• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.37-51
• /
• 2015

Due to the development of internet technology and the rapid increase of internet data, various studies are actively conducted on how to use and analyze internet data for various purposes. In particular, in recent years, a number of studies have been performed on the applications of text mining techniques in order to overcome the limitations of the current application of structured data. Especially, there are various studies on sentimental analysis to score opinions based on the distribution of polarity such as positivity or negativity of vocabularies or sentences of the texts in documents. As a part of such studies, this study tries to predict ups and downs of stock prices of companies by performing sentimental analysis on news contexts of the particular companies in the Internet. A variety of news on companies is produced online by different economic agents, and it is diffused quickly and accessed easily in the Internet. So, based on inefficient market hypothesis, we can expect that news information of an individual company can be used to predict the fluctuations of stock prices of the company if we apply proper data analysis techniques. However, as the areas of corporate management activity are different, an analysis considering characteristics of each company is required in the analysis of text data based on machine-learning. In addition, since the news including positive or negative information on certain companies have various impacts on other companies or industry fields, an analysis for the prediction of the stock price of each company is necessary. Therefore, this study attempted to predict changes in the stock prices of the individual companies that applied a sentimental analysis of the online news data. Accordingly, this study chose top company in KOSPI 200 as the subjects of the analysis, and collected and analyzed online news data by each company produced for two years on a representative domestic search portal service, Naver. In addition, considering the differences in the meanings of vocabularies for each of the certain economic subjects, it aims to improve performance by building up a lexicon for each individual company and applying that to an analysis. As a result of the analysis, the accuracy of the prediction by each company are different, and the prediction accurate rate turned out to be 56% on average. Comparing the accuracy of the prediction of stock prices on industry sectors, 'energy/chemical', 'consumer goods for living' and 'consumer discretionary' showed a relatively higher accuracy of the prediction of stock prices than other industries, while it was found that the sectors such as 'information technology' and 'shipbuilding/transportation' industry had lower accuracy of prediction. The number of the representative companies in each industry collected was five each, so it is somewhat difficult to generalize, but it could be confirmed that there was a difference in the accuracy of the prediction of stock prices depending on industry sectors. In addition, at the individual company level, the companies such as 'Kangwon Land', 'KT & G' and 'SK Innovation' showed a relatively higher prediction accuracy as compared to other companies, while it showed that the companies such as 'Young Poong', 'LG', 'Samsung Life Insurance', and 'Doosan' had a low prediction accuracy of less than 50%. In this paper, we performed an analysis of the share price performance relative to the prediction of individual companies through the vocabulary of pre-built company to take advantage of the online news information. In this paper, we aim to improve performance of the stock prices prediction, applying online news information, through the stock price prediction of individual companies. Based on this, in the future, it will be possible to find ways to increase the stock price prediction accuracy by complementing the problem of unnecessary words that are added to the sentiment dictionary.

• Journal of Korean Society of Forest Science
• /
• v.77 no.4
• /
• pp.429-444
• /
• 1988

Considering the recent trent toward the development of multiple-use of forest trees, investigations for comprehensive information on these young stands of Hinoki cypress are necessary for rational forest management. From this point of view, 83 sample trees were selected and cut down from 23-ear old stands of Hinoki cypress at Changsung-gun, Chonnam-do. Various stem growth factors of felled trees were measured and canonical correlaton analysis, principal component analysis and factor analysis were applied to investigate the stem growth characteristics, relationships among stem growth factors, and to get potential information and comprehensive information. The results are as follows ; Canonical correlation coefficient between stem volume and quality growth factor was 0.9877. Coefficient of canonical variates showed that DBH among diameter growth factors and height among height growth factors had important effects on stem volume. From the analysis of relationship between stem-volume and canonical variates, which were linearly combined DBH with height as one set, DBH had greater influence on volume growth than height. The 1st-2nd principal components here adopted to fit the effective value of 85% from the pincipal component analysis for 12 stem growth factors. The result showed that the 1st-2nd principal component had cumulative contribution rate of 88.10%. The 1st and the 2nd principal components were interpreted as "size factor" and "shape factor", respectively. From summed proportion of the efficient principal component fur each variate, information of variates except crown diameter, clear length and form height explained more than 87%. Two common factors were set by the eigen value obtained from SMC (squared multiple correlation) of diagonal elements of canonical matrix. There were 2 latent factors, $f_1$ and $f_2$. The former way interpreted as nature of diameter growth system. In inherent phenomenon of 12 growth factor, communalities except clear length and crown diameter had great explanatory poorer of 78.62-98.30%. Eighty three sample trees could he classified into 5 stem types as follows ; medium type within a radius of ${\pm}1$ standard deviation of factor scores, uniformity type in diameter and height growth in the 1st quadrant, slim type in the 2nd quadrant, dwarfish type in the 3rd quadrant, and fall-holed type in the 4 th quadrant.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.14 no.2
• /
• pp.77-82
• /
• 2010

