• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.48-57
• /
• 2019

The purpose of this study is to understand the intention of the inquirer from the single text type question in Goal-oriented dialogue. Goal-Oriented Dialogue system means a dialogue system that satisfies the user's specific needs via text or voice. The intention analysis process is a step of analysing the user's intention of inquiry prior to the answer generation, and has a great influence on the performance of the entire Goal-Oriented Dialogue system. The proposed model was used for a daily chemical products domain and Korean text data related to the domain was used. The analysis is divided into a speech-act which means independent on a specific field concept-sequence and which means depend on a specific field. We propose a classification method using the word embedding model and the CNN as a method for analyzing speech-act and concept-sequence. The semantic information of the word is abstracted through the word embedding model, and concept-sequence and speech-act classification are performed through the CNN based on the semantic information of the abstract word.

• Korean Journal of Heritage: History & Science
• /
• v.43 no.1
• /
• pp.128-159
• /
• 2010

In this study, the progress of domestic cultural properties designation, the changes and problems in classification were examined, and the relationship among Traditional Pal-kyung, Dongcheon-gukok, and Modern Pal-kyung were investigated targeting total of 68 cases of state-designated cultural properties of scenic sites in order to show that the traditional significance and value are being inherited today. The major results of this study are as follows. First, increase in scenic site designations with historical, cultural, and scenic characteristics can be viewed as an active intent to embrace the concepts such as cultural utilities, historical characteristics, literary value, and ideological backgrounds, which were specified as the basis for designation in the early Cultural Property Protection Law. Accordingly, it is very encouraging that the concept of cultural attractions such as traditional gardens and observatory points are regarded as an important standard for designation of scenic sites. Second, as for the classification of scenic sites per type, it was found that 'places with excellent natural scenery' were 44.16%(30 cases), followed by 'famous buildings or gardens and places with important legend' occupying 30.9%(21 cases), 'places with famous scenery' occupying 13.2%(9 cases), 'places with outstanding historical cultural and scenic value' that occupying 10.3%(7 cases), and 'animal and vegetation habitat with beautiful scenery' (1 case). Third, according to the current classification standards for scenic sites, there were only 7 cases which could be classified into Pal-kyungs(Famous 8 Sceneries) and 3 cases classified into Dongcheon(beautiful scenery surrounded by mountains and rivers), but there was no Gugok(beautiful valleys). Consequently, in terms of external appearance, the scenic sites among the total scenic sites that could be classified into Palkyung and Gugok were only 14.7%(10 cases). Fourth, the traditional scenic sites based on literal references and Internet analysis occupied 67.7%(46 cases), which were found to be scenic sites related to the traditional Pal-kyung among which 38 cases(55.9% of 46 cases) were included based on the scenery and 8 cases(11.8% of 46 cases) were included due to the scenery at the time. Fifth, there were 8(11.8%) scenic sites which were related to Dongcheon, and 4 cases(5.9%) related to Gugok. Also, it was found that total of 40(48.9%) scenic sites designated as modern scenic sites were playing the role of local scenic sites, and they were used as the tourism advertising contents. Sixth, it was identified that there were 62 cases(91.2%) of scenic sites in total related to traditional and modern Pal-kyung or Dongcheon-gugok, and unlike explicit classifications, most of the designated scenic sites were found to be deeply connected with the historical and cultural significance contained in the scenaries.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.10 no.1
• /
• pp.22-32
• /
• 2012

