knowledge is inputted. Since the relation of cause and effect between knowledge can be inherently determined by the sequence of tasks, the referential relationship between knowledge can be circuitously implemented if the knowledge is modeled to be one of input or output of each task. To describe the knowledge with respect to related process and task, the Protege-OWL, an editor that enables users to build ontologies for the Semantic Web, is used. An OWL ontology-based knowledge map includes descriptions of classes (process, task, and knowledge), properties (relationships between process and task, task and knowledge), and their instances. Given such an ontology, the OWL formal semantics specifies how to derive its logical consequences, i.e. facts not literally present in the ontology, but entailed by the semantics. Therefore a knowledge network can be automatically formulated based on the defined relationships, and the referential navigation between knowledge is enabled. To verify the validity of the proposed concepts, two real business process-oriented knowledge maps are exemplified: the knowledge map of the process of 'Business Trip Application' and 'Purchase Management'. By applying the 'DL-Query' provided by the Protege-OWL as a plug-in module, the performance of the implemented ontology-based knowledge map has been examined. Two kinds of queries to check whether the knowledge is networked with respect to the referential relations as well as the ontology-based knowledge network can infer further facts that are not literally described were tested. The test results show that not only the referential navigation between knowledge has been correctly realized, but also the additional inference has been accurately performed.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.67-88
• /
• 2019

Webtoon is a Korean-style digital comics platform that distributes comics content produced using the characteristic elements of the Internet in a form that can be consumed online. With the recent rapid growth of the webtoon industry and the exponential increase in the supply of webtoon content, the need for effective webtoon content recommendation measures is growing. Webtoons are digital content products that combine pictorial, literary and digital elements. Therefore, webtoons stimulate consumer sentiment by making readers have fun and engaging and empathizing with the situations in which webtoons are produced. In this context, it can be expected that the sentiment that webtoons evoke to consumers will serve as an important criterion for consumers' choice of webtoons. However, there is a lack of research to improve webtoons' recommendation performance by utilizing consumer sentiment. This study is aimed at developing consumer sentiment pattern maps that can support effective recommendations of webtoon content, focusing on consumer sentiments that have not been fully discussed previously. Metadata and consumer sentiments data were collected for 200 works serviced on the Korean webtoon platform 'Naver Webtoon' to conduct this study. 488 sentiment terms were collected for 127 works, excluding those that did not meet the purpose of the analysis. Next, similar or duplicate terms were combined or abstracted in accordance with the bottom-up approach. As a result, we have built webtoons specialized sentiment-index, which are reduced to a total of 63 emotive adjectives. By performing exploratory factor analysis on the constructed sentiment-index, we have derived three important dimensions for classifying webtoon types. The exploratory factor analysis was performed through the Principal Component Analysis (PCA) using varimax factor rotation. The three dimensions were named 'Immersion', 'Touch' and 'Irritant' respectively. Based on this, K-Means clustering was performed and the entire webtoons were classified into four types. Each type was named 'Snack', 'Drama', 'Irritant', and 'Romance'. For each type of webtoon, we wrote webtoon-sentiment 2-Mode network graphs and looked at the characteristics of the sentiment pattern appearing for each type. In addition, through profiling analysis, we were able to derive meaningful strategic implications for each type of webtoon. First, The 'Snack' cluster is a collection of webtoons that are fast-paced and highly entertaining. Many consumers are interested in these webtoons, but they don't rate them well. Also, consumers mostly use simple expressions of sentiment when talking about these webtoons. Webtoons belonging to 'Snack' are expected to appeal to modern people who want to consume content easily and quickly during short travel time, such as commuting time. Secondly, webtoons belonging to 'Drama' are expected to evoke realistic and everyday sentiments rather than exaggerated and light comic ones. When consumers talk about webtoons belonging to a 'Drama' cluster in online, they are found to express a variety of sentiments. It is appropriate to establish an OSMU(One source multi-use) strategy to extend these webtoons to other content such as movies and TV series. Third, the sentiment pattern map of 'Irritant' shows the sentiments that discourage customer interest by stimulating discomfort. Webtoons that evoke these sentiments are hard to get public attention. Artists should pay attention to these sentiments that cause inconvenience to consumers in creating webtoons. Finally, Webtoons belonging to 'Romance' do not evoke a variety of consumer sentiments, but they are interpreted as touching consumers. They are expected to be consumed as 'healing content' targeted at consumers with high levels of stress or mental fatigue in their lives. The results of this study are meaningful in that it identifies the applicability of consumer sentiment in the areas of recommendation and classification of webtoons, and provides guidelines to help members of webtoons' ecosystem better understand consumers and formulate strategies.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.113-137