Purpose: As PET/CT come into wide use, it caused increasing of expose in clinical use. Therefore, Korea Food and Drug Administration issued Patient DRL (Diagnostic Reference Level) in CT scan. In this study, to build the basis of patient dose reduction, we analyzed effective dose in transmission scan with CT scan. Materials and Methods: From February, 2010 to March 180 patients (age: $55{\pm}16$, weight: $61.0{\pm}10.4$ kg) who examined $^{18}F$-FDG PET/CT in Asan Medical Center. Biograph Truepoint 40 (SIEMENS, GERMANY), Biograph Sensation 16 (SIEMENS, GERMANY) and Discovery STe8 (GE healthcare, USA) were used in this study. Per each male and female average of 30 patients doses were analyzed by one. Automatic exposure control system for controlling the dose can affect the largest by a patient's body weight less than 50 kg, 50-60 kg less, 60 kg more than the average of the three groups were divided doses. We compared that measured value of CT-expo v1.7 and ImPACT v1.0. The relationship between body weight and the effective dose were analyzed. Results: When using CT-Expo V1.7, effective dose with BIO40, BIO16 and DSTe8 respectably were $6.46{\pm}1.18$ mSv, $9.36{\pm}1.96 $mSv and $9.36{\pm}1.96$ mSv for 30 male patients respectably $6.29{\pm}0.97$ mSv, $10.02{\pm}2.42$ mSv and $9.05{\pm}2.27$ mSv for 30 female patients respectably. When using ImPACT v1.0, effective dose with BIO40, BIO16 and DSTe8 respectably were $6.54{\pm}1.21$ mSv, $8.36{\pm}1.69$ mSv and $9.74{\pm}2.55$Sv for 30 male patients respectably $5.87{\pm}1.09$ mSv, $8.43{\pm}1.89$ mSv and $9.19{\pm}2.29$ mSv for female patients respectably. When divided three groups which were under 50 kg, 50~60 kg and over 60 kg respectably were 6.27 mSv, 7.67 mSv and 9.33 mSv respectably using CT-Expo V1.7, 5.62 mSv, 7.22 mSv and 8.91 mSv respectably using ImPACT v1.0. Weight and the effective dose coefficient analysis showed a very strong positive correlation(r=743, r=0.693). Conclusion: Using such a dose evaluation programs, easier to predict and evaluate the effective dose possible without performing phantom study and such dose evaluation programs could be used to collect basic data for CT dose management.

• Asia pacific journal of information systems
• /
• v.17 no.4
• /
• pp.31-59
• /
• 2007