Purpose: The purpose of this study was to examine the occurrence of toxic exposure cases in Korean emergency centers using a toxic exposure surveillance system-based report form and to provide guidelines for the prevention and treatment of toxic exposures. Methods: We retrospectively reviewed the medical records of toxic exposure patients who had visited emergency centers from January 2009 to December 2009. Epidemiology data points for the toxic exposure cases included age, gender, type of exposure, number and kind of substances involved, reason and route of poison exposure, management of the patients in the emergency departments, and the clinical outcome. Results: A total of 3,501 patients from 12 emergency departments were enrolled in the study. 50.0% of the total exposure patients were male and 63.0% of the total cases were fatal. Acute intoxication occurred in 91.3% of the total patients and suicidal intent was the most common (43.3%) reason for exposure. The most common route of exposure was ingestion (75.9%). Of the total cases, pesticides were involved in 26.3%, sedatives/hypnotics/antipsychotics were involved in 22.0%, and bites and envenomations were involved in 15.7%. Conclusion: We provided a database of patients who were admitted to emergency departments after poisoning incidents. We recommend that toxicology professionals develop a classification scheme for toxicants which is adequate for Korean domestic circumstances and initiate a toxic surveillance system for all types of exposures. With support of a psychiatric surveillance system for suicidal patients and establishment of social mediation for pesticide poisoning, major reductions in poison exposures can be achieved.

• Journal of Internet Computing and Services
• /
• v.18 no.4
• /
• pp.121-131
• /
• 2017

With emergence of Internet, social media, and mobile service, the consumers have actively presented their opinions and sentiment, and then it is spreading out real time as well. The user-generated text data on the Internet and social media is not only the communication text among the users but also the valuable resource to be analyzed for knowing the users' intent and sentiment. In special, economic participants have strongly asked that the social big data and its' analytics supports to recognize and forecast the economic trend in future. In this regard, the governments and the businesses are trying to apply the social big data into making the social and economic solutions. Therefore, this study aims to reveal the capability of social big data analysis for the economic use. The research proposed a social big data analysis model and an online consumer sentiment index. To test the model and index, the researchers developed an economic survey ontology, defined a sentiment dictionary for sentiment analysis, conducted classification and sentiment analysis, and calculated the online consumer sentiment index. In addition, the online consumer sentiment index was compared and validated with the composite consumer survey index of the Bank of Korea.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.489-498
• /
• 2012

This paper consists of two parts: In the first part, we describe our work to build hierarchical knowledge base of digital library patron's research interests and learning topics in various scholarly areas through analyzing well classified Electronic Theses and Dissertations (ETDs) of NDLTD Union catalog. Journal articles from ACM Transactions and conference web sites of computing areas also are added in the analysis to specialize computing fields. This hierarchical knowledge base would be a useful tool for many social computing and information service applications, such as personalization, recommender system, text mining, technology opportunity mining, information visualization, and so on. In the second part, we compare four grouping algorithms to select best one for our data mining researches by testing each one with the hierarchical knowledge base we described in the first part. From these two studies, we intent to show traditional verification methods for social community miming researches, based on interviewing and answering questionnaires, which are expensive, slow, and privacy threatening, can be replaced with systematic, consistent, fast, and privacy protecting methods by using our suggested hierarchical knowledge base.

• Sijohaknonchong
• /
• v.25
• /
• pp.211-237
• /
• 2006

Mansebo[만세보] contains a total of 111 old shijos under the title of Haedongyeongeon[해동영언]. This dissertation presumes Haedongyeongeon[해동영언] as early 20th century shijo text and surveys its literary characteristic and its significance in relation with anthological compilation. Haedongyeongeon can be seen as both newspaper serials and a short anthology. The basic pattern of the serials shows an organization of 'title. musical designation, author. text. and a brief review. Of these, the review is what most clearly shows the characteristic of the serials. The review is written in Chinese followed by Korean letters to designate the sound of the Chinese. which is presumably designed to attract more readers for the newspaper. On the other hand, Haedongyeongeon[해동영언], when seen as a collection of works printed in serials, clearly shows an intention of compiling an anthology, particularly in its way of overall classification of works or arranging works according to their authors, and thus may well be defined as a short anthology. This anthology somewhat excessively pursues perfection in formality, and is characterized by its strong intent to be read as popular literature, and therefore could be said to manifest the general characteristic of 20th century anthologies. The planner of the serial Haedongyeongeon[해동영언], or the compiler of the anthology is thought to be one of the core figures of Mansebo[만세보], that is, O Sechang[오세창], Lee Injik[이인직], Choi Yeongnyeon[최영년], Shin Gwanghui[신광희], but of them all, considering all circumstances, Choi Yeongnyeon[최영년] is most likely to be the one. Lastly, it is presently unknown what anthology was used as the basis of Haedongyeongeon[해동영언] and accordingly any judgement on that head has been deferred.

