• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.21-44
• /
• 2018

In recent years, the rapid development of internet technology and the popularization of smart devices have resulted in massive amounts of text data. Those text data were produced and distributed through various media platforms such as World Wide Web, Internet news feeds, microblog, and social media. However, this enormous amount of easily obtained information is lack of organization. Therefore, this problem has raised the interest of many researchers in order to manage this huge amount of information. Further, this problem also required professionals that are capable of classifying relevant information and hence text classification is introduced. Text classification is a challenging task in modern data analysis, which it needs to assign a text document into one or more predefined categories or classes. In text classification field, there are different kinds of techniques available such as K-Nearest Neighbor, Naïve Bayes Algorithm, Support Vector Machine, Decision Tree, and Artificial Neural Network. However, while dealing with huge amount of text data, model performance and accuracy becomes a challenge. According to the type of words used in the corpus and type of features created for classification, the performance of a text classification model can be varied. Most of the attempts are been made based on proposing a new algorithm or modifying an existing algorithm. This kind of research can be said already reached their certain limitations for further improvements. In this study, aside from proposing a new algorithm or modifying the algorithm, we focus on searching a way to modify the use of data. It is widely known that classifier performance is influenced by the quality of training data upon which this classifier is built. The real world datasets in most of the time contain noise, or in other words noisy data, these can actually affect the decision made by the classifiers built from these data. In this study, we consider that the data from different domains, which is heterogeneous data might have the characteristics of noise which can be utilized in the classification process. In order to build the classifier, machine learning algorithm is performed based on the assumption that the characteristics of training data and target data are the same or very similar to each other. However, in the case of unstructured data such as text, the features are determined according to the vocabularies included in the document. If the viewpoints of the learning data and target data are different, the features may be appearing different between these two data. In this study, we attempt to improve the classification accuracy by strengthening the robustness of the document classifier through artificially injecting the noise into the process of constructing the document classifier. With data coming from various kind of sources, these data are likely formatted differently. These cause difficulties for traditional machine learning algorithms because they are not developed to recognize different type of data representation at one time and to put them together in same generalization. Therefore, in order to utilize heterogeneous data in the learning process of document classifier, we apply semi-supervised learning in our study. However, unlabeled data might have the possibility to degrade the performance of the document classifier. Therefore, we further proposed a method called Rule Selection-Based Ensemble Semi-Supervised Learning Algorithm (RSESLA) to select only the documents that contributing to the accuracy improvement of the classifier. RSESLA creates multiple views by manipulating the features using different types of classification models and different types of heterogeneous data. The most confident classification rules will be selected and applied for the final decision making. In this paper, three different types of real-world data sources were used, which are news, twitter and blogs.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.147-161
• /
• 2010

