• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.161-177
• /
• 2019

In this paper, we study the performance improvement of the answer extraction in Question-Answering system by using sentence dependency parsing result. The Question-Answering (QA) system consists of query analysis, which is a method of analyzing the user's query, and answer extraction, which is a method to extract appropriate answers in the document. And various studies have been conducted on two methods. In order to improve the performance of answer extraction, it is necessary to accurately reflect the grammatical information of sentences. In Korean, because word order structure is free and omission of sentence components is frequent, dependency parsing is a good way to analyze Korean syntax. Therefore, in this study, we improved the performance of the answer extraction by adding the features generated by dependency parsing analysis to the inputs of the answer extraction model (Bidirectional LSTM-CRF). The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. In this study, we compared the performance of the answer extraction model when inputting basic word features generated without the dependency parsing and the performance of the model when inputting the addition of the Eojeol tag feature and dependency graph embedding feature. Since dependency parsing is performed on a basic unit of an Eojeol, which is a component of sentences separated by a space, the tag information of the Eojeol can be obtained as a result of the dependency parsing. The Eojeol tag feature means the tag information of the Eojeol. The process of generating the dependency graph embedding consists of the steps of generating the dependency graph from the dependency parsing result and learning the embedding of the graph. From the dependency parsing result, a graph is generated from the Eojeol to the node, the dependency between the Eojeol to the edge, and the Eojeol tag to the node label. In this process, an undirected graph is generated or a directed graph is generated according to whether or not the dependency relation direction is considered. To obtain the embedding of the graph, we used Graph2Vec, which is a method of finding the embedding of the graph by the subgraphs constituting a graph. We can specify the maximum path length between nodes in the process of finding subgraphs of a graph. If the maximum path length between nodes is 1, graph embedding is generated only by direct dependency between Eojeol, and graph embedding is generated including indirect dependencies as the maximum path length between nodes becomes larger. In the experiment, the maximum path length between nodes is adjusted differently from 1 to 3 depending on whether direction of dependency is considered or not, and the performance of answer extraction is measured. Experimental results show that both Eojeol tag feature and dependency graph embedding feature improve the performance of answer extraction. In particular, considering the direction of the dependency relation and extracting the dependency graph generated with the maximum path length of 1 in the subgraph extraction process in Graph2Vec as the input of the model, the highest answer extraction performance was shown. As a result of these experiments, we concluded that it is better to take into account the direction of dependence and to consider only the direct connection rather than the indirect dependence between the words. The significance of this study is as follows. First, we improved the performance of answer extraction by adding features using dependency parsing results, taking into account the characteristics of Korean, which is free of word order structure and omission of sentence components. Second, we generated feature of dependency parsing result by learning - based graph embedding method without defining the pattern of dependency between Eojeol. Future research directions are as follows. In this study, the features generated as a result of the dependency parsing are applied only to the answer extraction model in order to grasp the meaning. However, in the future, if the performance is confirmed by applying the features to various natural language processing models such as sentiment analysis or name entity recognition, the validity of the features can be verified more accurately.

• Korean Journal of Culture and Social Issue
• /
• v.12 no.5_spc
• /
• pp.81-98
• /
• 2006