We frequently use search engines to find relevant information in the Web but still end up with too much information. In order to solve this problem of information overload, ranking algorithms have been applied to various domains. As more information will be available in the future, effectively and efficiently ranking search results will become more critical. In this paper, we propose a ranking algorithm for the Semantic Web resources, specifically RDF resources. Traditionally, the importance of a particular Web page is estimated based on the number of key words found in the page, which is subject to manipulation. In contrast, link analysis methods such as Google's PageRank capitalize on the information which is inherent in the link structure of the Web graph. PageRank considers a certain page highly important if it is referred to by many other pages. The degree of the importance also increases if the importance of the referring pages is high. Kleinberg's algorithm is another link-structure based ranking algorithm for Web pages. Unlike PageRank, Kleinberg's algorithm utilizes two kinds of scores: the authority score and the hub score. If a page has a high authority score, it is an authority on a given topic and many pages refer to it. A page with a high hub score links to many authoritative pages. As mentioned above, the link-structure based ranking method has been playing an essential role in World Wide Web(WWW), and nowadays, many people recognize the effectiveness and efficiency of it. On the other hand, as Resource Description Framework(RDF) data model forms the foundation of the Semantic Web, any information in the Semantic Web can be expressed with RDF graph, making the ranking algorithm for RDF knowledge bases greatly important. The RDF graph consists of nodes and directional links similar to the Web graph. As a result, the link-structure based ranking method seems to be highly applicable to ranking the Semantic Web resources. However, the information space of the Semantic Web is more complex than that of WWW. For instance, WWW can be considered as one huge class, i.e., a collection of Web pages, which has only a recursive property, i.e., a 'refers to' property corresponding to the hyperlinks. However, the Semantic Web encompasses various kinds of classes and properties, and consequently, ranking methods used in WWW should be modified to reflect the complexity of the information space in the Semantic Web. Previous research addressed the ranking problem of query results retrieved from RDF knowledge bases. Mukherjea and Bamba modified Kleinberg's algorithm in order to apply their algorithm to rank the Semantic Web resources. They defined the objectivity score and the subjectivity score of a resource, which correspond to the authority score and the hub score of Kleinberg's, respectively. They concentrated on the diversity of properties and introduced property weights to control the influence of a resource on another resource depending on the characteristic of the property linking the two resources. A node with a high objectivity score becomes the object of many RDF triples, and a node with a high subjectivity score becomes the subject of many RDF triples. They developed several kinds of Semantic Web systems in order to validate their technique and showed some experimental results verifying the applicability of their method to the Semantic Web. Despite their efforts, however, there remained some limitations which they reported in their paper. First, their algorithm is useful only when a Semantic Web system represents most of the knowledge pertaining to a certain domain. In other words, the ratio of links to nodes should be high, or overall resources should be described in detail, to a certain degree for their algorithm to properly work. Second, a Tightly-Knit Community(TKC) effect, the phenomenon that pages which are less important but yet densely connected have higher scores than the ones that are more important but sparsely connected, remains as problematic. Third, a resource may have a high score, not because it is actually important, but simply because it is very common and as a consequence it has many links pointing to it. In this paper, we examine such ranking problems from a novel perspective and propose a new algorithm which can solve the problems under the previous studies. Our proposed method is based on a class-oriented approach. In contrast to the predicate-oriented approach entertained by the previous research, a user, under our approach, determines the weights of a property by comparing its relative significance to the other properties when evaluating the importance of resources in a specific class. This approach stems from the idea that most queries are supposed to find resources belonging to the same class in the Semantic Web, which consists of many heterogeneous classes in RDF Schema. This approach closely reflects the way that people, in the real world, evaluate something, and will turn out to be superior to the predicate-oriented approach for the Semantic Web. Our proposed algorithm can resolve the TKC(Tightly Knit Community) effect, and further can shed lights on other limitations posed by the previous research. In addition, we propose two ways to incorporate data-type properties which have not been employed even in the case when they have some significance on the resource importance. We designed an experiment to show the effectiveness of our proposed algorithm and the validity of ranking results, which was not tried ever in previous research. We also conducted a comprehensive mathematical analysis, which was overlooked in previous research. The mathematical analysis enabled us to simplify the calculation procedure. Finally, we summarize our experimental results and discuss further research issues.

