• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.53-77
• /
• 2012

This study analyses the difference of contents and tones of arguments among three Korean major newspapers, the Kyunghyang Shinmoon, the HanKyoreh, and the Dong-A Ilbo. It is commonly accepted that newspapers in Korea explicitly deliver their own tone of arguments when they talk about some sensitive issues and topics. It could be controversial if readers of newspapers read the news without being aware of the type of tones of arguments because the contents and the tones of arguments can affect readers easily. Thus it is very desirable to have a new tool that can inform the readers of what tone of argument a newspaper has. This study presents the results of clustering and classification techniques as part of text mining analysis. We focus on six main subjects such as Culture, Politics, International, Editorial-opinion, Eco-business and National issues in newspapers, and attempt to identify differences and similarities among the newspapers. The basic unit of text mining analysis is a paragraph of news articles. This study uses a keyword-network analysis tool and visualizes relationships among keywords to make it easier to see the differences. Newspaper articles were gathered from KINDS, the Korean integrated news database system. KINDS preserves news articles of the Kyunghyang Shinmun, the HanKyoreh and the Dong-A Ilbo and these are open to the public. This study used these three Korean major newspapers from KINDS. About 3,030 articles from 2008 to 2012 were used. International, national issues and politics sections were gathered with some specific issues. The International section was collected with the keyword of 'Nuclear weapon of North Korea.' The National issues section was collected with the keyword of '4-major-river.' The Politics section was collected with the keyword of 'Tonghap-Jinbo Dang.' All of the articles from April 2012 to May 2012 of Eco-business, Culture and Editorial-opinion sections were also collected. All of the collected data were handled and edited into paragraphs. We got rid of stop-words using the Lucene Korean Module. We calculated keyword co-occurrence counts from the paired co-occurrence list of keywords in a paragraph. We made a co-occurrence matrix from the list. Once the co-occurrence matrix was built, we used the Cosine coefficient matrix as input for PFNet(Pathfinder Network). In order to analyze these three newspapers and find out the significant keywords in each paper, we analyzed the list of 10 highest frequency keywords and keyword-networks of 20 highest ranking frequency keywords to closely examine the relationships and show the detailed network map among keywords. We used NodeXL software to visualize the PFNet. After drawing all the networks, we compared the results with the classification results. Classification was firstly handled to identify how the tone of argument of a newspaper is different from others. Then, to analyze tones of arguments, all the paragraphs were divided into two types of tones, Positive tone and Negative tone. To identify and classify all of the tones of paragraphs and articles we had collected, supervised learning technique was used. The Na$\ddot{i}$ve Bayesian classifier algorithm provided in the MALLET package was used to classify all the paragraphs in articles. After classification, Precision, Recall and F-value were used to evaluate the results of classification. Based on the results of this study, three subjects such as Culture, Eco-business and Politics showed some differences in contents and tones of arguments among these three newspapers. In addition, for the National issues, tones of arguments on 4-major-rivers project were different from each other. It seems three newspapers have their own specific tone of argument in those sections. And keyword-networks showed different shapes with each other in the same period in the same section. It means that frequently appeared keywords in articles are different and their contents are comprised with different keywords. And the Positive-Negative classification showed the possibility of classifying newspapers' tones of arguments compared to others. These results indicate that the approach in this study is promising to be extended as a new tool to identify the different tones of arguments of newspapers.