The objective of this research is to do a cultural comparison on the daily lives of the children of Korea, Japan and China. To achieve this objective, the questionnares were distributed to the 2940 mothers of children from the ages of 3 to 6 in the countries of Korea, Japan and China. The target audience consisted of 941 mothers living in Seoul and Kyunggi area for Korea, 1007 mothers living in Tokyo for Japan, and 992 mothers living in Beijing for China. As a result of the research, we found out that firstly, although children in general got up anytime between 7:00am to 9:00am and went to bed between 8:00pm and 11:00pm, 61.5% of the Korean children went to bed after 10pm and 16.8% after 11pm. Besides that, we found that compared to 3.51% of Korean children who got up before 6am, 13.41% of Japanese children and 17.24% of Chinese children got up before 6:00am. So we could see that the Korean children got up later and went to bed later than their Japanese and Chinese counterpart. This pattern could also be seen in the average rising time and bed time. Korean children went to bed at 10:00pm and woke up at 7:75am whereas the Japanese children went to bed at 9:28pm and woke up at 7:39am, and the Chinese children went to bed at 9:05pm and woke up at 7:05am. The average sleeping hours for Japanese children was 10.12 hours, 9.50 hours for the Chinese and 9.75 hours for the Korean. As a result, we could see that the Korean children went to bed later, got up later and slept fewer hours than their Japanese and Chinese counterparts. Also, since the rising time and bedtime of the Korean children was later than those of the Chinese and Japanese counterparts, the former s' breakfast and dinner time was also much later. Secondly, we looked at the time children went off to and came back from institutes such as kindergarten and child care centers. The Chinese were earliest at going with average attendance at 7:83am, the Japanese came next at 8:59am and the Korean children were last at 8:90am, whereas the Japanese came first in coming back home at 3:36pm, Korean next at 3:91pm and the Chinese last at 5:46pm. Next when we looked at the hours spent at the kindergartens and child care centers, Japan spent 6.76 hours, Korea 7.01 hours and China spent the longest hours with 9.63 hours. Excluding China where all preschool institutes are centralized into kindergartens, we nest looked at time children went to and came back from the institutes as well as the time spent there. In the case of kindergarten, there was not much difference but in the case of child care centers, the Japanese children went to the child care centers mach earlier and came home later than the Korean children. Also, the time spent at the child care center was much longer for the Japanese than the Korean children. This fact coincides with the Korean mothers' number one wish to the kindergartens and child care centers i.e. for the institutes to prolong their school hours. Thus, the time spent at child care centers for Korea was 7.75 hours, 9.39 hours for Japan and 9.63 hours for China. The time for Korea was comparatively much shorter than that of Japan and China but if we consider the fact that 50% of the target audience was working mothers, we could easily presume that the working parents who usually use the child care centers would want the child care centers to prolong the hours looked after their children. Besides this, the next most wanted wish mothers have towards the child care centers and kindergartens was for those institutes to "look after their children when sick". This item showed high marks in all three countries, and the marks in Korea was especially higher when compared to Japan and China. Thirdly, we looked at the private extracurricular activities of the children. We found that 72.6% of the Korean children, 61.7% of the Japanese children, and 64.6% of the Chinese children were doing private extracurricular activities after attending kindergarten or day care centers. Amongst the private extracurricular activities done by Korean children, the most popular one was worksheet with 51.9% of the children doing it. Drawing (15.20%) and English (11.6%) came next. Swimming (21.95%) was the most popular activity for Japan, with English (17.48%), music (15,79%) and sports (14.70%) coming next. For China, art (30.95%) was first with English (22.08%) and music (19.96%) following next. All three countries had English as the most popular activity related to art and physical activities after school hours, but the rate for worksheet studies was much higher for Korea compared to Japan China. The reason Koreans universally use worksheet in because the parents who buy the worksheet are mothers who have easy access to advertisement or salespeople selling those products. The price is also relatively cheap, the worksheet helps the children to grow the basic learning ability in preparation for elementary school, and it is thought to help the children to build the habit of studying everyday. Not only that but it is estimated that the worksheet education is being conducted because parents can share the responsibility of the children's learning with the worksheet-teacher who make home visits. Looking at the expenses spent on private extracurricular activities as compared to income, we found that China spent 5% of income for activities outside of regular education, Korea 3% and Japan 2%. Fourthly, we looked at the amount of time children spent on using multimedia. The majority of the children in Korea, Japan and China watch television almost every day. In terms of video games, the Japanese children played the games the most, with Korea and China following next. The Korean children used the computer the most, with Japan and China next. The Korean children used about 21.17% of their daily time on computers which is much more than the Japanese who used 20.62% of their time 3 or 4 times a week, or the Chinese. The Chinese children were found to use considerably less time on multimedia compared to the Korean of Japanese.

• The korean journal of orthodontics
• /
• v.31 no.2 s.85
• /
• pp.225-236
• /
• 2001