As broadcasting and communication are converged recently, communication is jointed to TV. TV viewing has brought about many changes. The IPTV (Internet Protocol Television) provides information service, movie contents, broadcast, etc. through internet with live programs + VOD (Video on demand) jointed. Using communication network, it becomes an issue of new business. In addition, new technical issues have been created by imaging technology for the service, networking technology without video cuts, security technologies to protect copyright, etc. Through this IPTV network, users can watch their desired programs when they want. However, IPTV has difficulties in search approach, menu approach, or finding programs. Menu approach spends a lot of time in approaching programs desired. Search approach can't be found when title, genre, name of actors, etc. are not known. In addition, inserting letters through remote control have problems. However, the bigger problem is that many times users are not usually ware of the services they use. Thus, to resolve difficulties when selecting VOD service in IPTV, a personalized service is recommended, which enhance users' satisfaction and use your time, efficiently. This paper provides appropriate programs which are fit to individuals not to save time in order to solve IPTV's shortcomings through filtering and recommendation-related system. The proposed recommendation system collects TV program information, the user's preferred program genres and detailed genre, channel, watching program, and information on viewing time based on individual records of watching IPTV. To look for these kinds of similarities, similarities can be compared by using ontology for TV programs. The reason to use these is because the distance of program can be measured by the similarity comparison. TV program ontology we are using is one extracted from TV-Anytime metadata which represents semantic nature. Also, ontology expresses the contents and features in figures. Through world net, vocabulary similarity is determined. All the words described on the programs are expanded into upper and lower classes for word similarity decision. The average of described key words was measured. The criterion of distance calculated ties similar programs through K-medoids dividing method. K-medoids dividing method is a dividing way to divide classified groups into ones with similar characteristics. This K-medoids method sets K-unit representative objects. Here, distance from representative object sets temporary distance and colonize it. Through algorithm, when the initial n-unit objects are tried to be divided into K-units. The optimal object must be found through repeated trials after selecting representative object temporarily. Through this course, similar programs must be colonized. Selecting programs through group analysis, weight should be given to the recommendation. The way to provide weight with recommendation is as the follows. When each group recommends programs, similar programs near representative objects will be recommended to users. The formula to calculate the distance is same as measure similar distance. It will be a basic figure which determines the rankings of recommended programs. Weight is used to calculate the number of watching lists. As the more programs are, the higher weight will be loaded. This is defined as cluster weight. Through this, sub-TV programs which are representative of the groups must be selected. The final TV programs ranks must be determined. However, the group-representative TV programs include errors. Therefore, weights must be added to TV program viewing preference. They must determine the finalranks.Based on this, our customers prefer proposed to recommend contents. So, based on the proposed method this paper suggested, experiment was carried out in controlled environment. Through experiment, the superiority of the proposed method is shown, compared to existing ways.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.46 no.5
• /
• pp.10-21
• /
• 2018

This study used text mining methodology to focus on the perceptions of the landscape embedded in text that users spontaneously uploaded to the "Taean Travel"blogpost. The study area is the Taean Coast National Park. Most of the places that are searched by 'Taean Travel' on the blog were located in the Taean Coast National Park. We conducted a network analysis on the top three places and extracted keywords related to the landscape. Finally, using a centrality and cohesion analysis, we derived landscape perceptions and the major characteristics of those landscapes. As a result of the study, it was possible to identify the main tourist places in Taean, the individual landscape experience, and the landscape perception in specific places. There were three different types of landscape characteristics: atmosphere-related keywords, which appeared in Kkotji Beach, symbolic image-related keywords appeared in Sinduri Coastal Sand Dune, and landscape objects-related appeared in Manlipo Beach. It can be inferred that the characteristics of these three places are perceived differently. Kkotji Beach is recognized as a place to appreciate a view the sunset and is a base for the Taean Coast National Park's trekking course. Sinduri Coastal Sand Dune is recognized as a place with unusual scenery, and is an ecologically valuable space. Finally, Manlipo Beach is adjacent to the Chunlipo Arboretum, which is often visited by tourists, and the beach itself is recognized as a place with an impressive appearance. Social media data is very useful because it can enable analysis of various types of contents that are not from an expert's point of view. In this study, we used social media data to analyze various aspects of how people perceive and enjoy landscapes by integrating various content, such as landscape objects, images, and activities. However, because social media data may be amplified or distorted by users' memories and perceptions, field surveys are needed to verify the results of this study.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.1-22
• /
• 2009

The World Wide Web is transitioning from being a mere collection of documents that contain useful information toward providing a collection of services that perform useful tasks. The emerging Web service technology has been envisioned as the next technological wave and is expected to play an important role in this recent transformation of the Web. By providing interoperable interface standards for application-to-application communication, Web services can be combined with component based software development to promote application interaction and integration both within and across enterprises. To make Web services for service-oriented computing operational, it is important that Web service repositories not only be well-structured but also provide efficient tools for developers to find reusable Web service components that meet their needs. As the potential of Web services for service-oriented computing is being widely recognized, the demand for effective Web service discovery mechanisms is concomitantly growing. A number of techniques for Web service discovery have been proposed, but the discovery challenge has not been satisfactorily addressed. Unfortunately, most existing solutions are either too rudimentary to be useful or too domain dependent to be generalizable. In this paper, we propose a Web service organizing framework that combines clustering techniques with string matching and leverages the semantics of the XML-based service specification in WSDL documents. We believe that this is one of the first attempts at applying data mining techniques in the Web service discovery domain. Our proposed approach has several appealing features : (1) It minimizes the requirement of prior knowledge from both service consumers and publishers; (2) It avoids exploiting domain dependent ontologies; and (3) It is able to visualize the semantic relationships among Web services. We have developed a prototype system based on the proposed framework using an unsupervised artificial neural network and empirically evaluated the proposed approach and tool using real Web service descriptions drawn from operational Web service registries. We report on some preliminary results demonstrating the efficacy of the proposed approach.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.45-67
• /
• 2016

