• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.43-57
• /
• 2012

To enhance the competitive advantage in a constantly changing business environment, an enterprise management must make the right decision in many business activities based on both internal and external information. Thus, providing accurate information plays a prominent role in management's decision making. Intuitively, historical data can provide a feasible estimate through the forecasting models. Therefore, if the service department can estimate the service quantity for the next period, the service department can then effectively control the inventory of service related resources such as human, parts, and other facilities. In addition, the production department can make load map for improving its product quality. Therefore, obtaining an accurate service forecast most likely appears to be critical to manufacturing companies. Numerous investigations addressing this problem have generally employed statistical methods, such as regression or autoregressive and moving average simulation. However, these methods are only efficient for data with are seasonal or cyclical. If the data are influenced by the special characteristics of product, they are not feasible. In our research, we propose a forecasting framework that predicts service demand of manufacturing organization by combining Case-based reasoning (CBR) and leveraging an unsupervised artificial neural network based clustering analysis (i.e., Self-Organizing Maps; SOM). We believe that this is one of the first attempts at applying unsupervised artificial neural network-based machine-learning techniques in the service forecasting domain. Our proposed approach has several appealing features : (1) We applied CBR and SOM in a new forecasting domain such as service demand forecasting. (2) We proposed our combined approach between CBR and SOM in order to overcome limitations of traditional statistical forecasting methods and We have developed a service forecasting tool based on the proposed approach using an unsupervised artificial neural network and Case-based reasoning. In this research, we conducted an empirical study on a real digital TV manufacturer (i.e., Company A). In addition, we have empirically evaluated the proposed approach and tool using real sales and service related data from digital TV manufacturer. In our empirical experiments, we intend to explore the performance of our proposed service forecasting framework when compared to the performances predicted by other two service forecasting methods; one is traditional CBR based forecasting model and the other is the existing service forecasting model used by Company A. We ran each service forecasting 144 times; each time, input data were randomly sampled for each service forecasting framework. To evaluate accuracy of forecasting results, we used Mean Absolute Percentage Error (MAPE) as primary performance measure in our experiments. We conducted one-way ANOVA test with the 144 measurements of MAPE for three different service forecasting approaches. For example, the F-ratio of MAPE for three different service forecasting approaches is 67.25 and the p-value is 0.000. This means that the difference between the MAPE of the three different service forecasting approaches is significant at the level of 0.000. Since there is a significant difference among the different service forecasting approaches, we conducted Tukey's HSD post hoc test to determine exactly which means of MAPE are significantly different from which other ones. In terms of MAPE, Tukey's HSD post hoc test grouped the three different service forecasting approaches into three different subsets in the following order: our proposed approach > traditional CBR-based service forecasting approach > the existing forecasting approach used by Company A. Consequently, our empirical experiments show that our proposed approach outperformed the traditional CBR based forecasting model and the existing service forecasting model used by Company A. The rest of this paper is organized as follows. Section 2 provides some research background information such as summary of CBR and SOM. Section 3 presents a hybrid service forecasting framework based on Case-based Reasoning and Self-Organizing Maps, while the empirical evaluation results are summarized in Section 4. Conclusion and future research directions are finally discussed in Section 5.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.123-139
• /
• 2019