It is widely accepted that the shape and structure of bone are closely related to the activity of attached muscle. Numerous clinical and animal experimental studies indicated the significant effects of masticatory muscle function on maxillofacial morphology. Recently, the development of ultrasonography has spread throughout different fields of medicine. In the clinical examinations, ultrasonography is a convenient, inexpensive technique to apply with accurate and reliable results. The aim of this study is to assess the thickness of the masseter muscle and its correlation to maxillofacial skeleton by examining 35 male and 15 female dental students at Kangnung National University. The masseter muscle thickness of the subjects were measured by ultrasonographic scanning with a 7.5MHz linear probe, and their maxillofacial morphology were investigated by lateral cephalometric radiographs. The relationship between the masseter muscle thickness and maxillofacial morphology of normal adult was statistically analyzed, and the following results were obtained. 1. The average thickness of male masseter muscle was 13.8${\pm}$1.71mm in the relaxed state and 14.8${\pm}$1.77mm at maximal clenching state, while that of female was 11.6${\pm}$1.58mm and 12.4${\pm}$1.47mm, respectively. Ethnic difference in thickness of the masseter muscle and maxillofacial skeleton was found when the results of many researchers were compared with those of this study. 2. The thickness of the masseter muscle in both sexes increased significantly at maximal clenching state than in relaxed state(P<0.05). 3. The masseter muscle thickness of male was greater than that of female both in the relaxed state and maximal clenching states(P<0.05). 4. In males, the thickness of the masseter muscle was negatively correlated with the mandibular plane angle and positively correlated with the mandibular ramus height and anterior cranial base length(P<0.05). It may suggest that the male with thicker masseter muscle has smaller facial divergence. 5. No significant correlation was found between the masseter muscle thickness and maxillofacial morphology in females(P<0.05). Therefore, these data suggest that ultrasonography can add valuable information to the conventional examinations of masseter muscle function.

• The Korean Journal of Air & Space Law and Policy
• /
• v.30 no.1
• /
• pp.31-64
• /
• 2015

The Chicago Convention and Annexes have become the basis of aviation safety regulations for every contracting state. Generally, aviation safety regulations refer to the SARPs provided in the Annexes of the Chicago Convention. In order to properly reflect international aviation safety regulations, constant studies of the aviation fields are of paramount importance. Treaties duly concluded and promulgated under the Constitution and the generally recognized rules of international law shall have the same effect as the domestic laws of the Republic of Korea. Each contracting state to the Chicago Convention should meet ICAO SARPs about AOC and FAOC. According to ICAO SARPs, Civil Aviation Authorities shall issue AOC to air carriers of the state, but don't require to issue for foreign air carrier. However some contracting states of the Chicago Convention issue FAOC and/or Operations Specifications for the foreign operators. This FAOC is being expanded from USA to the other contracting states. Foreign operators have doubly burden to implement AOC of the ICAO SARPs because FAOC is an additional requirement other than that prescribed by the ICAO SARPs In Article 33, the Chicago Convention stipulates that each contracting state shall recognize the validity of the certificates of airworthiness and licenses issued by other contracting states as long as they are equal to or above the minimum standards of the ICAO. In ICAO Annex 6, each contracting state shall recognize as valid an air operator certificate issued by another contracting state, provided that the requirements under which the certificate was issued are at least equal to the applicable Standards specified in this Annex. States shall establish a programme with procedures for the surveillance of operations in their territory by a foreign operator and for taking appropriate action when necessary to preserve safety. Consequently, it is submitted that the unilateral action of the states issuing the FAOC to the foreign air carriers of other states is against the Convention. Hence, I make some proposals on the FAOC as an example of comprehensive problem solving after comparative study with ICAO SARPs and the contracting state's regulations. Some issues must be improved and I have made amendment proposals to meet ICAO SARPs and to strengthen aviation development. Operators should be approved by FAOC at most 190 if all states require FAOC. Hence, it is highly recommended to eliminate the FAOC or reduce the restrictions it imposes. In certain compliance-related issues, delayed process shall not be permitted to flight operations. In addition, it is necessary for the ICAO to provide more unified and standardized guidelines in order to avoid confusion or bias regarding the arbitrary expansion of the FAOC. For all the issue mentioned above, I have studied the ICAO SARPs and some state's regulation regarding FAOC, and suggested some proposals on the FAOC as an example of comprehensive problem solving. I hope that this paper is 1) to help understanding about the international issue, 2) to help the improvement of korean aviation regulations, 3) to help compliance with international standards and to contribute to the promotion of aviation safety, in addition.

