• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.1-17
• /
• 2015

In this paper, we report what we have observed with regards to a prediction model for the military based on enlisted men's internal(cumulative records) and external data(SNS data). This work is significant in the military's efforts to supervise them. In spite of their effort, many commanders have failed to prevent accidents by their subordinates. One of the important duties of officers' work is to take care of their subordinates in prevention unexpected accidents. However, it is hard to prevent accidents so we must attempt to determine a proper method. Our motivation for presenting this paper is to mate it possible to predict accidents using enlisted men's internal and external data. The biggest issue facing the military is the occurrence of accidents by enlisted men related to maladjustment and the relaxation of military discipline. The core method of preventing accidents by soldiers is to identify problems and manage them quickly. Commanders predict accidents by interviewing their soldiers and observing their surroundings. It requires considerable time and effort and results in a significant difference depending on the capabilities of the commanders. In this paper, we seek to predict accidents with objective data which can easily be obtained. Recently, records of enlisted men as well as SNS communication between commanders and soldiers, make it possible to predict and prevent accidents. This paper concerns the application of data mining to identify their interests, predict accidents and make use of internal and external data (SNS). We propose both a topic analysis and decision tree method. The study is conducted in two steps. First, topic analysis is conducted through the SNS of enlisted men. Second, the decision tree method is used to analyze the internal data with the results of the first analysis. The dependent variable for these analysis is the presence of any accidents. In order to analyze their SNS, we require tools such as text mining and topic analysis. We used SAS Enterprise Miner 12.1, which provides a text miner module. Our approach for finding their interests is composed of three main phases; collecting, topic analysis, and converting topic analysis results into points for using independent variables. In the first phase, we collect enlisted men's SNS data by commender's ID. After gathering unstructured SNS data, the topic analysis phase extracts issues from them. For simplicity, 5 topics(vacation, friends, stress, training, and sports) are extracted from 20,000 articles. In the third phase, using these 5 topics, we quantify them as personal points. After quantifying their topic, we include these results in independent variables which are composed of 15 internal data sets. Then, we make two decision trees. The first tree is composed of their internal data only. The second tree is composed of their external data(SNS) as well as their internal data. After that, we compare the results of misclassification from SAS E-miner. The first model's misclassification is 12.1%. On the other hand, second model's misclassification is 7.8%. This method predicts accidents with an accuracy of approximately 92%. The gap of the two models is 4.3%. Finally, we test if the difference between them is meaningful or not, using the McNemar test. The result of test is considered relevant.(p-value : 0.0003) This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of enlisted men's data. Additionally, various independent variables used in the decision tree model are used as categorical variables instead of continuous variables. So it suffers a loss of information. In spite of extensive efforts to provide prediction models for the military, commanders' predictions are accurate only when they have sufficient data about their subordinates. Our proposed methodology can provide support to decision-making in the military. This study is expected to contribute to the prevention of accidents in the military based on scientific analysis of enlisted men and proper management of them.

• The Korean Journal of Archival Studies
• /
• no.26
• /
• pp.103-149
• /
• 2010

Documentation strategy has been experimented in various subject areas and local regions since late 1980's when it was proposed as archival appraisal and selection methods by archival communities in the United States. Though it was criticized to be too ideal, it needs to shed new light on the potentialities of the strategy for documenting local regions in digital environment. The purpose of this study is to analyse the implementation issues of documentation strategy and to suggest the directions for documenting local regions of Korea through the application of the strategy. The documentation strategy which was developed more than twenty years ago in mostly western countries gives us some implications for documenting local regions even in current digital environments. They are as follows; Firstly, documentation strategy can enhance the value of archivists as well as archives in local regions because archivist should be active shaper of history rather than passive receiver of archives according to the strategy. It can also be a solution for overcoming poor conditions of local archives management in Korea. Secondly, the strategy can encourage cooperation between collecting institutions including museums, libraries, archives, cultural centers, history institutions, etc. in each local region. In the networked environment the cooperation can be achieved more effectively than in traditional environment where the heavy workload of cooperative institutions is needed. Thirdly, the strategy can facilitate solidarity of various groups in local region. According to the analysis of the strategy projects, it is essential to collect their knowledge, passion, and enthusiasm of related groups to effectively implement the strategy. It can also provide a methodology for minor groups of society to document their memories. This study suggests the directions of documenting local regions in consideration of current archival infrastructure of Korean as follows; Firstly, very selective and intensive documentation should be pursued rather than comprehensive one for documenting local regions. Though it is a very political problem to decide what subject has priority for documentation, interests of local community members as well as professional groups should be considered in the decision-making process seriously. Secondly, it is effective to plan integrated representation of local history in the distributed custody of local archives. It would be desirable to implement archival gateway for integrated search and representation of local archives regardless of the location of archives. Thirdly, it is necessary to try digital documentation using Web 2.0 technologies. Documentation strategy as the methodology of selecting and acquiring archives can not avoid subjectivity and prejudices of appraiser completely. To mitigate the problems, open documentation system should be prepared for reflecting different interests of different groups. Fourth, it is desirable to apply a conspectus model used in cooperative collection management of libraries to document local regions digitally. Conspectus can show existing documentation strength and future documentation intensity for each participating institution. Using this, documentation level of each subject area can be set up cooperatively and effectively in the local regions.