The job classification system of major job sites differs from site to site and is different from the job classification system of the 'SQF(Sectoral Qualifications Framework)' proposed by the SW field. Therefore, a new job classification system is needed for SW companies, SW job seekers, and job sites to understand. The purpose of this study is to establish a standard job classification system that reflects market demand by analyzing SQF based on job offer information of major job sites and the NCS(National Competency Standards). For this purpose, the association analysis between occupations of major job sites is conducted and the association rule between SQF and occupation is conducted to derive the association rule between occupations. Using this association rule, we proposed an intelligent job classification system based on data mapping the job classification system of major job sites and SQF and job classification system. First, major job sites are selected to obtain information on the job classification system of the SW market. Then We identify ways to collect job information from each site and collect data through open API. Focusing on the relationship between the data, filtering only the job information posted on each job site at the same time, other job information is deleted. Next, we will map the job classification system between job sites using the association rules derived from the association analysis. We will complete the mapping between these market segments, discuss with the experts, further map the SQF, and finally propose a new job classification system. As a result, more than 30,000 job listings were collected in XML format using open API in 'WORKNET,' 'JOBKOREA,' and 'saramin', which are the main job sites in Korea. After filtering out about 900 job postings simultaneously posted on multiple job sites, 800 association rules were derived by applying the Apriori algorithm, which is a frequent pattern mining. Based on 800 related rules, the job classification system of WORKNET, JOBKOREA, and saramin and the SQF job classification system were mapped and classified into 1st and 4th stages. In the new job taxonomy, the first primary class, IT consulting, computer system, network, and security related job system, consisted of three secondary classifications, five tertiary classifications, and five fourth classifications. The second primary classification, the database and the job system related to system operation, consisted of three secondary classifications, three tertiary classifications, and four fourth classifications. The third primary category, Web Planning, Web Programming, Web Design, and Game, was composed of four secondary classifications, nine tertiary classifications, and two fourth classifications. The last primary classification, job systems related to ICT management, computer and communication engineering technology, consisted of three secondary classifications and six tertiary classifications. In particular, the new job classification system has a relatively flexible stage of classification, unlike other existing classification systems. WORKNET divides jobs into third categories, JOBKOREA divides jobs into second categories, and the subdivided jobs into keywords. saramin divided the job into the second classification, and the subdivided the job into keyword form. The newly proposed standard job classification system accepts some keyword-based jobs, and treats some product names as jobs. In the classification system, not only are jobs suspended in the second classification, but there are also jobs that are subdivided into the fourth classification. This reflected the idea that not all jobs could be broken down into the same steps. We also proposed a combination of rules and experts' opinions from market data collected and conducted associative analysis. Therefore, the newly proposed job classification system can be regarded as a data-based intelligent job classification system that reflects the market demand, unlike the existing job classification system. This study is meaningful in that it suggests a new job classification system that reflects market demand by attempting mapping between occupations based on data through the association analysis between occupations rather than intuition of some experts. However, this study has a limitation in that it cannot fully reflect the market demand that changes over time because the data collection point is temporary. As market demands change over time, including seasonal factors and major corporate public recruitment timings, continuous data monitoring and repeated experiments are needed to achieve more accurate matching. The results of this study can be used to suggest the direction of improvement of SQF in the SW industry in the future, and it is expected to be transferred to other industries with the experience of success in the SW industry.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.139-161
• /
• 2019