• Applied Biological Chemistry
• /
• v.15 no.1
• /
• pp.65-75
• /
• 1972

The rice qualities including cooking and eating qualities were studied using recommended Korean rice varieties (20 of japonica and 3 of indies type; IR 667) which were grown at Suwon, Korea in 1971. As the result, followings were obtained. 1. Amylose contents of white rice were varied with the varieties 21.1 to 25.5% and the average was 23.0%. Three indica type varieties (IR 667) showed higher amylose contents than the other japonica type varieties except Mankyung. Among japonica type varieties, Palkum, Mankyung composed the group of the highest amyloes content and Kimmaje was the lowest. 2. Blue values were distributed in the range of 0.38 to 0.48 and the average was 0.42 IR 667 varieties showed the highest blue value among them. Among japonica type varieties, Jaegun showd the highest blue value and Sooseung, Shirogane showed successively lower values, Shin #2, Nongbaik, Palkweng, Suwon #82, Mankyung, Nonglim #25 and Nongkwang relatively lower blue values. 3. Alkali numbers were in the range of 6.0 to 7.4 and the average was 6.8. Much difference was not shown in alkali number between IR 667 group and the japonica varieties group. 4. Gelatinization temperature were ranged from 59.5 to 64.0 IR 667 varieties showed relatively higher gelatinization temperature than japonica type varieties. 5. Water uptake ratios were measured in the range of 2.67 to 2.92 and the average was 2.79. IR 667 varieties were belonged to the group of highest water uptake ratio. Among japonica type varieties Kimmaje, Suwon #82, Nonglim #29, Deungpan #5, Jaegun, Jinhung, were belonged to the group of relatively high water uptake ratio and Palkweng, Palkeum and Paldal to the relatively low water uptake ratio. 6. Expaned volums were ranged from 29.8 to 33.7 and the average was 31.8. IR 667 varieties showed higher expanded volumes than japonica type varieties. 7. Intensities of starch-iodine blue value of residual liquid indicated 0.35 to 0.58. Among them IR 667 varieties showed relatively high intensities. 8. The range of total solids in residual liquids was 0.605 to 0.810 and the average was 0.700 Much difference was not shown in total solids in residual liquid between IR 667 varieties and japonica varieties. 9. pH values of residual liquids were in the range of 6.3 to 7.3 and the average was 6.95. IR 667 varieties showed lower pH than japonira type varieties.

• Applied Biological Chemistry
• /
• v.4
• /
• pp.33-42
• /
• 1963

1. Two fermentation methods have been compared for the production of Takju (Korean native Sake). One method (S1) uses 'Nuruk' (Korean mold wheat) and the other method (S2) uses 'Nuruk' and mold rice. The chemical analysis of source material, also, have been made in order the check the quantitative changes during the fermentation. The results are summarized below: a. The rate of fermentation was slower for the S2 method than for the S1 method. However, the residual sugar in the S2 method was smaller and the amount of alcohol produced the same as with the S1 method. This was true in spite of the fact that the total initial sugar content for the S2 method was 10 percent below that of S1. b. With both the S1 and S2 methods, 80 percent of the total alcohol production was obtained with in 3 to 4 days. c. The pH value of the base material at the beginning of fermentation was markedly different between the two methods I.e.6.0 to 6.2 for S1 and 4.8 to 5.2 for S2. However, after one or two day the pH of both materials was about the same 4.0 to 4.2 and remained at this value unit the fermentation was complete. 2. Organic acids and Sugars in the source materials have been detected by the paper partition chromatography(p.p.c.) method and the followings are obtained. a. Important Organic acids are Fumalic, malic Succinic, Citric, Acetic aicds in polished rice and Fumalic, Succinic, Acetic, Citric, Malic and Oxalic acids 'Nuruk'. The same kinds of acids as in the rice are found in mold rice, However, amount of Citrice acid is markedly increased in mold rice. b. The important Sugar, Glucose, Fructose and Raffinose in polished rice, Gulcose, Fructo, se, Xylose and one which supposed to be Kojibjose in 'Nuruk'. Glucose and those supposed to be Isomaltose, Kojibiose and Sakebiose and found in rice mold, however, no Sucrose, which was exist in polished rice, was found. 3. The important Organic acids found in fermenting mash using the p.p.c. method were Lactic, Succinic and Acetic. Citric acid identified early in the fermentation, S2 method. remained throughout. However, with the S1 method Cirtic acid was detected only during the late stage of fermentation. Sugars not found in the original materials were two which supposed to be Isomaltotriose and Pentose. Maltose found at the beginning of the fermentation disappeared within one day, Isomaltose was detected throughout the period of fermentation. 4. The Somogyi method which was employed to determine the quantitative changes of sugars in the orginal meterial and mach, showed that polished rice containes in order and in largest amounts Sucrose, Glucose, Raffinose and Fructose. 'Nuruk' contained almost equal quantities of Glucose and Fructose. However, the Glucose content of the mold rice exceeded that originally in the polished rice by 25 or 30 times. Only a small quantity of free sugars was found in the mash at the end of the fermentation.