• The korean journal of orthodontics
• /
• v.31 no.1 s.84
• /
• pp.25-38
• /
• 2001

The purpose of this study was to compare the force, the displacement and the stress distribution on the maxillary first molars altered by the application of various asymmetric head-gear. For this study, the finite element models of unilateral Cl II maxillary dental arch was made. Also, the finite element models of asymmetric face-bow was made. Three types of asymmetric face-bow were made : each of the right side 15mm, 25mm and 35mm shorter than the left side. We compared the forces, the displacement and the distribution of stress that were generated by application of various asymmetric head-gear, The results were as follows. 1. The total forces that both maxillary first molars received were similar in all groups. But the forces that mesially positioned tooth received were increased as the length of the outer-bow shortened, and the forces that normally positioned tooth received were decreased as the length of the outer-bow shortened. 2. In lateral force comparison, the buccal forces that normally positioned tooth received were increased as the length of the outer-bow shortened, and the buccal fortes that mesially positioned tooth received were decreased as the length of the outer-bow shortened. Though the net lateral force moved to the buccal side of normally positioned tooth as the length of the outer-bow shortened, both maxillary first molars received the buccal force. That showed 'Avchiai Expansion Effect' 3. The distal forces, the extrusion forces and the magnitudes of the crown distal tipping that mesially positioned tooth received were increased as the length of the outer-bow shortened, and the forces that normally positioned tooth received were decreased as the length of the outer-bow was shortened. 4. The magnitude of the distal-in rotation that normally positioned tooth received were increased as the length of the outer-bow was shortened. But, mesially positioned tooth show two different results. For the outer-bow 15mm shortened, mesially positioned tooth showed the distal-in rotation, hut for the outer-bow 25mm and 35mn shortened, mesially positioned tooth showed the distal-out rotation. Thus, the turning point exists between 15mm and 25mm. 5. This study of the initial stress distribution of the periodontal ligament at slightly inferior of the furcation area revealed that the compressive stress in the distobuccal root of the normally positioned tooth moved from the palatal side to the distal side and the buccal side successively as the length of the outer-bow shortened. 6. This study of the initial stress distribution of the periodontal ligament at slightly inferior of the furcation area revealed that the magnitudes of stress were altered but the total stress distributions were not altered in the mesiobuccal root and the palatal root of normally positioned tooth, and also three roots of mesially positioned tooth as the length of the outer-bow shortened.

• 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.3
• /
• pp.165-183
• /
• 2016