Given the recent development of smart devices, users are producing, sharing, and acquiring a variety of information via the Internet and social network services (SNSs). Because users tend to use multiple media simultaneously according to their goals and preferences, domestic SNS users use around 2.09 media concurrently on average. Since the information provided by such media is usually textually represented, recent studies have been actively conducting textual analysis in order to understand users more deeply. Earlier studies using textual analysis focused on analyzing a document's contents without substantive consideration of the diverse characteristics of the source medium. However, current studies argue that analytical and interpretive approaches should be applied differently according to the characteristics of a document's source. Documents can be classified into the following types: informative documents for delivering information, expressive documents for expressing emotions and aesthetics, operational documents for inducing the recipient's behavior, and audiovisual media documents for supplementing the above three functions through images and music. Further, documents can be classified according to their contents, which comprise facts, concepts, procedures, principles, rules, stories, opinions, and descriptions. Documents have unique characteristics according to the source media by which they are distributed. In terms of newspapers, only highly trained people tend to write articles for public dissemination. In contrast, with SNSs, various types of users can freely write any message and such messages are distributed in an unpredictable way. Again, in the case of newspapers, each article exists independently and does not tend to have any relation to other articles. However, messages (original tweets) on Twitter, for example, are highly organized and regularly duplicated and repeated through replies and retweets. There have been many studies focusing on the different characteristics between newspapers and SNSs. However, it is difficult to find a study that focuses on the difference between the two media from the perspective of supply and demand. We can regard the articles of newspapers as a kind of information supply, whereas messages on various SNSs represent a demand for information. By investigating traditional newspapers and SNSs from the perspective of supply and demand of information, we can explore and explain the information dilemma more clearly. For example, there may be superfluous issues that are heavily reported in newspaper articles despite the fact that users seldom have much interest in these issues. Such overproduced information is not only a waste of media resources but also makes it difficult to find valuable, in-demand information. Further, some issues that are covered by only a few newspapers may be of high interest to SNS users. To alleviate the deleterious effects of information asymmetries, it is necessary to analyze the supply and demand of each information source and, accordingly, provide information flexibly. Such an approach would allow the value of information to be explored and approximated on the basis of the supply-demand balance. Conceptually, this is very similar to the price of goods or services being determined by the supply-demand relationship. Adopting this concept, media companies could focus on the production of highly in-demand issues that are in short supply. In this study, we selected Internet news sites and Twitter as representative media for investigating information supply and demand, respectively. We present the notion of News Value Index (NVI), which evaluates the value of news information in terms of the magnitude of Twitter messages associated with it. In addition, we visualize the change of information value over time using the NVI. We conducted an analysis using 387,014 news articles and 31,674,795 Twitter messages. The analysis results revealed interesting patterns: most issues show lower NVI than average of the whole issue, whereas a few issues show steadily higher NVI than the average.

• Geophysics and Geophysical Exploration
• /
• v.10 no.4
• /
• pp.383-392
• /
• 2007

