• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Information Systems Review
• /
• v.18 no.3
• /
• pp.209-233
• /
• 2016

Internet companies that utilize social network have increased in number. The introduction of diverse social media services facilitated innovative changes in e-business. Social network service (SNS), which is a domain of social media, is a web-based service designed to strengthen human relations in the Internet and build new social relations. The remarkable growth of social network services and the profit generation and perception of this service are the new growth engines of this digital age. Given this development, many global IT companies views SNS as the most powerful form of social media. Thus, they invest efforts to develop business models using SNS.2) This study verifies the impact of privacy exposure in SNS as a result of privacy invasion. This study examines the purpose of using the SNS and user's awareness of the significance of personal information, which are key factors that affect self-disclosure of personal information. This study utilizes theory of reasoned action (TRA) to provide a theoretical platform that describes the specific behavior and emotional response of individuals. This study presents a research model that considers negative attitude (negatude). In this model, self-disclosure in SNS is considered a TRA. TRA is a subjective norm, a behavioral intention, and a key variable of exposure behavior. A survey was conducted on college students at Y university in Seoul to empirically verify the research model. The students have experiences in using SNS. A total of 198 samples were collected. Path analysis was applied to analyze the relations of factors. The results of path analysis show the statistically insignificant impact of privacy invasion on negatude, subjective norm, behavioral intention, and exposure behavior. The impact of unrecognized privacy invasion was also considered insignificant. The impacts of intention to use SNS on negatude, subjective norm, behavioral intention, and exposure behavior was significant. A significant impact was also found for the significance of personal information on subjective norm, behavioral intention, and exposure behavior, whereas the impact on negatude was insignificant. The impact of subjective norm on behavioral intention was significant. Lastly, the impact of behavioral intention on exposure behavior was insignificant. These findings are significant because the study examined the process of self-disclosure by integrating psychological and social factors based on theoretical discussion.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.3
• /
• pp.71-83
• /
• 2018

Recently, there are many efforts to define the field of entrepreneurship as an area of independent study. According to Shane & Venkataraman, the study of entrepreneurship is moving toward understanding the combination of entrepreneurial individual and valuable opportunity in becoming entrepreneurs. In Korea, entrepreneurship education is spreading widely on the basis of universities and in 2010 the entrepreneurship major was created in Sookmyung Women's University for the first time in Korea. The results of this study are as follows. First, there are many research about examining the relationship between entrepreneurship education and entrepreneurship intention. Nevertheless, there are lack of the study focusing on the opportunity recognition which many scholars have recognized as the independent study field of entrepreneurship domain. Therefore, the purpose of this study is to examine the effect of satisfaction of entrepreneurship major education on entrepreneurial opportunity recognition and to examine the mediating effect of entrepreneurial opportunity recognition according to educational commitment. The questionnaires were carried out for 3 weeks to entrepreneurship major students in Sookmyung Woment's University. A total of 84 surveys were collected and statistically analyzed by the R program. As a result of the analysis, it was found that the satisfaction of education positively influences the recognition of entrepreneurial opportunities. Commitment also has a full mediating effect on the recognition of entrepreneurial opportunities. The results of this analysis confirm that the ability to recognize entrepreneurial opportunity is developed by entrepreneurship education, and during the study students' commitment has an important role in the relationship between educational satisfaction and entrepreneurial opportunity recognition. The results were verified through empirical analysis. Satisfaction with entrepreneurship education and awareness of entrepreneurship opportunities through entrepreneurship can be anticipated as entrepreneurship activities in the future.