• The Journal of the Korean bone and joint tumor society
• /
• v.12 no.1
• /
• pp.37-46
• /
• 2006

Purpose: To evaluate the end results between the surgical treatment with neo-adjuvant chemotherapy in Korea and non-invasive high intensity focused ultrasound (HIFU) technique in China for osteogenic sarcomas. Materials and Methods: The surgical treatment with neoadjuvant chemotherapy for total 67 cases (4 IIA, 58 IIB, and 5 III) in Korea since 1993 and the HIFU therapy for total 71 cases (57 II and 14 III) in China since 1997 was performed. In Korea, neo-adjuvant chemotherapy in 66 cases out of total 67 patients, but the adjuvant chemotherapy in only one case was done. On the contrary, in China, full chemotherapy for more than 9 times for 37 patients with stage II out of total 71 cases, but for less than 8 times of partial chemotherapy for 23 patients (stage II) and 14 patients (stage III) was done. The surgical treatment in total 67 Korean patients was done with wide resection and reconstruction for 56 patients, but wide resection without reconstruction for 5 patients and amputation for 6 patients. In china, total 71 patients was treated with average 1.5 times (1~4 times) of HIFU, and if there are some evidences of residual tumor after HIFU with following MRI, the second HIFU therapy was given 2~4 weeks later. After then, the bony defect was in no touch, keep bracing for long time expecting regeneration. All of them were followed for average 46 Mo (12~150 Mo) in Korea, but followed for average 22 Mo (9 years~8 months) in China. Results: The 5 year survival rate (stage II), was average 92.7% (IIA 100%, IIB 85.5%) in Korea series, and average 78.7% (full chemotherapy 91.8%, part chemotherapy 56.6%) in China series. The 3 year survival rate (stage III) was 20% in Korea and 7.1% in China. So, the final overall survival rate was 65.2% in Korea and 51.8% in China. The overall functional outcome score by ISOLS was 24.3 (81%) in Korea and 19.8 (73%) in China. There are 25.4% (17/67 cases) of complications in Korea and 31% (27 complications in 22 patients out of total 71 cases) in China after each treatment. Conclusions: The end results of Korea series which was treated with neoadjuvant chemo- and surgical methods are better than that of non-invasive thermal ablation in china. But we also believe the HIFU, as one of, was also effective to decrease the local recurrence and symptomatic releaf for stage II or even in III of osteogenic sarcomas.

• Korean Journal of Psychosomatic Medicine
• /
• v.12 no.2
• /
• pp.165-173
• /
• 2004

Objectives: Diabetes mellitus is a heterogeneous, chronic, progressive disease characterized by hyperglycemia and abnormality in protein, carbohydrate, fat metabolism. Recent studies have reorted two times prevalence of depression in individuals with diabetes compared to individuals without diabetics. This study was designed to investigate glycemic controls, anxiety, alexithymia, stress responses between depressed diabetic patients and non-depressed diabetic patients. Methods The subjects were 60 diabetic patients(mean age : $50.3{\pm}9.7$ years, 31 men and 29 women) who were confirmed to have diabetes depending on the laboratory findings as welt as clinical symptoms at the St. Vincent Hospital Diabetes Clinic, from Mar. 2004 to Sep. 2004. Laboratory test including, blood chemistry. glycated hemoglobin, urinalysis for proteinuria and Korean version of Beck Depression Inventory(BDI), State and Trait Anxiety Inventory(STAI), Toronto Alexithymia Scale(TAS) and Stress Response Inventory(SRI) were used for assessment. Based on BDI scores, all diabetics were divided into 13 depressed-diabetics group(above 20 point) and 47 non-depressed group(below 20 point). We compared demographic data. glycemic controls, STAI, TAS and SRI scores between two groups by independent t-test. Results : 1) Depressed diabetic groups were 13(mean age : $55.4{\pm}7.2$ years, 7 men and 6 women) and non depressed groups were 47(mean age $48.9{\pm}9.8$ years, 24 men and 23 women). In depressed diabetics, compared with non-depressed group, manifested aged(p=0.031), but other demographic data showed no difference between two groups. 2) No significant differences were noted in FBS, PP2h, Hb A1C, total cholesterol, HDL-cholesterol, SGOT/SGPT, BUN levels between depressed and non-depressed groups. But, blood creatine levels of depressed group were significantly increased than non-depressed group(p=0.026). 3) No significant differences were found in the score of STAI, STAI-S, STAI-T, TAS between depressed and non-depressed groups. 4) The SRI scores of depressed groups were significantly higher than non-depressed groups$(59.7{\pm}24.9\;vs.\;31.5{\pm}22.0)(p=0.000)$. Conclusion : The above results suggest that depressed diabetic patients are have more stress responses and higher blood creatine levels. However, there were no differences in laboratory data related to glycemic controls, and anxiety. alexithymia levels between two groups. We suggest that physicians should consider integrated approaches for psychiatric problems in the management of diabetes.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.34 no.1
• /
• pp.40-52
• /
• 2016

