Efficient Topic Modeling by Mapping Global and Local Topics (전역 토픽의 지역 매핑을 통한 효율적 토픽 모델링 방안)
-
- Journal of Intelligence and Information Systems
- /
- v.23 no.3
- /
- pp.69-94
- /
- 2017
Recently, increase of demand for big data analysis has been driving the vigorous development of related technologies and tools. In addition, development of IT and increased penetration rate of smart devices are producing a large amount of data. According to this phenomenon, data analysis technology is rapidly becoming popular. Also, attempts to acquire insights through data analysis have been continuously increasing. It means that the big data analysis will be more important in various industries for the foreseeable future. Big data analysis is generally performed by a small number of experts and delivered to each demander of analysis. However, increase of interest about big data analysis arouses activation of computer programming education and development of many programs for data analysis. Accordingly, the entry barriers of big data analysis are gradually lowering and data analysis technology being spread out. As the result, big data analysis is expected to be performed by demanders of analysis themselves. Along with this, interest about various unstructured data is continually increasing. Especially, a lot of attention is focused on using text data. Emergence of new platforms and techniques using the web bring about mass production of text data and active attempt to analyze text data. Furthermore, result of text analysis has been utilized in various fields. Text mining is a concept that embraces various theories and techniques for text analysis. Many text mining techniques are utilized in this field for various research purposes, topic modeling is one of the most widely used and studied. Topic modeling is a technique that extracts the major issues from a lot of documents, identifies the documents that correspond to each issue and provides identified documents as a cluster. It is evaluated as a very useful technique in that reflect the semantic elements of the document. Traditional topic modeling is based on the distribution of key terms across the entire document. Thus, it is essential to analyze the entire document at once to identify topic of each document. This condition causes a long time in analysis process when topic modeling is applied to a lot of documents. In addition, it has a scalability problem that is an exponential increase in the processing time with the increase of analysis objects. This problem is particularly noticeable when the documents are distributed across multiple systems or regions. To overcome these problems, divide and conquer approach can be applied to topic modeling. It means dividing a large number of documents into sub-units and deriving topics through repetition of topic modeling to each unit. This method can be used for topic modeling on a large number of documents with limited system resources, and can improve processing speed of topic modeling. It also can significantly reduce analysis time and cost through ability to analyze documents in each location or place without combining analysis object documents. However, despite many advantages, this method has two major problems. First, the relationship between local topics derived from each unit and global topics derived from entire document is unclear. It means that in each document, local topics can be identified, but global topics cannot be identified. Second, a method for measuring the accuracy of the proposed methodology should be established. That is to say, assuming that global topic is ideal answer, the difference in a local topic on a global topic needs to be measured. By those difficulties, the study in this method is not performed sufficiently, compare with other studies dealing with topic modeling. In this paper, we propose a topic modeling approach to solve the above two problems. First of all, we divide the entire document cluster(Global set) into sub-clusters(Local set), and generate the reduced entire document cluster(RGS, Reduced global set) that consist of delegated documents extracted from each local set. We try to solve the first problem by mapping RGS topics and local topics. Along with this, we verify the accuracy of the proposed methodology by detecting documents, whether to be discerned as the same topic at result of global and local set. Using 24,000 news articles, we conduct experiments to evaluate practical applicability of the proposed methodology. In addition, through additional experiment, we confirmed that the proposed methodology can provide similar results to the entire topic modeling. We also proposed a reasonable method for comparing the result of both methods.