• KDI Journal of Economic Policy
• /
• v.14 no.2
• /
• pp.109-153
• /
• 1992

This paper estimates a translog cost function for the Korea's banking industry and derives various implications on the prospect for the Korean banking structure in the future based on the estimated efficiency indicators for the banking sector. The Korean banking industry is permitted to operate trust business to the full extent and the security business to a limited extent, while it is formally subjected to the strict, specialized banking system. Security underwriting and investment businesses are allowed in a very limited extent only for stocks and bonds of maturity longer than three year and only up to 100 percent of the bank paid-in capital. Until the end of 1991, the ceiling was only up to 25 percent of the total balance of the demand deposits. However, they are prohibited from the security brokerage business. While the in-house integration of security businesses with the traditional business of deposit and commercial lending is restrictively regulated as such, Korean banks can enter the security business by establishing subsidiaries in the industry. This paper, therefore, estimates the efficiency indicators as well as the cost functions, identifying the in-house integrated trust business and security investment business as important banking activities, for various cases where both the production and the intermediation function approaches in modelling the financial intermediaries are separately applied, and the banking businesses of deposit, lending and security investment as one group and the trust businesses as another group are separately and integrally analyzed. The estimation results of the efficiency indicators for various cases are summarized in Table 1 and Table 2. First, security businesses exhibit economies of scale but also economies of scope with traditional banking activities, which implies that in-house integration of the banking and security businesses may not be a nonoptimal banking structure. Therefore, this result further implies that the transformation of Korea's banking system from the current, specialized system to the universal banking system will not impede the improvement of the banking industry's efficiency. Second, the lending businesses turn out to be subjected to diseconomies of scale, while exhibiting unclear evidence for economies of scope. In sum, it implies potential efficiency gain of the continued in-house integration of the lending activity. Third, the continued integration of the trust businesses seems to contribute to improving the efficiency of the banking businesses, since the trust businesses exhibit economies of scope. Fourth, deposit services and fee-based activities, such as foreign exchange and credit card businesses, exhibit economies of scale but constant returns to scope, which implies, the possibility of separating those businesses from other banking and trust activities. The recent trend of the credit card business being operated separately from other banking activities by an independent identity in Korea as well as in the global banking market seems to be consistent with this finding. Then, how can the possibility of separating deposit services from the remaining activities be interpreted? If one insists a strict definition of commercial banking that is confined to deposit and commercial lending activities, separating the deposit service will suggest a resolution or a disappearance of banking, itself. Recently, however, there has been a suggestion that separating banks' deposit and lending activities by allowing a depository institution which specialize in deposit taking and investing deposit fund only in the safest securities such as government securities to administer the deposit activity will alleviate the risk of a bank run. This method, in turn, will help improve the safety of the payment system (Robert E. Litan, What should Banks Do? Washington, D.C., The Brookings Institution, 1987). In this context, the possibility of separating the deposit activity will imply that a new type of depository institution will arise naturally without contradicting the efficiency of the banking businesses, as the size of the banking market grows in the future. Moreover, it is also interesting to see additional evidences confirming this statement that deposit taking and security business are cost complementarity but deposit taking and lending businesses are cost substitute (see Table 2 for cost complementarity relationship in Korea's banking industry). Finally, it has been observed that the Korea's banking industry is lacking in the characteristics of natural monopoly. Therefore, it may not be optimal to encourage the merger and acquisition in the banking industry only for the purpose of improving the efficiency.

• Tuberculosis and Respiratory Diseases
• /
• v.42 no.6
• /
• pp.923-933
• /
• 1995

Background: Pleural abnormality is the the most common respiratory change caused by asbestos dust inhalation and also develop other asbestos related disease after cessation of asbestos exposure. So we conducted epidemiologic study to investigate if the pleural abnormality is associated with pulmonary function change and what factors are influenced on pulmonary function impairment. Methods: Two hundred and twenty two asbestos workers from 9 industries using asbestos in Korea were selected to measure the concentration of sectional asbestos fiber. Ouestionnaire, chest X-ray, PFT were also performed. All the data were analyzed by student t-test and chi-square test using SAS. Regressional analysis was performed to evaluate important factors, for example smoking, exposure concentration, period and the existence of pleural thickening, affecting to the change of pulmonary function. Results: 1) All nine industries except two, airborn asbestos fiber concentration was less than an average permissible concentration. PFT was performed on 222 workers and the percentage of male was 88.3%, their mean age was $41{\pm}9$ years old, and the duration of asbestos exposure was $10.6{\pm}7.8$ yrs. 2) The chest X-ray showed normal(89.19%), pulmonary Tb(inactive)(2.7%), pleral thickening (7.66%), suspected reticulonodular shadow(0.9%). 3) The mean values of height, smoking status, concentration of asbestos fiberwere not different between the subjects with pleural thickening and others, but age, cumulative pack-years, the duration of asbestos exposure were higher in subjects with pleural thickening. 4) All the PFT indices were lower in the subjects with pleural thickening than in the subjects without pleural thickening. 5) Simple regression analysis showed there was a significant correlation between $FEF_{75}$ which is sensitive in small airway obstruction and cumulative smoking pack-years, the duration of asbestos exposure and the concentration of asbestos fiber. 6) Multiple regression analysis showed all the pulmonary function indices were decreased as the increase of cumulative smoking pack-years and especially in the indices those are sensitive in small airway obstruction. Pleural thickening was associated with reduction in FVC, $FEV_1$, PEFR and $FEF_{25}$. Conclusion: The more concentration of asbestos fiber and the more duration of asbestos exposure, the greater reduction in $FEF_{50}$, $FEF_{75}$. Therefore PFT was important in the evaluation of early detection for small airway obstruction. Furthermore pleural thickening without asbesto-related parenchymal lung disease is associated with reduction in pulmonary function.