• Journal of Educational Research in Mathematics
• /
• v.22 no.1
• /
• pp.1-22
• /
• 2012

The purpose of this study is to understand Korea students' characteristics as well as to give important information of improving our education using comparative analysis of framework, test booklets, test results between PISA 2009 and NAEA 2009. PISA 2009 was administered on May of 2009 and NAEA was administered on October of same year. The summary of the results of comparing two assessment is as follows First, cut score of NAEA Advance level is bigger than the cut score of level 5, which is considered as high achievement level. The cut score of Basic level of NAEA is also higher than the level 2 of PISA, which is considered as basic achievement level. This phenomenon can show that NAEA achievement level is set little bit higher than the achievement level of PISA in mathematics domain. Second, the percentage of female students on higher level was higher than that of male students. In suburban area, the percentage of high level was small and the percentage of low level was big. Third, students of Advanced level are distributed concentrating in PISA levels 4~6, Proficient achievement level concentrating in PISA levels 3~5, Basic achievement level concentrating in PISA levels 2~4, and below basic achievement levels concentrating in below level 1 and level 3 of PISA. Fourth, the correlation between NAEA 2009 and PISA 2009 achievement scores are significantly positive. However, the correlation of subscales were low. Fifth, analysis of non-equivalent group, 11 items located in 'change and relationship', 'uncertainty', 'connection cluster' domains found to be significantly different. The percent correct showed very big difference. The analysis results presents the implication of mathematics curriculum, teaching and learning methods as well as National Assessment of Educational Achievement.

• Geophysics and Geophysical Exploration
• /
• v.21 no.3
• /
• pp.150-161
• /
• 2018

Recently, unmanned aircraft EM (electromagnetic) survey based on ICT (Information and Communication Technology) has been widely utilized because of the efficiency in regional survey. We performed the theoretical study on the unmanned airship EM system developed by KIGAM (Korea Institute of Geoscience and Mineral resources) as part of the practical application of unmanned aircraft EM survey. Since this system has different configurations of transmitting and receiving loops compared to the conventional aircraft EM systems, a new technique is required for the appropriate interpretation of measured responses. Therefore, we proposed a method to calculate the EM field for the arbitrary shaped transmitter and verified its validity through the comparison with analytic solution for circular loop. In addition, to simulate the magnetic responses by three-dimensionally (3D) distributed anomalies, we have adapted our algorithm to 3D frequency-domain EM modeling algorithm based on the edge-FEM (finite element method). Though the analysis on magnetic field responses from a subsurface anomaly, it was found that the response decreases as the depth of the anomaly increases or the flight altitude increases. Also, it was confirmed that the response became smaller as the resistivity of the anomaly increases. However, a nonlinear trend of the out-of-phase component is shown depending on the depth of the anomaly and the used frequency, that makes it difficult to apply simple analysis based on the mapping of the magnitude of the responses and can cause the non-uniqueness problem in calculating the apparent resistivity. Thus, it is a prerequisite to analyze the appropriate frequency band and flight altitude considering the purpose of the survey and the site conditions when conducting a survey using the unmanned aircraft EM system.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.171-183
• /
• 2012