Over the past decade, there has been a rapid diffusion of technological devices and a rising number of various devices, resulting in an escalation of virtual reality technology. Technological market has rapidly been changed from smartphone to wearable devices based on virtual reality. Virtual reality can make users feel real situation through sensing interaction, voice, motion capture and so on. Facebook.com, Google, Samsung, LG, Sony and so on have investigated developing platform of virtual reality. the pricing of virtual reality devices also had decreased into 30% from their launched period. Thus market infrastructure in virtual reality have rapidly been developed to crease marketplace. However, most consumers recognize that virtual reality is not ease to purchase or use. That could not lead consumers to positive attitude for devices and purchase the related devices in the early market. Through previous studies related to virtual reality, there are few studies focusing on why the devices for virtual reality stayed in early stage in adoption & diffusion context in the market. Almost previous studies considered the reasons of hard adoption for innovative products in the viewpoints of Typology of Innovation Resistance, MIR(Management of Innovation Resistant), UTAUT & UTAUT2. However, product-based antecedents also important to increase user intention to purchase and use products in the technological market. In this study, we focus on user acceptance and resistance for increasing purchase and usage promotions of wearable devices related to virtual reality based on headgear products like Galaxy Gear. Especially, we added a variables like attitude confidence as a dimension for user resistance. The research questions of this study are follows. First, how attitude confidence and innovativeness resistance affect user intention to use? Second, What factors related to content and brand contexts can affect user intention to use? This research collected data from the participants who have experiences using virtual rality headgears aged between 20s to 50s located in South Korea. In order to collect data, this study used a pilot test and through making face-to-face interviews on three specialists, face validity and content validity were evaluated for the questionnaire validity. Cleansing the data, we dropped some outliers and data of irrelevant papers. Totally, 156 responses were used for testing the suggested hypotheses. Through collecting data, demographics and the relationships among variables were analyzed through conducting structural equation modeling by PLS. The data showed that the sex of respondents who have experience using social commerce sites (male=86(55.1%), female=70(44.9%). The ages of respondents are mostly from 20s (74.4%) to 30s (16.7%). 126 respondents (80.8%) have used virtual reality devices. The results of our model estimation are as follows. With the exception of Hypothesis 1 and 7, which deals with the two relationships between brand awareness to attitude confidence, and quality of content to perceived enjoyment, all of our hypotheses were supported. In compliance with our hypotheses, perceived ease of use (H2) and use innovativeness (H3) were supported with its positively influence for the attitude confidence. This finding indicates that the more ease of use and innovativeness for devices increased, the more users' attitude confidence increased. Perceived price (H4), enjoyment (H5), Quantity of contents (H6) significantly increase user resistance. However, perceived price positively affect user innovativeness resistance meanwhile perceived enjoyment and quantity of contents negatively affect user innovativeness resistance. In addition, aesthetic exterior (H6) was also positively associated with perceived price (p<0.01). Also projection quality (H8) can increase perceived enjoyment (p<0.05). Finally, attitude confidence (H10) increased user intention to use virtual reality devices. however user resistance (H11) negatively affect user intention to use virtual reality devices. The findings of this study show that attitude confidence and user innovativeness resistance differently influence customer intention for using virtual reality devices. There are two distinct characteristic of attitude confidence: perceived ease of use and user innovativeness. This study identified the antecedents of different roles of perceived price (aesthetic exterior) and perceived enjoyment (quality of contents & projection quality). The findings indicated that brand awareness and quality of contents for virtual reality is not formed within virtual reality market yet. Therefore, firms should developed brand awareness for their product in the virtual market to increase market share.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.95-108
• /
• 2017

Recently, AlphaGo which is Bakuk (Go) artificial intelligence program by Google DeepMind, had a huge victory against Lee Sedol. Many people thought that machines would not be able to win a man in Go games because the number of paths to make a one move is more than the number of atoms in the universe unlike chess, but the result was the opposite to what people predicted. After the match, artificial intelligence technology was focused as a core technology of the fourth industrial revolution and attracted attentions from various application domains. Especially, deep learning technique have been attracted as a core artificial intelligence technology used in the AlphaGo algorithm. The deep learning technique is already being applied to many problems. Especially, it shows good performance in image recognition field. In addition, it shows good performance in high dimensional data area such as voice, image and natural language, which was difficult to get good performance using existing machine learning techniques. However, in contrast, it is difficult to find deep leaning researches on traditional business data and structured data analysis. In this study, we tried to find out whether the deep learning techniques have been studied so far can be used not only for the recognition of high dimensional data but also for the binary classification problem of traditional business data analysis such as customer churn analysis, marketing response prediction, and default prediction. And we compare the performance of the deep learning techniques with that of traditional artificial neural network models. The experimental data in the paper is the telemarketing response data of a bank in Portugal. It has input variables such as age, occupation, loan status, and the number of previous telemarketing and has a binary target variable that records whether the customer intends to open an account or not. In this study, to evaluate the possibility of utilization of deep learning algorithms and techniques in binary classification problem, we compared the performance of various models using CNN, LSTM algorithm and dropout, which are widely used algorithms and techniques in deep learning, with that of MLP models which is a traditional artificial neural network model. However, since all the network design alternatives can not be tested due to the nature of the artificial neural network, the experiment was conducted based on restricted settings on the number of hidden layers, the number of neurons in the hidden layer, the number of output data (filters), and the application conditions of the dropout technique. The F1 Score was used to evaluate the performance of models to show how well the models work to classify the interesting class instead of the overall accuracy. The detail methods for applying each deep learning technique in the experiment is as follows. The CNN algorithm is a method that reads adjacent values from a specific value and recognizes the features, but it does not matter how close the distance of each business data field is because each field is usually independent. In this experiment, we set the filter size of the CNN algorithm as the number of fields to learn the whole characteristics of the data at once, and added a hidden layer to make decision based on the additional features. For the model having two LSTM layers, the input direction of the second layer is put in reversed position with first layer in order to reduce the influence from the position of each field. In the case of the dropout technique, we set the neurons to disappear with a probability of 0.5 for each hidden layer. The experimental results show that the predicted model with the highest F1 score was the CNN model using the dropout technique, and the next best model was the MLP model with two hidden layers using the dropout technique. In this study, we were able to get some findings as the experiment had proceeded. First, models using dropout techniques have a slightly more conservative prediction than those without dropout techniques, and it generally shows better performance in classification. Second, CNN models show better classification performance than MLP models. This is interesting because it has shown good performance in binary classification problems which it rarely have been applied to, as well as in the fields where it's effectiveness has been proven. Third, the LSTM algorithm seems to be unsuitable for binary classification problems because the training time is too long compared to the performance improvement. From these results, we can confirm that some of the deep learning algorithms can be applied to solve business binary classification problems.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.53-77
• /
• 2015