The utilization of the e-commerce market has become a common life style in today. It has become important part to know where and how to make reasonable purchases of good quality products for customers. This change in purchase psychology tends to make it difficult for customers to make purchasing decisions in vast amounts of information. In this case, the recommendation system has the effect of reducing the cost of information retrieval and improving the satisfaction by analyzing the purchasing behavior of the customer. Amazon and Netflix are considered to be the well-known examples of sales marketing using the recommendation system. In the case of Amazon, 60% of the recommendation is made by purchasing goods, and 35% of the sales increase was achieved. Netflix, on the other hand, found that 75% of movie recommendations were made using services. This personalization technique is considered to be one of the key strategies for one-to-one marketing that can be useful in online markets where salespeople do not exist. Recommendation techniques that are mainly used in recommendation systems today include collaborative filtering and content-based filtering. Furthermore, hybrid techniques and association rules that use these techniques in combination are also being used in various fields. Of these, collaborative filtering recommendation techniques are the most popular today. Collaborative filtering is a method of recommending products preferred by neighbors who have similar preferences or purchasing behavior, based on the assumption that users who have exhibited similar tendencies in purchasing or evaluating products in the past will have a similar tendency to other products. However, most of the existed systems are recommended only within the same category of products such as books and movies. This is because the recommendation system estimates the purchase satisfaction about new item which have never been bought yet using customer's purchase rating points of a similar commodity based on the transaction data. In addition, there is a problem about the reliability of purchase ratings used in the recommendation system. Reliability of customer purchase ratings is causing serious problems. In particular, 'Compensatory Review' refers to the intentional manipulation of a customer purchase rating by a company intervention. In fact, Amazon has been hard-pressed for these "compassionate reviews" since 2016 and has worked hard to reduce false information and increase credibility. The survey showed that the average rating for products with 'Compensated Review' was higher than those without 'Compensation Review'. And it turns out that 'Compensatory Review' is about 12 times less likely to give the lowest rating, and about 4 times less likely to leave a critical opinion. As such, customer purchase ratings are full of various noises. This problem is directly related to the performance of recommendation systems aimed at maximizing profits by attracting highly satisfied customers in most e-commerce transactions. In this study, we propose the possibility of using new indicators that can objectively substitute existing customer 's purchase ratings by using RFM multi-dimensional analysis technique to solve a series of problems. RFM multi-dimensional analysis technique is the most widely used analytical method in customer relationship management marketing(CRM), and is a data analysis method for selecting customers who are likely to purchase goods. As a result of verifying the actual purchase history data using the relevant index, the accuracy was as high as about 55%. This is a result of recommending a total of 4,386 different types of products that have never been bought before, thus the verification result means relatively high accuracy and utilization value. And this study suggests the possibility of general recommendation system that can be applied to various offline product data. If additional data is acquired in the future, the accuracy of the proposed recommendation system can be improved.

• Journal of Intelligence and Information Systems
• /
• v.19 no.4
• /
• pp.133-146
• /
• 2013

While the use of internet is routine nowadays, users receive and share information through a variety of media. Through the use of internet, information delivery media is diversifying from traditional media of one-way communication, such as newspaper, TV, and radio, into media of two-way communication. In contrast of traditional media, blogs enable individuals to directly upload and share news, which can be considered to have a differential speed of information diffusion than news media that convey information unilaterally. Therefore this Study focused on the difference between online news and social media blogs. Moreover, there are variations in the speed of information diffusion because that information closely related to one person boosts communications between individuals. We believe that users' standard of evaluation would change based on the types of information. As well, the speed of information diffusion would change based on the level of proximity. Therefore, the purpose of this study is to examine the differences in information diffusion based on the types of media. And then information is segmentalized and an examination is done to see how information diffusion differentiates based on the types of information. This study used the Bass diffusion model, which has been frequently used because this model has higher explanatory power than other models by explaining diffusion of market through innovation effect and imitation effect. Also this model has been applied a lot in other information diffusion related studies. The Bass diffusion model includes an innovation effect and an imitation effect. Innovation effect measures the early-stage impact, while the imitation effect measures the impact of word of mouth at the later stage. According to Mahajan et al. (2000), Innovation effect is emphasized by usefulness and ease-of-use, as well Imitation effect is emphasized by subjective norm and word-of-mouth. Also, according to Lee et al. (2011), Innovation effect is emphasized by mass communication. According to Moore and Benbasat (1996), Innovation effect is emphasized by relative advantage. Because Imitation effect is adopted by within-group influences and Innovation effects is adopted by product's or service's innovation. Therefore, ours study compared online news and social media blogs to examine the differences between media. We also choose different types of information including entertainment related information "Psy Gentelman", Current affair news "Earthquake in Sichuan, China", and product related information "Galaxy S4" in order to examine the variations on information diffusion. We considered that users' information proximity alters based on the types of information. Hence, we chose the three types of information mentioned above, which have different level of proximity from users' standpoint, in order to examine the flow of information diffusion. The first conclusion of this study is that different media has similar effect on information diffusion, even the types of media of information provider are different. Information diffusion has only been distinguished by a disparity between proximity of information. Second, information diffusions differ based on types of information. From the standpoint of users, product and entertainment related information has high imitation effect because of word of mouth. On the other hand, imitation effect dominates innovation effect on Current affair news. From the results of this study, the flow changes of information diffusion is examined and be applied to practical use. This study has some limitations, and those limitations would be able to provide opportunities and suggestions for future research. Presenting the difference of Information diffusion according to media and proximity has difficulties for generalization of theory due to small sample size. Therefore, if further studies adopt to a request for an increase of sample size and media diversity, difference of the information diffusion according to media type and information proximity could be understood more detailed.