Korea-China FTA entered into force on the 20th of December 2015, and one year elapsed after its effectuation as the FTA with China, our country's largest trading partner. Therefore, this study looks at the trends of air transport trade between Korea and China, and examines the contents of concessions to the air transport services sector in Korea-China FTA, and analyzes the impact on the air transport sector by Korea-China FTA, and proposes our country's aviation policy direction in order to respond to such impact. In 2016 the trends of air transport trade between Korea and China are as follows : The export amount of air transport trade to China was 40.03 billion dollars, down by 9.3% from the last year, and occupied 32.2% of the total export amount to China. The import amount of air transport trade from China was 24.26 billion dollars, down by 9.1% from the last year, and occupied 27.7% of the total import amount from China. The contents of concessions to the air transport services sector in Korea-China FTA are as follows : China made concessions to the aircraft repair and maintenance services and the computer reservation system services with limitations on market access and national treatment in the air transport services sector of the China Schedule of Specific Commitments of Korea-China FTA Chapter 8 Annex. Korea made concessions to the computer reservation system services, selling and marketing of air transport services, and aircraft repair and maintenance without limitations on market access and national treatment in the air transport services sector of the Korea Schedule of Specific Commitments of Korea-China FTA Chapter 8 Annex. The impact on the air transport sector by Korea-China FTA are as follows : As for the impact on the air passenger market, in 2016 the arrival passengers of the international flight from China were 9.96 million, up by 20.6% from the last year, and the departure passengers to China were 9.90 million, up by 34.8% from the last year. As for the impact on the air cargo market, in 2016 the exported goods volumes of air cargo to China were 105,220.2 tons, up by 6.6% from the last year, and imported goods volumes from China were 133,750.9 tons, up by 12.3% from the last year. Among the major items of exported air cargo to China, the exported goods volumes of benefited items in the Tariff Schedule of China of Korea-China FTA were increased, and among the major items of imported air cargo from China, the imported goods volumes of benefited items in the Tariff Schedule of Korea of Korea-China FTA were increased. As for the impact on the logistics market, in 2016 the handling performance of exported air cargo to China by domestic forwarders were 119,618 tons, down by 2.1% from the last year, and the handling performance of imported air cargo from China were 79,430 tons, down by 4.4% from the last year. In 2016 the e-commerce export amount to China were 109.16 million dollars, up by 27.7% from the last year, and the e-commerce import amount from China were 89.43 million dollars, up by 72% from the last year. The author proposes the aviation policy direction of Korea according to Korea-China FTA as follows : First, the open skies between Korea and China shall be pushed ahead. In June 2006 Korea and China concluded the open skies agreement within the scope of the third freedom and fourth freedom of the air for passenger and cargo in Sandong Province and Hainan Province of China, and agreed the full open skies of flights between the two countries from the summer season in 2010. However, China protested against the interpretation of the draft of the memorandum of understanding to the air services agreement, therefore the further open skies did not take place. Through the separate aviation talks with China from Korea-China FTA, the gradual and selective open skies of air passenger market and air cargo market shall be pushed ahead. Second, the competitiveness of air transport industry and airport shall be secured. As for the strengthening methods of the competitiveness of Korea's air transport industry, the support system for the strengthening of national air carriers' competitiveness shall be prepared, and the new basis for competition of national air carriers shall be made, and the strategic network based on national interest shall be built. As for the strengthening methods of the competitiveness of Korea's airports, particularly Incheon Airport, the competitiveness of the network for aviation demand creation shall be strengthened, and the airport facilities and safety infrastructure shall be expanded, and the new added value through the airport shall be created, and the world's No.1 level of services shall be maintained. Third, the competitiveness of aviation logistics enterprises shall be strengthened. As for the strengthening methods of the competitiveness of Korea's aviation logistics enterprises, as the upbringing strategy of higher added value in response to the industry trends changes, the new logistics market shall be developed, and the logistics infrastructure shall be expanded, and the logistics professionals shall be trained. Additionally, as the expanding strategy of global logistics market, the support system for overseas investment of logistics enterprises shall be built, and according to expanding the global transport network, the international cooperation shall be strengthened, and the network infrastructure shall be secured. As for the strengthening methods of aviation logistics competitiveness of Incheon Airport, the enterprises' demand of moving in the logistics complex shall be responded, and the comparative advantage in the field of new growth cargo shall be preoccupied, and the logistics hub's capability shall be strengthened, and the competitiveness of cargo processing speed in the airport shall be advanced. Forth, in the subsequent negotiation of Korea-China FTA, the further opening of air transport services sector shall be secured. In the subsequent negotiation being initiated within two years after entry into force of Korea-China FTA, it is necessary to ask for the further opening of the concessions of computer reservation system services, and aircraft repair and maintenance services in which the concessions level of air transport services sector by China is insufficient compared to the concessions level in the existing FTA concluded by China. In conclusion, in order to respond to the impact on Korea's air passenger market, air cargo market and aviation logistics market by Korea-China FTA, the following policy tasks shall be pushed ahead : Taking into consideration of national air carriers' competitiveness and nation's benefits, the gradual and selective open skies shall be pushed ahead, and the support system to strengthen the competitiveness of air transport industry and airport shall be built, and entry into aviation logistics market by logistics enterprises shall be expanded, and the preparations to ask for the further opening of air transport services sector, low in the concessions level by China shall be made.