Mobile commerce provides a convenient shopping experience in which users can buy products without the constraints of time and space. Mobile commerce has already set off a mega trend in Korea. The market size is estimated at approximately 15 trillion won (KRW) for 2015, thus far. In the Korean market, social commerce and open market are key components. Social commerce has an overwhelming open market in terms of the number of users in the Korean mobile commerce market. From the point of view of the industry, quick market entry, and content curation are considered to be the major success factors, reflecting the rapid growth of social commerce in the market. However, academics' empirical research and analysis to prove the success rate of social commerce is still insufficient. Henceforward, it is to be expected that social commerce and the open market in the Korean mobile commerce will compete intensively. So it is important to conduct an empirical analysis to prove the differences in user experience between social commerce and open market. This paper is an exploratory study that shows a comparative analysis of social commerce and the open market regarding user experience, which is based on the mobile users' reviews. Firstly, this study includes a collection of approximately 10,000 user reviews of social commerce and open market listed Google play. A collection of mobile user reviews were classified into topics, such as perceived usefulness and perceived ease of use through LDA topic modeling. Then, a sentimental analysis and co-occurrence analysis on the topics of perceived usefulness and perceived ease of use was conducted. The study's results demonstrated that social commerce users have a more positive experience in terms of service usefulness and convenience versus open market in the mobile commerce market. Social commerce has provided positive user experiences to mobile users in terms of service areas, like 'delivery,' 'coupon,' and 'discount,' while open market has been faced with user complaints in terms of technical problems and inconveniences like 'login error,' 'view details,' and 'stoppage.' This result has shown that social commerce has a good performance in terms of user service experience, since the aggressive marketing campaign conducted and there have been investments in building logistics infrastructure. However, the open market still has mobile optimization problems, since the open market in mobile commerce still has not resolved user complaints and inconveniences from technical problems. This study presents an exploratory research method used to analyze user experience by utilizing an empirical approach to user reviews. In contrast to previous studies, which conducted surveys to analyze user experience, this study was conducted by using empirical analysis that incorporates user reviews for reflecting users' vivid and actual experiences. Specifically, by using an LDA topic model and TAM this study presents its methodology, which shows an analysis of user reviews that are effective due to the method of dividing user reviews into service areas and technical areas from a new perspective. The methodology of this study has not only proven the differences in user experience between social commerce and open market, but also has provided a deep understanding of user experience in Korean mobile commerce. In addition, the results of this study have important implications on social commerce and open market by proving that user insights can be utilized in establishing competitive and groundbreaking strategies in the market. The limitations and research direction for follow-up studies are as follows. In a follow-up study, it will be required to design a more elaborate technique of the text analysis. This study could not clearly refine the user reviews, even though the ones online have inherent typos and mistakes. This study has proven that the user reviews are an invaluable source to analyze user experience. The methodology of this study can be expected to further expand comparative research of services using user reviews. Even at this moment, users around the world are posting their reviews about service experiences after using the mobile game, commerce, and messenger applications.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.93-112
• /
• 2015