• Journal of Intelligence and Information Systems
• /
• v.20 no.3
• /
• pp.45-58
• /
• 2014

The Korean Culture Contents spread out to Worldwide, because the Korean wave is sweeping in the world. The contents stand in the middle of the Korean wave that we are used it. Each country is ongoing to keep their Culture industry improve the national brand and High added value. Performing contents is important factor of arousal in the enterprise industry. To improve high arousal confidence of product and positive attitude by populace is one of important factor by advertiser. Culture contents is the same situation. If culture contents have trusted by everyone, they will give information their around to spread word-of-mouth. So, many researcher study to measure for person's arousal analysis by statistical survey, physiological response, body movement and facial expression. First, Statistical survey has a problem that it is not possible to measure each person's arousal real time and we cannot get good survey result after they watched contents. Second, physiological response should be checked with surround because experimenter sets sensors up their chair or space by each of them. Additionally it is difficult to handle provided amount of information with real time from their sensor. Third, body movement is easy to get their movement from camera but it difficult to set up experimental condition, to measure their body language and to get the meaning. Lastly, many researcher study facial expression. They measures facial expression, eye tracking and face posed. Most of previous studies about arousal and interest are mostly limited to reaction of just one person and they have problems with application multi audiences. They have a particular method, for example they need room light surround, but set limits only one person and special environment condition in the laboratory. Also, we need to measure arousal in the contents, but is difficult to define also it is not easy to collect reaction by audiences immediately. Many audience in the theater watch performance. We suggest the system to measure multi-audience's reaction with real-time during performance. We use difference image analysis method for multi-audience but it weaks a dark field. To overcome dark environment during recoding IR camera can get the photo from dark area. In addition we present Multi-Audience Engagement Index (MAEI) to calculate algorithm which sources from sound, audience' movement and eye tracking value. Algorithm calculates audience arousal from the mobile survey, sound value, audience' reaction and audience eye's tracking. It improves accuracy of Multi-Audience Engagement Index, we compare Multi-Audience Engagement Index with mobile survey. And then it send the result to reporting system and proposal an interested persons. Mobile surveys are easy, fast, and visitors' discomfort can be minimized. Also additional information can be provided mobile advantage. Mobile application to communicate with the database, real-time information on visitors' attitudes focused on the content stored. Database can provide different survey every time based on provided information. The example shown in the survey are as follows: Impressive scene, Satisfied, Touched, Interested, Didn't pay attention and so on. The suggested system is combine as 3 parts. The system consist of three parts, External Device, Server and Internal Device. External Device can record multi-Audience in the dark field with IR camera and sound signal. Also we use survey with mobile application and send the data to ERD Server DB. The Server part's contain contents' data, such as each scene's weights value, group audience weights index, camera control program, algorithm and calculate Multi-Audience Engagement Index. Internal Device presents Multi-Audience Engagement Index with Web UI, print and display field monitor. Our system is test-operated by the Mogencelab in the DMC display exhibition hall which is located in the Sangam Dong, Mapo Gu, Seoul. We have still gotten from visitor daily. If we find this system audience arousal factor with this will be very useful to create contents.