• The Korean Journal of Air & Space Law and Policy
• /
• v.21 no.1
• /
• pp.169-189
• /
• 2006

In 2007, KSLV(Korea Small Launching Vehicle) that we made at Goheung National Space Center is going to launch and promotes of our space exploration systematically and 'Space Exploration Promotion Act' was enter into force. 'Space Exploration Promotion Act' article 3, section 1, as is prescribing "Korean government keeps the space treaties contracted with other countries and international organizations and pursues after peaceful uses of outer space." The representative international treaties are Outer Space Treaty (1967) and Liability Convention (1972) etc. In Liability convention article 2, "A launching State shall be absolutely liable to pay compensation for damage caused by its space object on the surface of the earth or to aircraft in flight. The important content of the art. 2 is the responsible entity is the 'State' not the 'Company'. According by Korean Space Exploration Act art. 14, person who launches space objects according to art. 8 and art. 11 must bear the liability for damages owing to space accidents of the space objects. Could Korean government apply the Products Liability Act which is enter into force from July 1, 2002 to space launching person? And what is the contact type between Korea Aerospace Research Institute(KARl) and Russia manufacturer. Is that a Co-Development contract or Licence Product contract? And there is no exemption clause to waive the Russia manufacturer's liability which we could find it from other similar contract condition. If there is no exemption clause to the Russia manufacturer, could we apply the Korean Products Liability Act to Russia one? The most important legal point is whether we could apply the Korean Products Liability Act to the main component company. According by the art. 17 of the contract between KARl and the company, KARl already apply the Products Liability Act to the main component company. For reference, we need to examine the Appalachian Insurance co. v. McDonnell Douglas case, this case is that long distance electricity communication satellite of Western Union Telegraph company possessions fails on track entry. In Western Union's insurance company supplied to Western Union with insurance of $ 105 millions, which has the satellite regard as entirely damage. Five insurance companies -Appalachian insurance company, Commonwealth insurance company, Industrial Indemnity, Mutual Marine Office, Northbrook Excess & Surplus insurance company- went to court against McDonnell Douglases, Morton Thiokol and Hitco company to inquire for fault and strict liability of product. By the Appalachian Insurance co. v. McDonnell Douglas case, KARl should waiver the main component's product liability burden. And we could study the possibility of the adapt 'Government Contractor Defense' theory to the main component company.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.1-17
• /
• 2015