• Quality Improvement in Health Care
• /
• v.7 no.2
• /
• pp.138-155
• /
• 2000

Background: Factors related to waiting and staying time for patient care in emergency care center (ECC) were examined during 1 month from Apr. 1 to Apr. 30, 1997 at an ECC of Yeungnam university hospital in Taegu metropolitan city, to obtain the baseline data on the strategy of effective management of emergency patients. Method: The study subjects consisted of the 1,742 patients who visited at ECC and the data were obtained from the medical records of ECC and direct surveys. Results: The mean interval between ECC admission time and initial care time by each ECC duty residents was 83.1 minutes for male patients and 84.9 minutes for female patients, and mean ECC staying time (time interval between admission and final disposition from ECC) was 718.0 minutes in men and 670.5 minutes in women. As the results, the mean staying time in ECC was higher in older age, and especially the both of initial care time and staying time were highest in patients of medical aid, and shortest in patients of worker's accident compensation insurance. The on admission or not, previously endotracheal-intubation state of patient. The ECC staying ti initial care time was much more delayed in patients of not having previous medical records and the ECC staying time was higher in referred patients from out-patient department, in transferred patients from the other hospitals and patients having previous records, and in patients partly used the order-communicating system. The factors associated with the initial care time were the numbers of ECC patients and the existence of any true emergent patients, being cardiopulmonary resuscitation (CPR) statusme was much more longer in patients of drug intoxication, in CPR patients, in medical department patients, in transfused patients and in patients related to 3 or more departments. And according to the numbers of duty internships, the ECC staying time for four internships was more longer than for five internships and after admission ordering was done, also-more longer in status being of no available beds. As above mentioned results, the factors for the ECC staying time were thought to be statistically significant (P<0.01) according to the patient's age and the laboratory orders and the X-ray films checked. And also the factor for the ECC staying time were thought to be statistically significant (P<0.01) according to the status being of no available beds, the laboratory orders and/or the special laboratory orders, the X-ray films checked, final disposing department, transferred to other hospital or not, home medication or not, admission or not, the grades of beds, the year grades of residents, the causes of ECC visit, the being CPR status on admission or not, the surgical operation or not, being known personells in our hospital. Conclution: Authors concluded that the relieving method of long-staying time in ECC was being establishing the legally proved apparatus which could differentiate the true emergency or non-emergency patients, and that the methods of shortening ECC staying time were doing definitely necessary laboratory orders and managing beds more flexibly to admit for ECC patients and finally this methods were thought to be a method of unloading for ECC personnels and improving the quality of care in emergency patients.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.59-77
• /
• 2012

This study focuses on predicting which firms will increase capital by issuing new stocks in the near future. Many stakeholders, including banks, credit rating agencies and investors, performs a variety of analyses for firms' growth, profitability, stability, activity, productivity, etc., and regularly report the firms' financial analysis indices. In the paper, we develop predictive models for rights issues using these financial analysis indices and data mining techniques. This study approaches to building the predictive models from the perspective of two different analyses. The first is the analysis period. We divide the analysis period into before and after the IMF financial crisis, and examine whether there is the difference between the two periods. The second is the prediction time. In order to predict when firms increase capital by issuing new stocks, the prediction time is categorized as one year, two years and three years later. Therefore Total six prediction models are developed and analyzed. In this paper, we employ the decision tree technique to build the prediction models for rights issues. The decision tree is the most widely used prediction method which builds decision trees to label or categorize cases into a set of known classes. In contrast to neural networks, logistic regression and SVM, decision tree techniques are well suited for high-dimensional applications and have strong explanation capabilities. There are well-known decision tree induction algorithms such as CHAID, CART, QUEST, C5.0, etc. Among them, we use C5.0 algorithm which is the most recently developed algorithm and yields performance better than other algorithms. We obtained data for the rights issue and financial analysis from TS2000 of Korea Listed Companies Association. A record of financial analysis data is consisted of 89 variables which include 9 growth indices, 30 profitability indices, 23 stability indices, 6 activity indices and 8 productivity indices. For the model building and test, we used 10,925 financial analysis data of total 658 listed firms. PASW Modeler 13 was used to build C5.0 decision trees for the six prediction models. Total 84 variables among financial analysis data are selected as the input variables of each model, and the rights issue status (issued or not issued) is defined as the output variable. To develop prediction models using C5.0 node (Node Options: Output type = Rule set, Use boosting = false, Cross-validate = false, Mode = Simple, Favor = Generality), we used 60% of data for model building and 40% of data for model test. The results of experimental analysis show that the prediction accuracies of data after the IMF financial crisis (59.04% to 60.43%) are about 10 percent higher than ones before IMF financial crisis (68.78% to 71.41%). These results indicate that since the IMF financial crisis, the reliability of financial analysis indices has increased and the firm intention of rights issue has been more obvious. The experiment results also show that the stability-related indices have a major impact on conducting rights issue in the case of short-term prediction. On the other hand, the long-term prediction of conducting rights issue is affected by financial analysis indices on profitability, stability, activity and productivity. All the prediction models include the industry code as one of significant variables. This means that companies in different types of industries show their different types of patterns for rights issue. We conclude that it is desirable for stakeholders to take into account stability-related indices and more various financial analysis indices for short-term prediction and long-term prediction, respectively. The current study has several limitations. First, we need to compare the differences in accuracy by using different data mining techniques such as neural networks, logistic regression and SVM. Second, we are required to develop and to evaluate new prediction models including variables which research in the theory of capital structure has mentioned about the relevance to rights issue.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.59-83
• /
• 2018