HSDPA (High-Speed Downlink Packet Access) is a 3.5-generation asynchronous mobile communications service based on the third generation of W-CDMA. In Korea, it is mainly provided in through videophone service. Because of the diffusion of more powerful and diversified services, along with steep advances in mobile communications technology, consumers demand a wide range of choices. However, because of the variety of technologies, which tend to overflow the market regardless of consumer preferences, consumers feel increasingly confused. Therefore, we should not adopt strategies that focus only on developing new technology on the assumption that new technologies are next-generation projects. Instead, we should understand the process by which consumers accept new forms of technology and devise schemes to lower market entry barriers through strategies that enable developers to understand and provide what consumers really want. In the Technology Acceptance Model (TAM), perceived usefulness and perceived ease of use are suggested as the most important factors affecting the attitudes of people adopting new technologies (Davis, 1989; Taylor and Todd, 1995; Venkatesh, 2000; Lee et al., 2004). Perceived usefulness is the degree to which a person believes that a particular technology will enhance his or her job performance. Perceived ease of use is the degree of subjective belief that using a particular technology will require little physical and mental effort (Davis, 1989; Morris and Dillon, 1997; Venkatesh, 2000). Perceived pleasure and perceived usefulness have been shown to clearly affect attitudes toward accepting technology (Davis et al., 1992). For example, pleasure in online shopping has been shown to positively impact consumers' attitudes toward online sellers (Eighmey and McCord, 1998; Mathwick, 2002; Jarvenpaa and Todd, 1997). The perceived risk of customers is a subjective risk, which is distinguished from an objective probabilistic risk. Perceived risk includes a psychological risk that consumers perceive when they choose brands, stores, and methods of purchase to obtain a particular item. The ability of an enterprise to revolutionize products depends on the effective acquisition of knowledge about new products (Bierly and Chakrabarti, 1996; Rothwell and Dodgson, 1991). Knowledge acquisition is the ability of a company to perceive the value of novelty and technology of the outside (Cohen and Levinthal, 1990), to evaluate the outside technology that has newly appeared (Arora and Gambaradella, 1994), and to predict the future evolution of technology accurately (Cohen and Levinthal, 1990). Consumer innovativeness is the degree to which an individual adopts innovation earlier than others in the social system (Lee, Ahn, and Ha, 2001; Gatignon and Robertson, 1985). That is, it shows how fast and how easily consumers adopt new ideas. Innovativeness is regarded as important because it has a significant effect on whether consumers adopt new products and on how fast they accept new products (Midgley and Dowling, 1978; Foxall, 1988; Hirschman, 1980). We conducted cross-national comparative research using the TAM model, which empirically verified the relationship between the factors that affect attitudes - perceived usefulness, ease of use, perceived pleasure, perceived risk, innovativeness, and perceived level of knowledge management - and attitudes toward HSDPA service. We also verified the relationship between attitudes and usage intention for the purpose of developing more effective methods of management for HSDPA service providers. For this research, 346 questionnaires were distributed among 350 students in the Republic of Korea. Because 26 of the returned questionnaires were inconsistent or had missing data, 320 questionnaires were used in the hypothesis tests. In UK, 192 of the total 200 questionnaires were retrieved, and two incomplete ones were discarded, bringing the total to 190 questionnaires used for statistical analysis. The results of the overall model analysis are as follows: Republic of Korea x2=333.27(p=0.0), NFI=0.88, NNFI=0.88, CFI=0.91, IFI=0.91, RMR=0.054, GFI=0.90, AGFI=0.84, UK x2=176.57(p=0.0), NFI=0.88, NNFI=0.90, CFI=0.93, IFI=0.93, RMR=0.062, GFI=0.90, AGFI=0.84. From the results of the hypothesis tests of Korean consumers about the relationship between factors that affect intention to use HSDPA services and attitudes, we can conclude that perceived usefulness, ease of use, pleasure, a high level of knowledge management, and innovativeness promote positive attitudes toward HSDPA mobile phones. However, ease of use and perceived pleasure did not have a direct effect on intention to use HSDPA service. This may have resulted from the fact that the use of video phones is not necessary for everyday life yet. Moreover, it has been shown that attitudes toward HSDPA video phones are directly correlated with usage intention, which means that perceived usefulness, ease of use, pleasure, a high level of knowledge management, and innovativeness. These relationships form the basis of the intention to buy, contributing to a situation in which consumers decide to choose carefully. A summary of the results of the hypothesis tests of European consumers revealed that perceived usefulness, pleasure, risk, and the level of knowledge management are factors that affect the formation of attitudes, while ease of use and innovativeness do not have an effect on attitudes. In particular, with regard to the effect value, perceived usefulness has the largest effect on attitudes, followed by pleasure and knowledge management. On the contrary, perceived risk has a smaller effect on attitudes. In the Asian model, ease of use and perceived pleasure were found not to have a direct effect on intention to use. However, because attitudes generally affect the intention to use, perceived usefulness, pleasure, risk, and knowledge management may be considered key factors in attitude development from which usage intention arises. In conclusion, perceived usefulness, pleasure, and the level of knowledge management have an effect on attitude formation in both Asian and European consumers, and such attitudes shape these consumers' intention to use. Furthermore, the hypotheses that ease of use and perceived pleasure affect usage intention are rejected. However, ease of use, perceived risk, and innovativeness showed different results. Perceived risk had no effect on attitude formation among Asians, while ease of use and innovativeness had no effect on attitudes among Europeans.