In this paper, we report what we have observed with regards to a prediction model for the military based on enlisted men's internal(cumulative records) and external data(SNS data). This work is significant in the military's efforts to supervise them. In spite of their effort, many commanders have failed to prevent accidents by their subordinates. One of the important duties of officers' work is to take care of their subordinates in prevention unexpected accidents. However, it is hard to prevent accidents so we must attempt to determine a proper method. Our motivation for presenting this paper is to mate it possible to predict accidents using enlisted men's internal and external data. The biggest issue facing the military is the occurrence of accidents by enlisted men related to maladjustment and the relaxation of military discipline. The core method of preventing accidents by soldiers is to identify problems and manage them quickly. Commanders predict accidents by interviewing their soldiers and observing their surroundings. It requires considerable time and effort and results in a significant difference depending on the capabilities of the commanders. In this paper, we seek to predict accidents with objective data which can easily be obtained. Recently, records of enlisted men as well as SNS communication between commanders and soldiers, make it possible to predict and prevent accidents. This paper concerns the application of data mining to identify their interests, predict accidents and make use of internal and external data (SNS). We propose both a topic analysis and decision tree method. The study is conducted in two steps. First, topic analysis is conducted through the SNS of enlisted men. Second, the decision tree method is used to analyze the internal data with the results of the first analysis. The dependent variable for these analysis is the presence of any accidents. In order to analyze their SNS, we require tools such as text mining and topic analysis. We used SAS Enterprise Miner 12.1, which provides a text miner module. Our approach for finding their interests is composed of three main phases; collecting, topic analysis, and converting topic analysis results into points for using independent variables. In the first phase, we collect enlisted men's SNS data by commender's ID. After gathering unstructured SNS data, the topic analysis phase extracts issues from them. For simplicity, 5 topics(vacation, friends, stress, training, and sports) are extracted from 20,000 articles. In the third phase, using these 5 topics, we quantify them as personal points. After quantifying their topic, we include these results in independent variables which are composed of 15 internal data sets. Then, we make two decision trees. The first tree is composed of their internal data only. The second tree is composed of their external data(SNS) as well as their internal data. After that, we compare the results of misclassification from SAS E-miner. The first model's misclassification is 12.1%. On the other hand, second model's misclassification is 7.8%. This method predicts accidents with an accuracy of approximately 92%. The gap of the two models is 4.3%. Finally, we test if the difference between them is meaningful or not, using the McNemar test. The result of test is considered relevant.(p-value : 0.0003) This study has two limitations. First, the results of the experiments cannot be generalized, mainly because the experiment is limited to a small number of enlisted men's data. Additionally, various independent variables used in the decision tree model are used as categorical variables instead of continuous variables. So it suffers a loss of information. In spite of extensive efforts to provide prediction models for the military, commanders' predictions are accurate only when they have sufficient data about their subordinates. Our proposed methodology can provide support to decision-making in the military. This study is expected to contribute to the prevention of accidents in the military based on scientific analysis of enlisted men and proper management of them.

• Asia pacific journal of information systems
• /
• v.19 no.4
• /
• pp.125-148
• /
• 2009