In the development of technologies, the exhibition industry has received much attention from governments and companies as an important way of marketing activities. Also, the exhibitors have considered the exhibition as new channels of marketing activities. However, the growing size of exhibitions for net square feet and the number of visitors naturally creates the competitive environment for them. Therefore, to make use of the effective marketing tools in these environments, they have planned and implemented many promotion technics. Especially, through smart environment which makes them provide real-time information for visitors, they can implement various kinds of promotion. However, promotions ignoring visitors' various needs and preferences can lose the original purposes and functions of them. That is, as indiscriminate promotions make visitors feel like spam, they can't achieve their purposes. Therefore, they need an approach using STP strategy which segments visitors through right evidences (Segmentation), selects the target visitors (Targeting), and give proper services to them (Positioning). For using STP Strategy in the smart exhibition environment, we consider these characteristics of it. First, an exhibition is defined as market events of a specific duration, which are held at intervals. According to this, exhibitors who plan some promotions should different events and promotions in each exhibition. Therefore, when they adopt traditional STP strategies, a system can provide services using insufficient information and of existing visitors, and should guarantee the performance of it. Second, to segment automatically, cluster analysis which is generally used as data mining technology can be adopted. In the smart exhibition environment, information of visitors can be acquired in real-time. At the same time, services using this information should be also provided in real-time. However, many clustering algorithms have scalability problem which they hardly work on a large database and require for domain knowledge to determine input parameters. Therefore, through selecting a suitable methodology and fitting, it should provide real-time services. Finally, it is needed to make use of data in the smart exhibition environment. As there are useful data such as booth visit records and participation records for events, the STP strategy for the smart exhibition is based on not only demographical segmentation but also behavioral segmentation. Therefore, in this study, we analyze a case of the promotion methodology which exhibitors can provide a differentiated service to segmented visitors in the smart exhibition environment. First, considering characteristics of the smart exhibition environment, we draw evidences of segmentation and fit the clustering methodology for providing real-time services. There are many studies for classify visitors, but we adopt a segmentation methodology based on visitors' behavioral traits. Through the direct observation, Veron and Levasseur classify visitors into four groups to liken visitors' traits to animals (Butterfly, fish, grasshopper, and ant). Especially, because variables of their classification like the number of visits and the average time of a visit can estimate in the smart exhibition environment, it can provide theoretical and practical background for our system. Next, we construct a pilot system which automatically selects suitable visitors along the objectives of promotions and instantly provide promotion messages to them. That is, based on the segmentation of our methodology, our system automatically selects suitable visitors along the characteristics of promotions. We adopt this system to real exhibition environment, and analyze data from results of adaptation. As a result, as we classify visitors into four types through their behavioral pattern in the exhibition, we provide some insights for researchers who build the smart exhibition environment and can gain promotion strategies fitting each cluster. First, visitors of ANT type show high response rate for promotion messages except experience promotion. So they are fascinated by actual profits in exhibition area, and dislike promotions requiring a long time. Contrastively, visitors of GRASSHOPPER type show high response rate only for experience promotion. Second, visitors of FISH type appear favors to coupon and contents promotions. That is, although they don't look in detail, they prefer to obtain further information such as brochure. Especially, exhibitors that want to give much information for limited time should give attention to visitors of this type. Consequently, these promotion strategies are expected to give exhibitors some insights when they plan and organize their activities, and grow the performance of them.

• Cartoon and Animation Studies
• /
• s.26
• /
• pp.131-156
• /
• 2012

As the Global Age has arrived, the domain of festivals has expanded to fulfill the role of being not only a tourist attraction but of being a factor that determines the image and identity of cities, and the factor of enhancing the brand value of a particular city is being focused upon. The city of Bucheon, which aims to be a culture oriented city, is attempting to utilize the Bucheon International Comics Festival as a cultural asset for the revitalization of the city. This study has as its purpose the development of an evaluation index model on the brand value of the Bucheon International Comics Festival and research being conducted based on the developed evaluation index model on the awareness level of the citizens of Bucheon of the festival. In regards to this, the theoretical background was examined and the index model was developed based on precedent research. Based on this, a survey of 1,000 citizens of Bucheon was conducted in this study. This study conducted a survey targeting 500 persons, dividing them into 2 groups according to whether they participated in the festival. The survey of this study established 9 evaluation categories for the International Comics Festival evaluation index model which consists of demographic research and participation motivation, value of comics, festival brand awareness and association image, perceived product quality and loyalty for the festival, internationality of the festival and urban activation. Each survey question is composed of 5 points scale measurement. As a result of the survey, 'for an education of children' was the highest for the participation motivation, and 'not knowing of the festival information' was the highest for the reason of not having participated. The industrial value was evaluated as the highest among the value of comics by the both two groups, and it was studied that there was perception gap for the festival according to whether they participated in the festival for each survey question. It was revealed that the level of awareness of the Bucheon International Comics Festival was "normal," the "city revitalization" index and the "value of comics" index were relatively high and the "international character of the festival" index was the lowest. Furthermore, it was shown that there were differences in the awareness of the established categories of the developed evaluation index model based on whether or not there was participation in the festival. This study comprehensively organizes these analytical results and derives implications which can be used as data for the criteria of the development of future strategy for the Bucheon International Comics Festival.