Depending on the change in consumer's consumption pattern, existing retail shop has evolved in hypermarket or convenience store offering grocery and daily products mostly. Therefore, it is important to maintain the inventory levels and proper product configuration for effectively utilize the limited space in the retail store and increasing sales. Accordingly, this study proposed proper product configuration and inventory level strategy based on RFM(Recency, Frequency, Monetary) model and SOM(self-organizing map) for manage the retail shop effectively. RFM model is analytic model to analyze customer behaviors based on the past customer's buying activities. And it can differentiates important customers from large data by three variables. R represents recency, which refers to the last purchase of commodities. The latest consuming customer has bigger R. F represents frequency, which refers to the number of transactions in a particular period and M represents monetary, which refers to consumption money amount in a particular period. Thus, RFM method has been known to be a very effective model for customer segmentation. In this study, using a normalized value of the RFM variables, SOM cluster analysis was performed. SOM is regarded as one of the most distinguished artificial neural network models in the unsupervised learning tool space. It is a popular tool for clustering and visualization of high dimensional data in such a way that similar items are grouped spatially close to one another. In particular, it has been successfully applied in various technical fields for finding patterns. In our research, the procedure tries to find sales patterns by analyzing product sales records with Recency, Frequency and Monetary values. And to suggest a business strategy, we conduct the decision tree based on SOM results. To validate the proposed procedure in this study, we adopted the M-mart data collected between 2014.01.01~2014.12.31. Each product get the value of R, F, M, and they are clustered by 9 using SOM. And we also performed three tests using the weekday data, weekend data, whole data in order to analyze the sales pattern change. In order to propose the strategy of each cluster, we examine the criteria of product clustering. The clusters through the SOM can be explained by the characteristics of these clusters of decision trees. As a result, we can suggest the inventory management strategy of each 9 clusters through the suggested procedures of the study. The highest of all three value(R, F, M) cluster's products need to have high level of the inventory as well as to be disposed in a place where it can be increasing customer's path. In contrast, the lowest of all three value(R, F, M) cluster's products need to have low level of inventory as well as to be disposed in a place where visibility is low. The highest R value cluster's products is usually new releases products, and need to be placed on the front of the store. And, manager should decrease inventory levels gradually in the highest F value cluster's products purchased in the past. Because, we assume that cluster has lower R value and the M value than the average value of good. And it can be deduced that product are sold poorly in recent days and total sales also will be lower than the frequency. The procedure presented in this study is expected to contribute to raising the profitability of the retail store. The paper is organized as follows. The second chapter briefly reviews the literature related to this study. The third chapter suggests procedures for research proposals, and the fourth chapter applied suggested procedure using the actual product sales data. Finally, the fifth chapter described the conclusion of the study and further research.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.69-92
• /
• 2015

The explosion of social media data has led to apply text-mining techniques to analyze big social media data in a more rigorous manner. Even if social media text analysis algorithms were improved, previous approaches to social media text analysis have some limitations. In the field of sentiment analysis of social media written in Korean, there are two typical approaches. One is the linguistic approach using machine learning, which is the most common approach. Some studies have been conducted by adding grammatical factors to feature sets for training classification model. The other approach adopts the semantic analysis method to sentiment analysis, but this approach is mainly applied to English texts. To overcome these limitations, this study applies the Word2Vec algorithm which is an extension of the neural network algorithms to deal with more extensive semantic features that were underestimated in existing sentiment analysis. The result from adopting the Word2Vec algorithm is compared to the result from co-occurrence analysis to identify the difference between two approaches. The results show that the distribution related word extracted by Word2Vec algorithm in that the words represent some emotion about the keyword used are three times more than extracted by co-occurrence analysis. The reason of the difference between two results comes from Word2Vec's semantic features vectorization. Therefore, it is possible to say that Word2Vec algorithm is able to catch the hidden related words which have not been found in traditional analysis. In addition, Part Of Speech (POS) tagging for Korean is used to detect adjective as "emotional word" in Korean. In addition, the emotion words extracted from the text are converted into word vector by the Word2Vec algorithm to find related words. Among these related words, noun words are selected because each word of them would have causal relationship with "emotional word" in the sentence. The process of extracting these trigger factor of emotional word is named "Emotion Trigger" in this study. As a case study, the datasets used in the study are collected by searching using three keywords: professor, prosecutor, and doctor in that these keywords contain rich public emotion and opinion. Advanced data collecting was conducted to select secondary keywords for data gathering. The secondary keywords for each keyword used to gather the data to be used in actual analysis are followed: Professor (sexual assault, misappropriation of research money, recruitment irregularities, polifessor), Doctor (Shin hae-chul sky hospital, drinking and plastic surgery, rebate) Prosecutor (lewd behavior, sponsor). The size of the text data is about to 100,000(Professor: 25720, Doctor: 35110, Prosecutor: 43225) and the data are gathered from news, blog, and twitter to reflect various level of public emotion into text data analysis. As a visualization method, Gephi (http://gephi.github.io) was used and every program used in text processing and analysis are java coding. The contributions of this study are as follows: First, different approaches for sentiment analysis are integrated to overcome the limitations of existing approaches. Secondly, finding Emotion Trigger can detect the hidden connections to public emotion which existing method cannot detect. Finally, the approach used in this study could be generalized regardless of types of text data. The limitation of this study is that it is hard to say the word extracted by Emotion Trigger processing has significantly causal relationship with emotional word in a sentence. The future study will be conducted to clarify the causal relationship between emotional words and the words extracted by Emotion Trigger by comparing with the relationships manually tagged. Furthermore, the text data used in Emotion Trigger are twitter, so the data have a number of distinct features which we did not deal with in this study. These features will be considered in further study.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.167-181
• /
• 2018