Karstic features and mining-related cavities not only lead to severe restrictions in land utilizations, but also constitute serious concern about geohazard and groundwater contamination. A microgravity survey was applied for detecting, mapping and monitoring karstic cavities in the test site at Muan prepared by KIGAM. The gravity data were collected using an AutoGrav CG-3 gravimeter at about 800 stations by 5 m interval along paddy paths. The density distribution beneath the profiles was drawn by two dimensional inversion based on the minimum support stabilizing functional, which generated better focused images of density discontinuities. We also imaged three dimensional density distribution by growing body inversion with solution from Euler deconvolution as a priori information. The density image showed that the cavities were dissolved, enlarged and connected into a cavity network system, which was supported by drill hole logs. A time-lapse microgravity was executed on the road in the test site for monitoring the change of the subsurface density distribution before and after grouting. The data were adjusted for reducing the effects due to the different condition of each survey, and inverted to density distributions. They show the change of density structure during the lapsed time, which implies the effects of grouting. This case history at the Muan test site showed that the microgravity with accuracy and precision of ${\mu}Gal$ is an effective and practical tool for detecting, mapping and monitoring the subsurface cavities.

• Economic and Environmental Geology
• /
• v.3 no.1
• /
• pp.25-34
• /
• 1970

Very few articles are available on geologic structure and genesis of Sangdong scheelite-deposits in spite of the fact that the mine is one of the leading tungsten producer in the world. Sangdong scheelite deposits, embedded in Myobong slate of Cambrian age at the southem limb of the Hambaek syncline which strikes $N70{\sim}80^{\circ}W$ and dips $15{\sim}30^{\circ}$ northeast, comprise six parallel veins in coincide with the bedding plane of Myobong formation, namely four footwall veins, a main vein, and a hangingwall vein. Four footwall veins are discontinuous and diminish both directions in short distance and were worked at near surface in old time. Hangingwall vein is emplaced in brecciated zone in contact plane of Myobong slate and overlying Pungchon limestone bed of Cambrian age and has not been worked until recent. The main vein, presently working, continues more than 1,500 m in both strike and dip sides and has a thickness varying 3.5 to 5 m. Characteristic is the distinct zonal arrangement of the main vein along strike side which gives a clue to the genesis of the deposits. The zones symmetrically arranged in both sides from center are, in order of center to both margins, muscovite-biotite-quartz zone, biotite-hornblende-quartz zone and garnet-diopside zone. The zones grade into each other with no boundary, and minable part of the vein streches in the former two zones extending roughly 1,000 m in strike side and over 1,100 m in dip side to which mining is underway at present. The quartz in both muscovite-biotite-quartz and biotite-hornblende-quartz zones is not network type of later intrusion, but the primary constituent of the special type of rock that forms the main vein. The minable zone has been enriched several times by numerous quartz veins along post-mineral fractures in the vein which carry scheelite, molybdenite, bismuthinite, fluorite and other sulfide minerals. These quartz veins varying from few centimeter to few tens of centimeter in width are roughly parallel to the main vein although few of them are diagonal, and distributed in rich zones not beyond the vein into both walls and garnet-diopside zone. Ore grade ranges from 1.5~2.5% $WO_3$ in center zone to less than 0.5% in garnet-diopside zone at margin, biotite-hornblende-quartz zone being inbetween in garde. The grade is, in general, proportional to the content of primary quartz. Judging from regional structure in mid-central parts of South Korea, Hambaek syncline was formed by the disturbance at the end of Triassic period with which bedding thrust and accompanied feather cracks in footwall side were created in Myobong slate and brecciated zone in contact plane between Myobong slate and Pungchon limestone. These fractures acted as a pathway of hot solution from interior which was in turn differentiated in situ to form deposit of the main vein with zonal arrangement. The footwall veins were developed along feather cracks accompanied with the main thrust by intrusion of biotite-hornblende-quartz vein and the hangingwall vein in shear zone along contact plane by replacement. The main vein thus formed was enriched at later stage by hydrothermal solutions now represented by quartz veins. The main mineralization and subsequent hydrothermal enrichments had probably taken place in post-Triassic to pre-Cretaceous periods. The veins were slightly displaced by post-mineral faults which cross diagonally the vein. This hypothesis differs from those done by previous workers who postulated that the deposits were formed by pyrometasomatic to contact replacement of the intercalated thin limestone bed in Myobong slate at the end of Cretaceous period.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Knowledge Management Research
• /
• v.23 no.4
• /
• pp.315-338
• /
• 2022