• The Korean Journal of Air & Space Law and Policy
• /
• v.28 no.1
• /
• pp.55-71
• /
• 2013

By aircraft from Aviation regulations and institutional regulatory framework for ensuring the safety is secured. State-of-the-art aircraft, according to the type of development and diversification, modernization and new types of aircraft are operated. In particular, light aircraft and ultralight flying device such as the gyro-plane and unmanned flying devices is introduced a new device, and the device operates at these flight in accordance with the standards of the Aviation Act regulations may not occur often. Variety of light aircraft and ultra-light aircraft assembly, can be adapted for a person engaged in the business of aviation safety management and to perform the legal basis was established. Depending on the classification of newly introduced aircraft, the biggest change is the introduction of the concept of the LSA. In Korea, the various light aircraft are operating, but these aircraft range not clearly Aviation Regulations had difficulty in ensuring safety. This study examined the differences between international rules and regulations of Korea about the classification of aircraft. The LSA are included in aircraft categories internationally, but LSA will not be included in the aircraft categories, which is one of a range of powered flight device exists in Korea Aviation Act. Limit for maximum continuous power speed in a LSA, it is a limit on the right of the people who want using the high-performance plane. Also it is an international trend does not fit in, and is consistent with the intent of LSA manufacturer. Delete the content from a range of future aviation law revisions and light aircraft-related provisions to limit the maximum continuous power speed is considered to be suitable for the purpose of introducing the light aircraft industry. The laws and regulations set up in order to ensure the safety of ultralight aircraft categories existing in ultralight aircraft that exceeds the purpose of the introduction of LSA technology development at home and abroad, and is intended to reflect. These standards complement of aircraft operation is not appropriate for the situation unless the country is difficult to ensure the safety of operations. Also developed in other countries, the introduction of aircraft operating in the country, so many problems occur early revision is required.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.28 no.1
• /
• pp.49-58
• /
• 2010

This study is attempted to establish the concept of Byeulseo Scenic Spot that the definitions of Byeulseo and Scenic Spot would be presented first followed by clarifying the basis, reason and justification that Byeulseo would be called as Byeulseo Scenic Spot that the following is the major results formulated herein. First, the concept of scenic spot under the Cultural Property Act is the reference to the famous site with the building improvement well known for its great scenery or the point where splendid scenery is viewed that has the artistic value along with the trace of human lives in this cultural heritage that, although the scenery is important but the attention has to be on discovery of historic resources with the story telling in the subject site. Second, the criteria of designation on the Scenic Spot in Korea would be natural scenery, animal and plant site with well-known scenery, view point of scenery, famous building or garden and important places with legend that there lacks diversification. In this aspect, the intent of the concept of Scenic Spot would be facilitated to expand the designation of the Byeulseo Scenic Spot as the Scenic Spot of living style. Third, from the foreign cases, particularly, in Japan, it is needed to note that Byeulseos and housing gardens are designated for 196 places of Scenic Spot, reaching 55.4% of entire Scenic Spots. Laws, regulations, systems and designated criteria on the cases of designating the foreign Scenic Spots would be studied and quoted. Fourth, the classification work for each type to designate as cultural heritage has to be continued as the Scenic Spot of subject site with even more emerged for the value as the Scenic Spot in garden, original site and the like classified as historic site, important folk data and the like. Fifth, the designation of Scenic Spot of Byeulseo garden with splendid scenery as the living Scenic Spot has to be expanded. The pavilion existed now nationwide would be approximately 1,500, and these pavilions are the place where the scholars stay in the famous site, and this is the central space of Byeulseo to study, and if there is clear one that has written and record of deed to create the stories to people with the value for publicity campaign, it would be the subject of Scenic Spot. And sixth, for the case of view point with splendid scenery in Byeulseo Garden, it cannot be the subject of designation that the designation of Scenic Spot has to be expanded. In the event of the Byeulseo garden in Korea, there are many cases of having outstanding view points, and there is a few case of designating the subject site with great view point as a Scenic Spot.