Buyongjeong, a pavilion in the Rear Garden of Changdeok Palace, was appointed as Treasure No. 1763 on March 2, 2012, by the South Korea government since it shows significant symmetry and proportion on its unique planar shape, spatial configuration, building decoration, and so forth. However, the designation of Treasure selection was mainly evaluated by concrete science, in that the selection has not clearly articulated how and why Buoungjeong was constructed as a present unique form. Therefore, this study aims to clarify the identity of Buyongjeong at the time of construction by considering its historical, ideological, philosophical background and building intention. Summary are as follows: First, Construction backgrounds and characters of Buyongjeong: Right after the enthronement, King Jeongjo had founded Kyujanggak(奎章閣), and sponsored civil ministers who were elected by the national examination, as a part of political reform. In addition, he established his own political system by respecting "Kaksin(閣臣)", Kyujanggak's officials as much as "Kain(家人)", internal family members. King Jeongjo's aggressive political reform finally enabled King's lieges to visit King's Rear Garden. In the reign of King Jeongjo's 16th year(1792), Naekaksangjohoe(內閣賞釣會) based on "Kaksin" was officially launched and the Rear Garden visitation became a regular meeting. The Rear Garden visitation consisted of "Sanghwajoeoyeon(賞花釣魚宴)" - enjoying flowers and fishing, and activities of "Nanjeongsugye". Afterward, it eventually became a huge national event since high rank government officials participated the event. King Jeongjo shared the cultural activities with government officials together to Buyongjeong as a place to fulfill his royal politics. Second, The geographical location and spatial characteristics of Buyongjeong: On the enthronement of King Jeongjo(1776), he renovated Taeksujae. Above all, aligning and linking Gaeyuwa - Taeksujae - a cicular island - Eosumun - Kyujangkak along with the construction axis is an evidence for King Jeongjo to determine how the current Kyujangkak zone was prepared and designed to fulfill King Jeonjo's political ideals. In 17th year(1793) of the reign of King Jeongjo, Taeksujae, originally a square shaped pavilion, was modified and expanded with ranks to provide a place to get along with the King and officials. The northern part of Buyongjeong, placed on pond, was designed for the King's place and constructed one rank higher than others. Discernment on windows and doors were made with "Ajasal" - a special pattern for the King. The western and eastern parts were for government officials. The center part was prepared for a place where government officials were granted an audience with the King, who was located in the nortern part of Buyongjeong. Government officials from the western and eastern parts of Buyongjeong, could enter the central part of the Buyongjeong from the southern part by detouring the corner of Buyongjeong. After all, Buyongjeong is a specially designed garden building, which was constructed to be a royal palace utilizing its minimal space. Third, Cultural Values of Buyongjeong: The Buyongjeong area exhibits a trait that it had been continuously developed and it had reflected complex King's private garden cultures from King Sejo, Injo, Hyunjong, Sukjong, Jeongjo and so forth. In particular, King Jeongjo had succeded physical, social and imaginary environments established by former kings and invited their government officials for his royal politics. As a central place for his royal politics, King Jeongjo completed Buyongjeong. Therefore, the value of Buyongjeong, as a garden building reflecting permanency of the Joseon Dynasty, can be highly evaluated. In addition, as it reflects Confucianism in the pavilion - represented by distinguishing hierarchical ranks, it is a unique example to exhibit its distinctiveness in a royal garden.

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

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