With the increasing importance of sentiment analysis to grasp the needs of customers and the public, various types of deep learning models have been actively applied to English texts. In the sentiment analysis of English texts by deep learning, natural language sentences included in training and test datasets are usually converted into sequences of word vectors before being entered into the deep learning models. In this case, word vectors generally refer to vector representations of words obtained through splitting a sentence by space characters. There are several ways to derive word vectors, one of which is Word2Vec used for producing the 300 dimensional Google word vectors from about 100 billion words of Google News data. They have been widely used in the studies of sentiment analysis of reviews from various fields such as restaurants, movies, laptops, cameras, etc. Unlike English, morpheme plays an essential role in sentiment analysis and sentence structure analysis in Korean, which is a typical agglutinative language with developed postpositions and endings. A morpheme can be defined as the smallest meaningful unit of a language, and a word consists of one or more morphemes. For example, for a word '예쁘고', the morphemes are '예쁘(= adjective)' and '고(=connective ending)'. Reflecting the significance of Korean morphemes, it seems reasonable to adopt the morphemes as a basic unit in Korean sentiment analysis. Therefore, in this study, we use 'morpheme vector' as an input to a deep learning model rather than 'word vector' which is mainly used in English text. The morpheme vector refers to a vector representation for the morpheme and can be derived by applying an existent word vector derivation mechanism to the sentences divided into constituent morphemes. By the way, here come some questions as follows. What is the desirable range of POS(Part-Of-Speech) tags when deriving morpheme vectors for improving the classification accuracy of a deep learning model? Is it proper to apply a typical word vector model which primarily relies on the form of words to Korean with a high homonym ratio? Will the text preprocessing such as correcting spelling or spacing errors affect the classification accuracy, especially when drawing morpheme vectors from Korean product reviews with a lot of grammatical mistakes and variations? We seek to find empirical answers to these fundamental issues, which may be encountered first when applying various deep learning models to Korean texts. As a starting point, we summarized these issues as three central research questions as follows. First, which is better effective, to use morpheme vectors from grammatically correct texts of other domain than the analysis target, or to use morpheme vectors from considerably ungrammatical texts of the same domain, as the initial input of a deep learning model? Second, what is an appropriate morpheme vector derivation method for Korean regarding the range of POS tags, homonym, text preprocessing, minimum frequency? Third, can we get a satisfactory level of classification accuracy when applying deep learning to Korean sentiment analysis? As an approach to these research questions, we generate various types of morpheme vectors reflecting the research questions and then compare the classification accuracy through a non-static CNN(Convolutional Neural Network) model taking in the morpheme vectors. As for training and test datasets, Naver Shopping's 17,260 cosmetics product reviews are used. To derive morpheme vectors, we use data from the same domain as the target one and data from other domain; Naver shopping's about 2 million cosmetics product reviews and 520,000 Naver News data arguably corresponding to Google's News data. The six primary sets of morpheme vectors constructed in this study differ in terms of the following three criteria. First, they come from two types of data source; Naver news of high grammatical correctness and Naver shopping's cosmetics product reviews of low grammatical correctness. Second, they are distinguished in the degree of data preprocessing, namely, only splitting sentences or up to additional spelling and spacing corrections after sentence separation. Third, they vary concerning the form of input fed into a word vector model; whether the morphemes themselves are entered into a word vector model or with their POS tags attached. The morpheme vectors further vary depending on the consideration range of POS tags, the minimum frequency of morphemes included, and the random initialization range. All morpheme vectors are derived through CBOW(Continuous Bag-Of-Words) model with the context window 5 and the vector dimension 300. It seems that utilizing the same domain text even with a lower degree of grammatical correctness, performing spelling and spacing corrections as well as sentence splitting, and incorporating morphemes of any POS tags including incomprehensible category lead to the better classification accuracy. The POS tag attachment, which is devised for the high proportion of homonyms in Korean, and the minimum frequency standard for the morpheme to be included seem not to have any definite influence on the classification accuracy.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.33-56
• /
• 2017