UGC(User Generated Contents) is emerging as the center of e-business in the web 2.0 era. The trend reflects changing roles of users in production and consumption of contents on websites and helps us to understand new strategies of websites such as web portals and social network websites. Nowadays, we consume contents created by other non-professional users for both utilitarian (e.g., knowledge) and hedonic values (e.g., fun). Also, contents produced by ourselves (e.g., photo, video) are posted on websites so that our friends, family, and even the public can consume those contents. This means that non-professionals, who used to be passive audience in the past, are now creating contents and share their UGCs with others in the Web. Accessible media, tools, and applications have also reduced difficulty and complexity in the process of creating contents. Realizing that users create plenty of materials which are very interesting to other people, media companies (i.e., web portals and social networking websites) are adjusting their strategies and business models accordingly. Increased demand of UGC may lead to website visits which are the source of benefits from advertising. Therefore, they put more efforts into making their websites open platforms where UGCs can be created and shared among users without technical and methodological difficulties. Many websites have increasingly adopted new technologies such as RSS and openAPI. Some have even changed the structure of web pages so that UGC can be seen several times to more visitors. This mainstream of UGCs on websites indicates that acquiring more UGCs and supporting participating users have become important things to media companies. Although those companies need to understand why general users have shown increasing interest in creating and posting contents and what is important to them in the process of productions, few research results exist in this area to address these issues. Also, behavioral process in creating video UGCs has not been explored enough for the public to fully understand it. With a solid theoretical background (i.e., theory of implementation intentions), parts of our proposed research model mirror the process of user behaviors in creating video contents, which consist of intention to upload, intention to edit, edit, and upload. In addition, in order to explain how those behavioral intentions are developed, we investigated influences of antecedents from three motivational perspectives (i.e., intrinsic, editing software-oriented, and website's network effect-oriented). First, from the intrinsic motivation perspective, we studied the roles of self-expression, enjoyment, and social attention in forming intention to edit with preferred editing software or in forming intention to upload video contents to preferred websites. Second, we explored the roles of editing software for non-professionals to edit video contents, in terms of how it makes production process easier and how it is useful in the process. Finally, from the website characteristic-oriented perspective, we investigated the role of a website's network externality as an antecedent of users' intention to upload to preferred websites. The rationale is that posting UGCs on websites are basically social-oriented behaviors; thus, users prefer a website with the high level of network externality for contents uploading. This study adopted a longitudinal research design; we emailed recipients twice with different questionnaires. Guided by invitation email including a link to web survey page, respondents answered most of questions except edit and upload at the first survey. They were asked to provide information about UGC editing software they mainly used and preferred website to upload edited contents, and then asked to answer related questions. For example, before answering questions regarding network externality, they individually had to declare the name of the website to which they would be willing to upload. At the end of the first survey, we asked if they agreed to participate in the corresponding survey in a month. During twenty days, 333 complete responses were gathered in the first survey. One month later, we emailed those recipients to ask for participation in the second survey. 185 of the 333 recipients (about 56 percentages) answered in the second survey. Personalized questionnaires were provided for them to remind the names of editing software and website that they reported in the first survey. They answered the degree of editing with the software and the degree of uploading video contents to the website for the past one month. To all recipients of the two surveys, exchange tickets for books (about 5,000~10,000 Korean Won) were provided according to the frequency of participations. PLS analysis shows that user behaviors in creating video contents are well explained by the theory of implementation intentions. In fact, intention to upload significantly influences intention to edit in the process of accomplishing the goal behavior, upload. These relationships show the behavioral process that has been unclear in users' creating video contents for uploading and also highlight important roles of editing in the process. Regarding the intrinsic motivations, the results illustrated that users are likely to edit their own video contents in order to express their own intrinsic traits such as thoughts and feelings. Also, their intention to upload contents in preferred website is formed because they want to attract much attention from others through contents reflecting themselves. This result well corresponds to the roles of the website characteristic, namely, network externality. Based on the PLS results, the network effect of a website has significant influence on users' intention to upload to the preferred website. This indicates that users with social attention motivations are likely to upload their video UGCs to a website whose network size is big enough to realize their motivations easily. Finally, regarding editing software characteristic-oriented motivations, making exclusively-provided editing software more user-friendly (i.e., easy of use, usefulness) plays an important role in leading to users' intention to edit. Our research contributes to both academic scholars and professionals. For researchers, our results show that the theory of implementation intentions is well applied to the video UGC context and very useful to explain the relationship between implementation intentions and goal behaviors. With the theory, this study theoretically and empirically confirmed that editing is a different and important behavior from uploading behavior, and we tested the behavioral process of ordinary users in creating video UGCs, focusing on significant motivational factors in each step. In addition, parts of our research model are also rooted in the solid theoretical background such as the technology acceptance model and the theory of network externality to explain the effects of UGC-related motivations. For practitioners, our results suggest that media companies need to restructure their websites so that users' needs for social interaction through UGC (e.g., self-expression, social attention) are well met. Also, we emphasize strategic importance of the network size of websites in leading non-professionals to upload video contents to the websites. Those websites need to find a way to utilize the network effects for acquiring more UGCs. Finally, we suggest that some ways to improve editing software be considered as a way to increase edit behavior which is a very important process leading to UGC uploading.