• /
• 2021

According to the clear potential of mobile banking growth, many studies related to this are being conducted, but in Korea, it is concentrated on the analysis of technical factors or consumers' intentions, behaviors, and satisfaction. In addition, even though it has a strong customer base of 20s, there are few studies that have been conducted specifically for this customer group. In order for mobile banking to take a leap forward, a strategy to secure various perspectives is needed not only through research on itself but also through research on external factors affecting mobile banking. Therefore, this study analyzes impulsiveness, credit card use, and SNS addiction among various external factors that can significantly affect mobile banking in their 20s. This study examines whether the relationship between impulsiveness and mobile banking usage depends on whether or not a credit card is used, and checks whether a customer's impulsiveness is possible by examining whether a credit card is used. Based on this, it is possible to establish new standards for classification of marketing target groups of mobile banking. After finding out the static or unsuitable relationship between whether to use a credit card and impulsiveness, we want to indirectly predict the customer's impulsiveness through whether to use a credit card or not to use a credit card. It also verifies the mediating effect of SNS addiction in the relationship between impulsiveness and mobile banking usage. For this analysis, the collected data were conducted according to research problems using the SPSS Statistics 25 program. The findings are as follows. First, positive urgency has been shown to have a significant static effect on mobile banking usage. Second, whether to use credit cards has shown moderating effects in the relationship between fraudulent urgency and mobile banking usage. Third, it has been shown that all subfactors of impulsiveness have significant static relationships with subfactors of SNS addiction. Fourth, it has been confirmed that the relationship between positive urgency, SNS addiction, and mobile banking usage has total effect and direct effect. The first result means that mobile banking usage may be high if positive urgency is measured relatively high, even if the multi-dimensional impulsiveness scale is low. The second result indicates that mobile banking usage rates were not affected by the independent variable, negative urgency, but were found to have a significant static relationship with negative urgency when using credit cards. The third result means that SNS is likely to become addictive if lack of premeditation or lack of perseverance is high because it provides instant enjoyment and satisfaction as a mobile-based service. This also means that SNS can be used as an avoidance space for those with negative urgency, and as an emotional expression space for those with high positive urgency.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.99-122
• /
• 2019

According to the recent IDC (International Data Corporation) report, as from 2025, the total volume of data is estimated to reach ten times higher than that of 2016, corresponding to 163 zettabytes. then the main body of generating information is moving more toward corporations than consumers. So-called "the wave of Big-data" is arriving, and the following aftermath affects entire industries and firms, respectively and collectively. Therefore, effective management of vast amounts of data is more important than ever in terms of the firm. However, there have been no previous studies that measure the effects of big data investment, even though there are number of previous studies that quantitatively the effects of IT investment. Therefore, we quantitatively analyze the Big-data investment effects, which assists firm's investment decision making. This study applied the Event Study Methodology, which is based on the efficient market hypothesis as the theoretical basis, to measure the effect of the big data investment of firms on the response of market investors. In addition, five sub-variables were set to analyze this effect in more depth: the contents are firm size classification, industry classification (finance and ICT), investment completion classification, and vendor existence classification. To measure the impact of Big data investment announcements, Data from 91 announcements from 2010 to 2017 were used as data, and the effect of investment was more empirically observed by observing changes in corporate value immediately after the disclosure. This study collected data on Big Data Investment related to Naver 's' News' category, the largest portal site in Korea. In addition, when selecting the target companies, we extracted the disclosures of listed companies in the KOSPI and KOSDAQ market. During the collection process, the search keywords were searched through the keywords 'Big data construction', 'Big data introduction', 'Big data investment', 'Big data order', and 'Big data development'. The results of the empirically proved analysis are as follows. First, we found that the market value of 91 publicly listed firms, who announced Big-data investment, increased by 0.92%. In particular, we can see that the market value of finance firms, non-ICT firms, small-cap firms are significantly increased. This result can be interpreted as the market investors perceive positively the big data investment of the enterprise, allowing market investors to better understand the company's big data investment. Second, statistical demonstration that the market value of financial firms and non - ICT firms increases after Big data investment announcement is proved statistically. Third, this study measured the effect of big data investment by dividing by company size and classified it into the top 30% and the