Over the past decade, deep learning has been in spotlight among various machine learning algorithms. In particular, CNN(Convolutional Neural Network), which is known as the effective solution for recognizing and classifying images or voices, has been popularly applied to classification and prediction problems. In this study, we investigate the way to apply CNN in business problem solving. Specifically, this study propose to apply CNN to stock market prediction, one of the most challenging tasks in the machine learning research. As mentioned, CNN has strength in interpreting images. Thus, the model proposed in this study adopts CNN as the binary classifier that predicts stock market direction (upward or downward) by using time series graphs as its inputs. That is, our proposal is to build a machine learning algorithm that mimics an experts called 'technical analysts' who examine the graph of past price movement, and predict future financial price movements. Our proposed model named 'CNN-FG(Convolutional Neural Network using Fluctuation Graph)' consists of five steps. In the first step, it divides the dataset into the intervals of 5 days. And then, it creates time series graphs for the divided dataset in step 2. The size of the image in which the graph is drawn is $40(pixels){\times}40(pixels)$, and the graph of each independent variable was drawn using different colors. In step 3, the model converts the images into the matrices. Each image is converted into the combination of three matrices in order to express the value of the color using R(red), G(green), and B(blue) scale. In the next step, it splits the dataset of the graph images into training and validation datasets. We used 80% of the total dataset as the training dataset, and the remaining 20% as the validation dataset. And then, CNN classifiers are trained using the images of training dataset in the final step. Regarding the parameters of CNN-FG, we adopted two convolution filters ($5{\times}5{\times}6$ and $5{\times}5{\times}9$) in the convolution layer. In the pooling layer, $2{\times}2$ max pooling filter was used. The numbers of the nodes in two hidden layers were set to, respectively, 900 and 32, and the number of the nodes in the output layer was set to 2(one is for the prediction of upward trend, and the other one is for downward trend). Activation functions for the convolution layer and the hidden layer were set to ReLU(Rectified Linear Unit), and one for the output layer set to Softmax function. To validate our model - CNN-FG, we applied it to the prediction of KOSPI200 for 2,026 days in eight years (from 2009 to 2016). To match the proportions of the two groups in the independent variable (i.e. tomorrow's stock market movement), we selected 1,950 samples by applying random sampling. Finally, we built the training dataset using 80% of the total dataset (1,560 samples), and the validation dataset using 20% (390 samples). The dependent variables of the experimental dataset included twelve technical indicators popularly been used in the previous studies. They include Stochastic %K, Stochastic %D, Momentum, ROC(rate of change), LW %R(Larry William's %R), A/D oscillator(accumulation/distribution oscillator), OSCP(price oscillator), CCI(commodity channel index), and so on. To confirm the superiority of CNN-FG, we compared its prediction accuracy with the ones of other classification models. Experimental results showed that CNN-FG outperforms LOGIT(logistic regression), ANN(artificial neural network), and SVM(support vector machine) with the statistical significance. These empirical results imply that converting time series business data into graphs and building CNN-based classification models using these graphs can be effective from the perspective of prediction accuracy. Thus, this paper sheds a light on how to apply deep learning techniques to the domain of business problem solving.