• Journal of Distribution Research
• /
• v.17 no.3
• /
• pp.25-57
• /
• 2012

This study identified motives for writing apparel product reviews in online stores, and determined what motives increase the behavior of writing reviews. It also classified store customers based on the type of writing motives, and clarified the characteristics of internet purchase behavior and of a demographic profile. Data were collected from 252 females aged 20s' and 30s' who have experience of reading and writing reviews on online shopping. The five types of writing motives were altruistic information sharing, remedying of a grievance and vengeance, economic incentives, helping new product development, and the expression of satisfaction feelings. Among five motives, altruistic information sharing, economic incentives, and helping new product development stimulate writing reviews. Store customers who write reviews were classified into three groups based on their writing motive types: Other consumer advocates(29.8%), self-interested shoppers(40.5%) and shoppers with moderate motives(29.8%). There were significant differences among three groups in writing behavior (the frequency of writing reviews, writing intent of reviews, duration of writing reviews, and frequency of online shopping) and age. Based on results, managerial implications were suggested. Long Abstract : The purpose of present study is to identify the types of writing motives on online shopping, and to clarify the motives affecting the behavior of writing reviews. This study also classifies online shoppers based on the motive types, and identifies the characteristics of the classified groups in terms of writing behavior, frequency of online shopping, and demographics. Use and Gratification Theory was adopted in this study. Qualitative research (focus group interview) and quantitative research were used. Korean women(20 to 39 years old) who reported experience with purchasing clothing online, and reading and writing reviews were selected as samples(n=252). Most of the respondents were relatively young (20-34yrs., 86.1%,), single (61.1%), employed(61.1%) and residents living in big cities(50.9%). About 69.8% of respondents read and 40.5% write apparel reviews frequently or very frequently. 24.6% of the respondents indicated an "average" in their writing frequency. Based on the qualitative result of focus group interviews and previous studies on motives for online community activities, measurement items of motives for writing after-purchase reviews were developed. All items were used a five-point Likert scale with endpoints 1 (strongly disagree) and 5 (strongly agree). The degree of writing behavior was measured by items concerning experience of writing reviews, frequency of writing reviews, amount of writing reviews, and intention of writing reviews. A five-point scale(strongly disagree-strongly agree) was employed. SPSS 18.0 was used for exploratory factor analysis, K-means cluster analysis, one-way ANOVA(Scheffe test) and ${\chi}^2$-test. Confirmatory factor analysis and path model analysis were conducted by AMOS 18.0. By conducting principal components factor analysis (varimax rotation, extracting factors with eigenvalues above 1.0) on the measurement items, five factors were identified: Altruistic information sharing, remedying of a grievance and vengeance, economic incentives, helping new product development, and expression of satisfaction feelings(see Table 1). The measurement model including these final items was analyzed by confirmatory factor analysis. The measurement model had good fit indices(GFI=.918, AGFI=.884, RMR=.070, RMSEA=.054, TLI=.941) except for the probability value associated with the ${\chi}^2$ test(${\chi}^2$=189.078, df=109, p=.00). Convergent validities of all variables were confirmed using composite reliability. All SMC values were found to be lower than AVEs confirming discriminant validity. The path model's goodness-of-fit was greater than the recommended limits based on several indices(GFI=.905, AGFI=.872, RMR=.070, RMSEA=.052, TLI=.935; ${\chi}^2$=260.433, df=155, p=.00). Table 2 shows that motives of altruistic information sharing, economic incentives and helping new product development significantly increased the degree of writing product reviews of online shopping. In particular, the effect of altruistic information sharing and pursuit of economic incentives on the behavior of writing reviews were larger than the effect of helping new product development. As shown in table 3, online store shoppers were classified into three groups: Other consumer advocates (29.8%), self-interested shoppers (40.5%), and moderate shoppers (29.8%). There were significant differences among the three groups in the degree of writing reviews (experience of writing reviews, frequency of writing reviews, amount of writing reviews, intention of writing reviews, and duration of writing reviews, frequency of online shopping) and age. For five aspects of writing behavior, the group of other consumer advocates who is mainly comprised of 20s had higher scores than the other two groups. There were not any significant differences between self-interested group and moderate group regarding writing behavior and demographics.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.111-126
• /
• 2020