bottom 30% of company size standard (market capitalization) without measuring the median value. To maximize the difference. The analysis showed that the investment effect of small sample companies was greater, and the difference between the two groups was also clear. Fourth, one of the most significant features of this study is that the Big Data Investment announcements are classified and structured according to vendor status. We have shown that the investment effect of a group with vendor involvement (with or without a vendor) is very large, indicating that market investors are very positive about the involvement of big data specialist vendors. Lastly but not least, it is also interesting that market investors are evaluating investment more positively at the time of the Big data Investment announcement, which is scheduled to be built rather than completed. Applying this to the industry, it would be effective for a company to make a disclosure when it decided to invest in big data in terms of increasing the market value. Our study has an academic implication, as prior research looked for the impact of Big-data investment has been nonexistent. This study also has a practical implication in that it can be a practical reference material for business decision makers considering big data investment.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.19-41
• /
• 2019

According to the rapidly increasing demand for text data analysis, research and investment in text mining are being actively conducted not only in academia but also in various industries. Text mining is generally conducted in two steps. In the first step, the text of the collected document is tokenized and structured to convert the original document into a computer-readable form. In the second step, tasks such as document classification, clustering, and topic modeling are conducted according to the purpose of analysis. Until recently, text mining-related studies have been focused on the application of the second steps, such as document classification, clustering, and topic modeling. However, with the discovery that the text structuring process substantially influences the quality of the analysis results, various embedding methods have actively been studied to improve the quality of analysis results by preserving the meaning of words and documents in the process of representing text data as vectors. Unlike structured data, which can be directly applied to a variety of operations and traditional analysis techniques, Unstructured text should be preceded by a structuring task that transforms the original document into a form that the computer can understand before analysis. It is called "Embedding" that arbitrary objects are mapped to a specific dimension space while maintaining algebraic properties for structuring the text data. Recently, attempts have been made to embed not only words but also sentences, paragraphs, and entire documents in various aspects. Particularly, with the demand for analysis of document embedding increases rapidly, many algorithms have been developed to support it. Among them, doc2Vec which extends word2Vec and embeds each document into one vector is most widely used. However, the traditional document embedding method represented by doc2Vec generates a vector for each document using the whole corpus included in the document. This causes a limit that the document vector is affected by not only core words but also miscellaneous words. Additionally, the traditional document embedding schemes usually map each document into a single corresponding vector. Therefore, it is difficult to represent a complex document with multiple subjects into a single vector accurately using the traditional approach. In this paper, we propose a new multi-vector document embedding method to overcome these limitations of the traditional document embedding methods. This study targets documents that explicitly separate body content and keywords. In the case of a document without keywords, this method can be applied after extract keywords through various analysis methods. However, since this is not the core subject of the proposed method, we introduce the process of applying the proposed method to documents that predefine keywords in the text. The proposed method consists of (1) Parsing, (2) Word Embedding, (3) Keyword Vector Extraction, (4) Keyword Clustering, and (5) Multiple-Vector Generation. The specific process is as follows. all text in a document is tokenized and each token is represented as a vector having N-dimensional real value through word embedding. After that, to overcome the limitations of the traditional document embedding method that is affected by not only the core word but also the miscellaneous words, vectors corresponding to the keywords of each document are extracted and make up sets of keyword vector for each document. Next, clustering is conducted on a set of keywords for each document to identify multiple subjects included in the document. Finally, a Multi-vector is generated from vectors of keywords constituting each cluster. The experiments for 3.147 academic papers revealed that the single vector-based traditional approach cannot properly map complex documents because of interference among subjects in each vector. With the proposed multi-vector based method, we ascertained that complex documents can be vectorized more accurately by eliminating the interference among subjects.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.201-220
• /
• 2019