• Journal of Korea Water Resources Association
• /
• v.40 no.10
• /
• pp.769-781
• /
• 2007

Factor analysis has been usually employed in reducing quantity of data and summarizing information on a system or phenomenon. In this analysis methodology, variables are grouped into several factors by consideration of statistic characteristics, and the results are used for dropping variables which have lower weight than others. In this study, factor analysis was applied for extracting primary factors influencing multi-dam system operation in the Han River basin, where there are two multi-purpose dams such as Soyanggang Dam and Chungju Dam, and water has been supplied by integrating two dams in water use season. In order to fulfill factor analysis, first the variables related to two dams operation were gathered and divided into five groups (Soyanggang Dam: inflow, hydropower product, storage management, storage, and operation results of the past; Chungju Dam: inflow, hydropower product, water demand, storage, and operation results of the past). And then, considering statistic properties, in the gathered variables, some variables were chosen and grouped into five factors; hydrological condition, dam operation of the past, dam operation at normal season, water demand, and downstream dam operation. In order to check the appropriateness and applicability of factors, a multiple regression equation was newly constructed using factors as description variables, and those factors were compared with terms of objective function used in operation water resources optimally in a river basin. Reviewing the results through two check processes, it was revealed that the suggested approach provided satisfactory results. And, it was expected for extracted primary factors to be useful for making dam operation schedule considering the future situation and previous results.

• Journal of Environmental Impact Assessment
• /
• v.4 no.3
• /
• pp.41-48
• /
• 1995

In former times the protection of our environment didn't play an important role due to the fact that emissions and effluents were not considered as serious impacts. However, opinions and scientific measurements meanwhile confirmed that the impacts are more serious than expected. Thus measures to protect our earth has to be taken into consideration. A part of these measures in the Environmental Impact Assessment (EIA). One of the most important parts of the EIA is the collection of basic datas and the following evaluation. Experience out of the daily business of Gerling Consulting Group shows that the content of the EIA has to be revised and enlarged in certain fields. The historical development demonstrated that in areas in which the population and the industrial activities reached high concentration there is a high necessity to develop strict environmental laws and regulations. Maximum values of the concentration of hazardous materials were fixed concerning the emission into and water. Companies not following these regulations were punished. The total amount of environmental offences increased rapidly during the last decade, at least in Germany. During this development the public consciousness concerning environmental affairs increased as well in the industrialized countries. But it could clearly be seen that the development in the field of environmental protection went into the wrong direction. The technologies to protect the environment became more and more sophisticated and terms as: "state of the art" guided more and more to lower emissions, Filtertechnologies and wastewater treatment for example reached a high technical level-but all these sophisticated technologies has one and the same characteristic: they were end-of-the pipe solutions. A second effect was that this kind of environmental protection costs a lot of money. High investments are necessary to reduce the dust emission by another ppm! Could this be the correct way? In Germany the discussion started that the environmental laws reduce the attractivity to invest or to enlarge existing investments within the country. Other countries seem to be not so strict with controlling the environmental laws which means it's simply cheaper to produce in Portugal or Greece. Everybody however knows that this is not the correct way and does not solve the environmental problems. Meanwhile the general picture changes a little bit and we think it changes into the correct direction "End-of-the-pipe" solutions are still necessary but this word received a real negative touch and nobody wants to be brought into connection with this word received a real negative touch and nobody wants to be brought into connection with this word especially in connection with environmental management and safety. Modern actual environmental management starts in a different way. Thoughts about emissions start in the very beginning of the production, they start with the design of the product and modification of traditional modes of production. Basis of these ideas are detailed analyses of products and processes. Due to the above mentioned facts that the public environmental consciousness changed dramatically a continous environmental improvement of each single production plant has to be guarantied. This question is already an important question of the EIA. But it was never really checked in a wholistic approach. Environmental risks have to be taken into considerations during the execution of an EIA. This means that the environmental risks have to be reduced down to a capable risk-level. Environmental risks have to be considered within the phase of planning, during the operation of a plant and after shut down. The experience shows that most of the environmental relevant accidents were and caused by human fault. Even in highly protected plants the human risk-factor can not be excluded during evaluation of the risk-potential. Thus the approach of an EIA has to regard technical evaluations as well as organizational thoughts and the human factor. An environmental risk is a threat to the environment. An analysis of the risk concerning the organizational and human aspect however never was properly executed during an EIA. A possible solution could be to use an instrument as the actual EMAS (Environmental Management System) of the EC for more accurate evaluation of the impact to the environment during an EIA. Organizations or investors could demonstrate by an approved EMAS or even by showing their installment of EMAS that not only the technical level of the planned investment meets the requested standards but as well the actual or planned management is able to reduce the environmental impact down to a bearable level.