• Industry Promotion Research
• /
• v.7 no.2
• /
• pp.43-49
• /
• 2022

This study aims to study Esping-Anderson's theory of welfare state system, develop a model of welfare state suitable for Korea's situation, and apply it to reality. In this research method, basic research and analysis of ideology is used, focusing on Esping-Anderson's welfare state system theory, and applying it appropriately to the Korean situation. Studies on the model of the welfare state have been studied after the classification of complementary and institutional models asserted by Willensky and Lebo in 1965. In addition, Esping-Andersen asserts three things as a model of the welfare state according to ideology. First, the role of the market is central to the liberal welfare system that best fits the image of classical capitalism, and individualistic solidarity through the market. The role of the state or family, which can be a hindrance, is actually marginalized. In addition, in order to maximize individualistic solidarity through the market, de-commodification in the national domain tends to be minimized. Second, the conservative welfare system has a strong familistic element, so the source of social solidarity is the family, and the state plays a role of supporting and supplementing the characteristics of this family. In the conservative system, de-commodification appears to be high among household heads, or the welfare system takes on a corporatist and nationalistic form, it can be said that these characteristics are reflected. Third, in the social democratic welfare system, the source of social solidarity is the state. Therefore, the role of the state is large, the state has a high possibility of decommodification, and it has the characteristics of substitutes for the family and the market through universalist intervention. This study applies Esping-Anderson's three welfare state models to study a model suitable for the Korean situation. In conclusion, Esping-Anderson's three welfare state models can be classified into a market-oriented model based on a liberal welfare system, a status-oriented model based on a conservative corporatist welfare system, and a solidarity-oriented model based on a social-democratic welfare system, presented a compromise between liberalism and conservatism as a Korean model.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.219-239
• /
• 2019

As the importance of providing customized services to individuals becomes important, researches on personalized recommendation systems are constantly being carried out. Collaborative filtering is one of the most popular systems in academia and industry. However, there exists limitation in a sense that recommendations were mostly based on quantitative information such as users' ratings, which made the accuracy be lowered. To solve these problems, many studies have been actively attempted to improve the performance of the recommendation system by using other information besides the quantitative information. Good examples are the usages of the sentiment analysis on customer review text data. Nevertheless, the existing research has not directly combined the results of the sentiment analysis and quantitative rating scores in the recommendation system. Therefore, this study aims to reflect the sentiments shown in the reviews into the rating scores. In other words, we propose a new algorithm that can directly convert the user 's own review into the empirically quantitative information and reflect it directly to the recommendation system. To do this, we needed to quantify users' reviews, which were originally qualitative information. In this study, sentiment score was calculated through sentiment analysis technique of text mining. The data was targeted for movie review. Based on the data, a domain specific sentiment dictionary is constructed for the movie reviews. Regression analysis was used as a method to construct sentiment dictionary. Each positive / negative dictionary was constructed using Lasso regression, Ridge regression, and ElasticNet methods. Based on this constructed sentiment dictionary, the accuracy was verified through confusion matrix. The accuracy of the Lasso based dictionary was 70%, the accuracy of the Ridge based dictionary was 79%, and that of the ElasticNet (${\alpha}=0.3$) was 83%. Therefore, in this study, the sentiment score of the review is calculated based on the dictionary of the ElasticNet method. It was combined with a rating to create a new rating. In this paper, we show that the collaborative filtering that reflects sentiment scores of user review is superior to the traditional method that only considers the existing rating. In order to show that the proposed algorithm is based on memory-based user collaboration filtering, item-based collaborative filtering and model based matrix factorization SVD, and SVD ++. Based on the above algorithm, the mean absolute error (MAE) and the root mean square error (RMSE) are calculated to evaluate the recommendation system with a score that combines sentiment scores with a system that only considers scores. When the evaluation index was MAE, it was improved by 0.059 for UBCF, 0.0862 for IBCF, 0.1012 for SVD and 0.188 for SVD ++. When the evaluation index is RMSE, UBCF is 0.0431, IBCF is 0.0882, SVD is 0.1103, and SVD ++ is 0.1756. As a result, it can be seen that the prediction performance of the evaluation point reflecting the sentiment score proposed in this paper is superior to that of the conventional evaluation method. In other words, in this paper, it is confirmed that the collaborative filtering that reflects the sentiment score of the user review shows superior accuracy as compared with the conventional type of collaborative filtering that only considers the quantitative score. We then attempted paired t-test validation to ensure that the proposed model was a better approach and concluded that the proposed model is better. In this study, to overcome limitations of previous researches that judge user's sentiment only by quantitative rating score, the review was numerically calculated and a user's opinion was more refined and considered into the recommendation system to improve the accuracy. The findings of this study have managerial implications to recommendation system developers who need to consider both quantitative information and qualitative information it is expect. The way of constructing the combined system in this paper might be directly used by the developers.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.35 no.1
• /
• pp.10-24
• /
• 2017