Fake news has emerged as a significant issue over the last few years, igniting discussions and research on how to solve this problem. In particular, studies on automated fact-checking and fake news detection using artificial intelligence and text analysis techniques have drawn attention. Fake news detection research entails a form of document classification; thus, document classification techniques have been widely used in this type of research. However, document summarization techniques have been inconspicuous in this field. At the same time, automatic news summarization services have become popular, and a recent study found that the use of news summarized through abstractive summarization has strengthened the predictive performance of fake news detection models. Therefore, the need to study the integration of document summarization technology in the domestic news data environment has become evident. In order to examine the effect of extractive summarization on the fake news detection model, we first summarized news articles through extractive summarization. Second, we created a summarized news-based detection model. Finally, we compared our model with the full-text-based detection model. The study found that BPN(Back Propagation Neural Network) and SVM(Support Vector Machine) did not exhibit a large difference in performance; however, for DT(Decision Tree), the full-text-based model demonstrated a somewhat better performance. In the case of LR(Logistic Regression), our model exhibited the superior performance. Nonetheless, the results did not show a statistically significant difference between our model and the full-text-based model. Therefore, when the summary is applied, at least the core information of the fake news is preserved, and the LR-based model can confirm the possibility of performance improvement. This study features an experimental application of extractive summarization in fake news detection research by employing various machine-learning algorithms. The study's limitations are, essentially, the relatively small amount of data and the lack of comparison between various summarization technologies. Therefore, an in-depth analysis that applies various analytical techniques to a larger data volume would be helpful in the future.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.75-94
• /
• 2021

The low birth rate and shortened military service period are causing concerns about selecting excellent military officers. The Republic of Korea entered a low birth rate society in 1984 and an aged society in 2018 respectively, and is expected to be in a super-aged society in 2025. In addition, the troop-oriented military is changed as a state-of-the-art weapons-oriented military, and the reduction of the military service period was implemented in 2018 to ease the burden of military service for young people and play a role in the society early. Some observe that the application rate for military officers is falling due to a decrease of manpower resources and a preference for shortened mandatory military service over military officers. This requires further consideration of the policy of securing excellent military officers. Most of the related studies have used social scientists' methodologies, but this study applies the methodology of text mining suitable for large-scale documents analysis. This study extracts words of discriminative characteristics from the Republic of Korea Air Force Non-Commissioned Officer Applicant cover letters and analyzes the polarity of pass and fail. It consists of three steps in total. First, the application is divided into general and technical fields, and the words characterized in the cover letter are ordered according to the difference in the frequency ratio of each field. The greater the difference in the proportion of each application field, the field character is defined as 'more discriminative'. Based on this, we extract the top 50 words representing discriminative characteristics in general fields and the top 50 words representing discriminative characteristics in technology fields. Second, the number of appropriate topics in the overall cover letter is calculated through the LDA. It uses perplexity score and coherence score. Based on the appropriate number of topics, we then use LDA to generate topic and probability, and estimate which topic words of discriminative characteristic belong to. Subsequently, the keyword indicators of questions used to set the labeling candidate index, and the most appropriate index indicator is set as the label for the topic when considering the topic-specific word distribution. Third, using L-LDA, which sets the cover letter and label as pass and fail, we generate topics and probabilities for each field of pass and fail labels. Furthermore, we extract only words of discriminative characteristics that give labeled topics among generated topics and probabilities by pass and fail labels. Next, we extract the difference between the probability on the pass label and the probability on the fail label by word of the labeled discriminative characteristic. A positive figure can be seen as having the polarity of pass, and a negative figure can be seen as having the polarity of fail. This study is the first research to reflect the characteristics of cover letters of Republic of Korea Air Force non-commissioned officer applicants, not in the private sector. Moreover, these methodologies can apply text mining techniques for multiple documents, rather survey or interview methods, to reduce analysis time and increase reliability for the entire population. For this reason, the methodology proposed in the study is also applicable to other forms of multiple documents in the field of military personnel. This study shows that L-LDA is more suitable than LDA to extract discriminative characteristics of Republic of Korea Air Force Noncommissioned cover letters. Furthermore, this study proposes a methodology that uses a combination of LDA and L-LDA. Therefore, through the analysis of the results of the acquisition of non-commissioned Republic of Korea Air Force officers, we would like to provide information available for acquisition and promotional policies and propose a methodology available for research in the field of military manpower acquisition.