As Internet usage is becoming more common worldwide and smartphone become necessity in daily life, technologies and applications related to mobile Internet are developing rapidly. The results of the Internet usage patterns of consumers around the world imply that there are many potential new business opportunities for mobile Internet technologies and applications. The location-based service (LBS) is a service based on the location information of the mobile device. LBS has recently gotten much attention among many mobile applications and various LBSs are rapidly developing in numerous categories. However, even with the development of LBS related technologies and services, there is still a lack of empirical research on the intention to use LBS. The application of previous researches is limited because they focused on the effect of one particular factor and had not shown the direct relationship on the intention to use LBS. Therefore, this study presents a research model of factors that affect the intention to use and actual use of LBS whose market is expected to grow rapidly, and tested it by conducting a questionnaire survey of 330 users. The results of data analysis showed that service customization, service quality, and personal innovativeness have a positive effect on the intention to use LBS and the intention to use LBS has a positive effect on the actual use of LBS. These results implies that LBS providers can enhance the user's intention to use LBS by offering service customization through the provision of various LBSs based on users' needs, improving information service qualities such as accuracy, timeliness, sensitivity, and reliability, and encouraging personal innovativeness. However, privacy concerns in the context of LBS are not significantly affected by service customization and personal innovativeness and privacy concerns do not significantly affect the intention to use LBS. In fact, the information related to users' location collected by LBS is less sensitive when compared with the information that is used to perform financial transactions. Therefore, such outcomes on privacy concern are revealed. In addition, the advantages of using LBS are more important than the sensitivity of privacy protection to the users who use LBS than to the users who use information systems such as electronic commerce that involves financial transactions. Therefore, LBS are recommended to be treated differently from other information systems. This study is significant in the theoretical point of contribution that it proposed factors affecting the intention to use LBS in a multi-faceted perspective, proved the proposed research model empirically, brought new insights on LBS, and broadens understanding of the intention to use and actual use of LBS. Also, the empirical results of the customization of LBS affecting the user's intention to use the LBS suggest that the provision of customized LBS services based on the usage data analysis through utilizing technologies such as artificial intelligence can enhance the user's intention to use. In a practical point of view, the results of this study are expected to help LBS providers to develop a competitive strategy for responding to LBS users effectively and lead to the LBS market grows. We expect that there will be differences in using LBSs depending on some factors such as types of LBS, whether it is free of charge or not, privacy policies related to LBS, the levels of reliability related application and technology, the frequency of use, etc. Therefore, if we can make comparative studies with those factors, it will contribute to the development of the research areas of LBS. We hope this study can inspire many researchers and initiate many great researches in LBS fields.