• The Korean Society of Law and Medicine
• /
• v.21 no.2
• /
• pp.105-162
• /
• 2020

In the pandemic of infectious disease, restrictions of individual liberty have been justified in the name of public health and public interest. In March 2020, the National Assembly of the Republic of Korea passed the revised bill of the 「Infectious Disease Control and Prevention Act.」 The revised bill newly established the legal basis for forced testing and disclosure of the information of confirmed cases, and also raised the penalties for violation of self-isolation and treatment refusal. This paper examines whether and how these individual liberty limiting clauses be justified, and if so on what ethical and philosophical grounds. The authors propose the theories of the philosophy of law related to the justifiability of liberty-limiting measures by the state and conceptualized the dual-aspect of applying the liberty-limiting principle to the infected patient. In COVID-19 pandemic crisis, the infected person became the 'Patient as Victim and Vector (PVV)' that posits itself on the overlapping area of 'harm to self' and 'harm to others.' In order to apply the liberty-limiting principle proposed by Joel Feinberg to a pandemic with uncertainties, it is necessary to extend the harm principle from 'harm' to 'risk'. Under the crisis with many uncertainties like COVID-19 pandemic, this shift from 'harm' to 'risk' justifies the state's preemptive limitation on individual liberty based on the precautionary principle. This, at the same time, raises concerns of overcriminalization, i.e., too much limitation of individual liberty without sufficient grounds. In this article, we aim to propose principles regarding how to balance between the precautionary principle for preemptive restrictions of liberty and the concerns of overcriminalization. Public health crisis such as the COVID-19 pandemic requires a population approach where the 'population' rather than an 'individual' works as a unit of analysis. We propose the second expansion of the harm principle to be applied to 'population' in order to deal with the public interest and public health. The new concept 'risk to population,' derived from the two arguments stated above, should be introduced to explain the public health crisis like COVID-19 pandemic. We theorize 'the extended harm principle' to include the 'risk to population' as a third liberty-limiting principle following 'harm to others' and 'harm to self.' Lastly, we examine whether the restriction of liberty of the revised 「Infectious Disease Control and Prevention Act」 can be justified under the extended harm principle. First, we conclude that forced isolation of the infected patient could be justified in a pandemic situation by satisfying the 'risk to the population.' Secondly, the forced examination of COVID-19 does not violate the extended harm principle either, based on the high infectivity of asymptomatic infected people to others. Thirdly, however, the provision of forced treatment can not be justified, not only under the traditional harm principle but also under the extended harm principle. Therefore it is necessary to include additional clauses in the provision in order to justify the punishment of treatment refusal even in a pandemic.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.1-25
• /
• 2020

Sentiment Analysis (SA) is a Natural Language Processing (NLP) task that analyzes the sentiments consumers or the public feel about an arbitrary object from written texts. Furthermore, Aspect-Based Sentiment Analysis (ABSA) is a fine-grained analysis of the sentiments towards each aspect of an object. Since having a more practical value in terms of business, ABSA is drawing attention from both academic and industrial organizations. When there is a review that says "The restaurant is expensive but the food is really fantastic", for example, the general SA evaluates the overall sentiment towards the 'restaurant' as 'positive', while ABSA identifies the restaurant's aspect 'price' as 'negative' and 'food' aspect as 'positive'. Thus, ABSA enables a more specific and effective marketing strategy. In order to perform ABSA, it is necessary to identify what are the aspect terms or aspect categories included in the text, and judge the sentiments towards them. Accordingly, there exist four main areas in ABSA; aspect term extraction, aspect category detection, Aspect Term Sentiment Classification (ATSC), and Aspect Category Sentiment Classification (ACSC). It is usually conducted by extracting aspect terms and then performing ATSC to analyze sentiments for the given aspect terms, or by extracting aspect categories and then performing ACSC to analyze sentiments for the given aspect category. Here, an aspect category is expressed in one or more aspect terms, or indirectly inferred by other words. In the preceding example sentence, 'price' and 'food' are both aspect categories, and the aspect category 'food' is expressed by the aspect term 'food' included in the review. If the review sentence includes 'pasta', 'steak', or 'grilled chicken special', these can all be aspect terms for the aspect category 'food'. As such, an aspect category referred to by one or more specific aspect terms is called an explicit aspect. On the other hand, the aspect category like 'price', which does not have any specific aspect terms but can be indirectly guessed with an emotional word 'expensive,' is called an implicit aspect. So far, the 'aspect category' has been used to avoid confusion about 'aspect term'. From now on, we will consider 'aspect category' and 'aspect' as the same concept and use the word 'aspect' more for convenience. And one thing to note is that ATSC analyzes the sentiment towards given aspect terms, so it deals only with explicit aspects, and ACSC treats not only explicit aspects but also implicit aspects. This study seeks to find answers to the following issues ignored in the previous studies when applying the BERT pre-trained language model to ACSC and derives superior ACSC models. First, is it more effective to reflect the output vector of tokens for aspect categories than to use only the final output vector of [CLS] token as a classification vector? Second, is there any performance difference between QA (Question Answering) and NLI (Natural Language Inference) types in the sentence-pair configuration of input data? Third, is there any performance difference according to the order of sentence including aspect category in the QA or NLI type sentence-pair configuration of input data? To achieve these research objectives, we implemented 12 ACSC models and conducted experiments on 4 English benchmark datasets. As a result, ACSC models that provide performance beyond the existing studies without expanding the training dataset were derived. In addition, it was found that it is more effective to reflect the output vector of the aspect category token than to use only the output vector for the [CLS] token as a classification vector. It was also found that QA type input generally provides better performance than NLI, and the order of the sentence with the aspect category in QA type is irrelevant with performance. There may be some differences depending on the characteristics of the dataset, but when using NLI type sentence-pair input, placing the sentence containing the aspect category second seems to provide better performance. The new methodology for designing the ACSC model used in this study could be similarly applied to other studies such as ATSC.