Most industries have recently become aware of the importance of customer lifetime value as they are exposed to a competitive environment. As a result, preventing customers from churn is becoming a more important business issue than securing new customers. This is because maintaining churn customers is far more economical than securing new customers, and in fact, the acquisition cost of new customers is known to be five to six times higher than the maintenance cost of churn customers. Also, Companies that effectively prevent customer churn and improve customer retention rates are known to have a positive effect on not only increasing the company's profitability but also improving its brand image by improving customer satisfaction. Predicting customer churn, which had been conducted as a sub-research area for CRM, has recently become more important as a big data-based performance marketing theme due to the development of business machine learning technology. Until now, research on customer churn prediction has been carried out actively in such sectors as the mobile telecommunication industry, the financial industry, the distribution industry, and the game industry, which are highly competitive and urgent to manage churn. In addition, These churn prediction studies were focused on improving the performance of the churn prediction model itself, such as simply comparing the performance of various models, exploring features that are effective in forecasting departures, or developing new ensemble techniques, and were limited in terms of practical utilization because most studies considered the entire customer group as a group and developed a predictive model. As such, the main purpose of the existing related research was to improve the performance of the predictive model itself, and there was a relatively lack of research to improve the overall customer churn prediction process. In fact, customers in the business have different behavior characteristics due to heterogeneous transaction patterns, and the resulting churn rate is different, so it is unreasonable to assume the entire customer as a single customer group. Therefore, it is desirable to segment customers according to customer classification criteria, such as loyalty, and to operate an appropriate churn prediction model individually, in order to carry out effective customer churn predictions in heterogeneous industries. Of course, in some studies, there are studies in which customers are subdivided using clustering techniques and applied a churn prediction model for individual customer groups. Although this process of predicting churn can produce better predictions than a single predict model for the entire customer population, there is still room for improvement in that clustering is a mechanical, exploratory grouping technique that calculates distances based on inputs and does not reflect the strategic intent of an entity such as loyalties. This study proposes a segment-based customer departure prediction process (CCP/2DL: Customer Churn Prediction based on Two-Dimensional Loyalty segmentation) based on two-dimensional customer loyalty, assuming that successful customer churn management can be better done through improvements in the overall process than through the performance of the model itself. CCP/2DL is a series of churn prediction processes that segment two-way, quantitative and qualitative loyalty-based customer, conduct secondary grouping of customer segments according to churn patterns, and then independently apply heterogeneous churn prediction models for each churn pattern group. Performance comparisons were performed with the most commonly applied the General churn prediction process and the Clustering-based churn prediction process to assess the relative excellence of the proposed churn prediction process. The General churn prediction process used in this study refers to the process of predicting a single group of customers simply intended to be predicted as a machine learning model, using the most commonly used churn predicting method. And the Clustering-based churn prediction process is a method of first using clustering techniques to segment customers and implement a churn prediction model for each individual group. In cooperation with a global NGO, the proposed CCP/2DL performance showed better performance than other methodologies for predicting churn. This churn prediction process is not only effective in predicting churn, but can also be a strategic basis for obtaining a variety of customer observations and carrying out other related performance marketing activities.