• Korean Journal of Environment and Ecology
• /
• v.34 no.3
• /
• pp.249-258
• /
• 2020

This study aims to provide reference material for effective forest management techniques at the catchment scale, based on the field investigation of large woody debris (LWD) in 11 streams within a third-order forest catchment in Gangwon Province, Korea. To achieve this aim, we analyzed the morphological features of LWD pieces, and the storage and distribution status of LWD by stream order throughout the entire investigation. As a result, a total of 1,207 individual pieces of LWD were categorized into three types as follows: (ⅰ) 1,142 pieces (95%) as only trunk and 65 pieces (5%) as a trunk with root wad, (ⅱ) 1,015 pieces (84%) as non-thinned and 192 pieces (16%) as the thinned, and (ⅲ) 1,050 pieces (87%) as conifer and 157 pieces (13%) as broadleaf. Additionally, in-stream LWD loads (㎥/ha) decreased with increasing stream order, yielding 105.4, 71.3, and 35.6 for first-, second-, and third-order streams, respectively. On the other hand, the ratio of LWD jams to the total LWD volume increased with increasing stream order, yielding 11%, 43%, and 49% for first-, second-, and third-order streams, respectively. Finally, a comparison of the in-stream LWD load with previous studies in several countries around the world indicated that in-stream LWD load was positively correlated with forest stand age even though the climate, topography, forest soil type, forest composition, stand growth rate, disturbance regime, and forest management practices were different. These results could contribute to understanding the significance of LWD as a by-product of forest ecosystems and an indicator of riparian forest disturbance. Based on this, we conclude that advanced forest management techniques, including treatment of thinning slash and stand density control of riparian forest by site location (hillslope and riparian zone, or stream order), should be established in the future, taking the forest ecosystem and the aquatic environment from headwater streams to low land rivers into consideration.

• Journal of KIISE:Software and Applications
• /
• v.33 no.9
• /
• pp.751-775
• /
• 2006

In this paper, we suggested an avatar control technique using the high-level behavior. We separated behaviors into three levels according to level of abstraction and defined layered scripts. Layered scripts provide the user with the control over the avatar behaviors at the abstract level and the reusability of scripts. As the 3D environment gets complicated, the number of required avatar behaviors increases accordingly and thus controlling the avatar-object behaviors gets even more challenging. To solve this problem, we embed avatar behaviors into each environment object, which informs how the avatar can interact with the object. Even with a large number of environment objects, our system can manage avatar-object interactions in an object-oriented manner Finally, we suggest an easy-to-use user interface technique that allows the user to control avatars based on context menus. Using the avatar behavior information that is embedded into the object, the system can analyze the object state and filter the behaviors. As a result, context menu shows the behaviors that the avatar can do. In this paper, we made the virtual presentation environment and applied our model to the system. In this paper, we suggested the technique that we controling an the avatar control technique using the high-level behavior. We separated behaviors into three levels byaccording to level of abstract levelion and defined multi-levellayered script. Multi-leveILayered script offers that the user can control avatar behavior at the abstract level and reuses script easily. We suggested object models for avatar-object interaction. Because, TtThe 3D environment is getting more complicated very quickly, so that the numberss of avatar behaviors are getting more variableincreased. Therefore, controlling avatar-object behavior is getting complex and difficultWe need tough processing for handling avatar-object interaction. To solve this problem, we suggested object models that embedded avatar behaviors into object for avatar-object interaction. insert embedded ail avatar behaviors into object. Even though the numbers of objects areis large bigger, it can manage avatar-object interactions by very efficientlyobject-oriented manner. Finally Wewe suggested context menu for ease ordering. User can control avatar throughusing not avatar but the object-oriented interfaces. To do this, Oobject model is suggested by analyzeing object state and filtering the behavior, behavior and context menu shows the behaviors that avatar can do. The user doesn't care about the object or avatar state through the related object.

• 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.