• Trans-
• /
• v.12
• /
• pp.51-79
• /
• 2022

This study investigates the methods for deriving colors which can serve as a reference to users such as designers and or contents creators who search for online images from the web portal sites using specific words for color planning and more. Two experiments were conducted in order to accomplish this. Digital scenery photos within the geographic scope of Korea were downloaded from web portal sites, and those photos were studied to find out what colors were used to describe daytime and nighttime. Machine learning was used as the study methodology to classify colors in daytime and nighttime, and KSCA was used to derive the color frequency of daytime and nighttime photos and to compare and analyze the two results. The results of classifying the colors of daytime and nighttime photos using machine learning show that, when classifying the colors by 51~100%, the area of daytime colors was approximately 2.45 times greater than that of nighttime colors. The colors of the daytime class were distributed by brightness with white as its center, while that of the nighttime class was distributed with black as its center. Colors that accounted for over 70% of the daytime class were 647, those over 70% of the nighttime class were 252, and the rest (31-69%) were 101. The number of colors in the middle area was low, while other colors were classified relatively clearly into day and night. The resulting color distributions in the daytime and nighttime classes were able to provide the borderline color values of the two classes that are classified by brightness. As a result of analyzing the frequency of digital photos using KSCA, colors around yellow were expressed in generally bright daytime photos, while colors around blue value were expressed in dark night photos. For frequency of daytime photos, colors on the upper 40% had low chroma, almost being achromatic. Also, colors that are close to white and black showed the highest frequency, indicating a large difference in brightness. Meanwhile, for colors with frequency from top 5 to 10, yellow green was expressed darkly, and navy blue was expressed brightly, partially composing a complex harmony. When examining the color band, various colors, brightness, and chroma including light blue, achromatic colors, and warm colors were shown, failing to compose a generally harmonious arrangement of colors. For the frequency of nighttime photos, colors in approximately the upper 50% are dark colors with a brightness value of 2 (Munsell signal). In comparison, the brightness of middle frequency (50-80%) is relatively higher (brightness values of 3-4), and the brightness difference of various colors was large in the lower 20%. Colors that are not cool colors could be found intermittently in the lower 8% of frequency. When examining the color band, there was a general harmonious arrangement of colors centered on navy blue. As the results of conducting the experiment using two methods in this study, machine learning could classify colors into two or more classes, and could evaluate how close an image was with certain colors to a certain class. This method cannot be used if an image cannot be classified into a certain class. The result of such color distribution would serve as a reference when determining how close a certain color is to one of the two classes when the color is used as a dominant color in the base or background color of a certain design. Also, when dividing the analyzed images into several classes, even colors that have not been used in the analyzed image can be determined to find out how close they are to a certain class according to the color distribution properties of each class. Nevertheless, the results cannot be used to find out whether a specific color was used in the class and by how much it was used. To investigate such an issue, frequency analysis was conducted using KSCA. The color frequency could be measured within the range of images used in the experiment. The resulting values of color distribution and frequency from this study would serve as references for color planning of digital design regarding natural scenery in the geographic scope of Korea. Also, the two experiments are meaningful attempts for searching the methods for deriving colors that can be a useful reference among numerous images for content creator users of the relevant field.