The research takes note of the formation process and settling period of Gwandong-Palkyung(關東八景, Eight Sites of Eastern Korea), the representative palgyeong(prominent eight sites) and jipgyeong(集景, landscape collection of scenic beauty), and investigates the time of formation regarding the palkyung and jipgeyong of Gwandong's scenic beauty through the analysis and interpretation of bibliographic data, and reference data. The result of the study is as follows. As the first document that records the terminology of "Gwandong-Palkyung" is "Daphongeunggil(答洪應吉)" of Yi, Hwang(李滉), Gwandong-Palkyung is inferred to be settled within the recognition of the people even before the 16th century. The geographic analysis result including "Sinjeung Donggukyeojiseungram(新增東國輿地勝覽)", Gwandong-Palkyung expanded as Gwandong-Sipkyung in early to middle of the 16th century. The first confirmed landscape collection regarding Gwandong-Palkyung in this study is confirmed in Shin Zup(申楫)'s "Yeonggwandong-Palkyung(詠關東八景)", thus, the terminology of Gwandong-Palkyung existed before 16th century at the latest. The settlement time of current "Palkyung" collection is estimated to be early 17th century at the latest. Poetries regarding Gwandong-Palkyung, and the frequency on the appearance of Gwandong scenic beauties are analyzed as making clear of the concentrated phenomenon on the sceneries of Gwandong-Palkyung. On the other hand, the collection of Gwandong-Palkyung in the domain of arts is confirmed initially in the ${\ll}$Gwandongpalkyungdobyeong(關東八景圖屛)${\gg}$ of Heo, Pil(許泌). Gwandong-Palkyung, expressed as the actual scene landscape painting shows similar tendencies of the conditions in the jipgyeong from the poetry, but the appearance rate of the painting subject was more prominent in visual solidarity and cohesion due to the reflection of the importance on icon(圖像) of the art works produced with particular meaning in the case of fixed ideal system. From late Joseon to modern times, ${\ll}$palpokbyeongpung(八幅屛風)${\gg}$ of various forms of folk painting is a corroborative evidence notifying that the cultural phenomenon of Gwandong-Palkyung has entered the universal period of embrace. Also, the 13 scenic beauties of Gangwon-Do appearing in the games of Namseungdo and Myeongseungyuramdo include Gwandong-Palkyung, which confirms the settlement of Gwandog-Palkyung even within the culture of games in late Joseon. Such results demonstrate the existence of awareness regarding Gwandong-Palkyung from the first half of the 15th century, which is presumed to have completely settled in the 17th century through the continuous development of formative process in the 16th century. Ultimately, Gwandong-Palkyung is the concrete formation of regional scenic beauties that individually gained its reputations as scenery from the Koryo Dynasty to late 17th century. Gwandong-Palkyung of the scenic beauty of Gwandong is a unique cultural scenery of the region that have germinated and formed through the process of cutting and polishing of long time to collect the best eight of scenic beauty from the many participation of sightseeing culture.