• Asia Marketing Journal
• /
• v.14 no.1
• /
• pp.99-130
• /
• 2012

Service failure and a poor service recovery may lead loyal customers to try to aggressively punish the service firm. We use perceived betrayal and desire for vengeance as the key constructs to understand customer retaliation. Perceived betrayal is defined as a customer's belief that a firm has intentionally violated what is normative in the context of their relationship. And the desire for vengeance is defined as the retaliatory feelings that consumers feel toward a firm, such as the desire to exert harm on the firm. The perceived betrayal and the desire for vengeance are key antecedents of retaliatory behaviors such as vindictive complaining, negative WOM and third-party complaining for publicity. The empirical results suggest that betrayal is a key motivational factor that lead customers to restore fairness by making use of all means, including retaliation. We also find that relationship quality has effect on a customer's response to a failure in service recovery. As the levels of relationship increases, a violation of the proper fairness has a stronger effect on the sense of betrayal experienced by customers. Considerable research has investigated consumer responses to dissatisfaction. But our study examine the response of outraged and highly frustrated consumers. We focus on emotional and behavioral processes that have not been covered by previous dissatisfaction researches and which are unique to outraged consumers caused by extremely dissatisfied purchase experience. It has recently been pointed out by various mass media that the customers not only have positive effects on the company performance but also put the company in crisis. It has often been reported that one customer's dissatisfaction, for example, never ends as it is, and it tends to grow for retaliating upon the company, depending on the level of seriousness of the dissatisfaction. This sometimes leads to a lawsuit against the company. Our study focuses on the customers' emotional and behavioral responses induced by their extreme dissatisfactions. We divided the customer groups into the customers with high relationship quality and the customers with low relationship quality, and the difference between two groups is examined. The objective of this study is to comprehend the causal relationship between the feeling of betrayal caused by the service failure and the retaliatory behavior triggered by the desire of revenge. Our study is divided into three parts. First, a causal relationship between perceived unfairness and the perceived betrayal and desire for revenge. Second, the effect of the perceived betrayal and desire for revenge on the retaliatory behavior is investigated. Finally, the moderating role of relationship quality in the causal relationship between the unfairness in service recovery and the perceived betrayal is analyzed. This study finds the following empirical results. The distributive unfairness, procedural unfairness and interactional unfairness had significant effects on the perceived betrayal. Especially, the perceived distributive unfairness results in the highest perceived betrayal. When the service company does not provide customers proper and sufficient compensation for the failure, they feel the strong sense of betrayal. And in the causal relationship between the perceived betrayal, desire for revenge and retaliatory behavior, the perceived betrayal has significant effects on e desire for revenge. In addition desire for revenge has significant effects on negative word of mouth, retaliatory complaining behavior and publicity of complaints through third group. Therefore the perceived unfairness has effects on retaliatory behavior through the mediation of the perceived betrayal and desire for revenge. Finally the moderating role of relationship quality was examined in the relationship between the unfairness and perceived betrayal. If the customers experienced the perceived unfairness in the process of service recovery, the customers with high relationship quality feel the stronger perceived betrayal than the customers with low relationship quality do. When they experience the double service failure, the customer group with high relationship quality accumulating the sense of trust feel the more perceived betrayal than the customer with low relationship quality who do not have strong trust. The contribution of this study is to find the effect of the service failure on the retaliatory behavior with the moderating roles of relationship quality. The dimensions of unfairness in service recovery is found to have differential effects on the perceived betrayal, desire for revenge. And these differential effect is moderated by the level of relationship quality.