In 1986, Korea established legal systems to support small and medium-sized start-ups, which becomes the main pillars of national development. The legal systems have stimulated start-up ecosystems to have more than 1 million new start-up companies founded every year during the past 30 years. To analyze the trend of Korea's start-up ecosystem, in this study, we collected 1.18 million news articles from 1991 to 2020. Then, we extracted news articles that have the keywords "start-up", "venture", and "start-up". We employed network analysis and topic modeling to analyze collected news articles. Our analysis can contribute to analyzing the government policy direction shown in the history of start-up support policy. Specifically, our analysis identifies the dynamic characteristics of government influenced by external environmental factors (e.g., society, economy, and culture). The results of our analysis suggest that the start-up ecosystems in Korea have changed and developed mainly by the government policies for corporation governance, industrial development planning, deregulation, and economic prosperity plan. Our frequency keyword analysis contributes to understanding entrepreneurial productivity attributed to activities among the networked components in industrial ecosystems. Our analyses and results provide practitioners and researchers with practical and academic implications that can help to establish dedicated support policies through forecast tasks of the economic environment surrounding the start-ups. Korean entrepreneurial productivity has been empowered by growing numbers of large companies in the mobile phone industry. The spectrum of large companies incorporates content startups, platform providers, online shopping malls, and youth-oriented start-ups. In addition, economic situational factors contribute to the growth of Korean entrepreneurial productivity the economic, which are related to the global expansions of the mobile industry, and government efforts to foster start-ups. Our research is methodologically implicative. We employ natural language processes for 30 years of media articles, which enables more rigorous analysis compared to the existing studies which only observe changes in government and policy based on a qualitative manner.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.79-96
• /
• 2012

As the pace of competition dramatically accelerates and the complexity of change grows, a variety of research have been conducted to improve firms' short-term performance and to enhance firms' long-term survival. In particular, researchers and practitioners have paid their attention to identify promising technologies that lead competitive advantage to a firm. Discovery of promising technology depends on how a firm evaluates the value of technologies, thus many evaluating methods have been proposed. Experts' opinion based approaches have been widely accepted to predict the value of technologies. Whereas this approach provides in-depth analysis and ensures validity of analysis results, it is usually cost-and time-ineffective and is limited to qualitative evaluation. Considerable studies attempt to forecast the value of technology by using patent information to overcome the limitation of experts' opinion based approach. Patent based technology evaluation has served as a valuable assessment approach of the technological forecasting because it contains a full and practical description of technology with uniform structure. Furthermore, it provides information that is not divulged in any other sources. Although patent information based approach has contributed to our understanding of prediction of promising technologies, it has some limitations because prediction has been made based on the past patent information, and the interpretations of patent analyses are not consistent. In order to fill this gap, this study proposes a technology forecasting methodology by integrating patent information approach and artificial intelligence method. The methodology consists of three modules : evaluation of technologies promising, implementation of technologies value prediction model, and recommendation of promising technologies. In the first module, technologies promising is evaluated from three different and complementary dimensions; impact, fusion, and diffusion perspectives. The impact of technologies refers to their influence on future technologies development and improvement, and is also clearly associated with their monetary value. The fusion of technologies denotes the extent to which a technology fuses different technologies, and represents the breadth of search underlying the technology. The fusion of technologies can be calculated based on technology or patent, thus this study measures two types of fusion index; fusion index per technology and fusion index per patent. Finally, the diffusion of technologies denotes their degree of applicability across scientific and technological fields. In the same vein, diffusion index per technology and diffusion index per patent are considered respectively. In the second module, technologies value prediction model is implemented using artificial intelligence method. This studies use the values of five indexes (i.e., impact index, fusion index per technology, fusion index per patent, diffusion index per technology and diffusion index per patent) at different time (e.g., t-n, t-n-1, t-n-2, ${\cdots}$) as input variables. The out variables are values of five indexes at time t, which is used for learning. The learning method adopted in this study is backpropagation algorithm. In the third module, this study recommends final promising technologies based on analytic hierarchy process. AHP provides relative importance of each index, leading to final promising index for technology. Applicability of the proposed methodology is tested by using U.S. patents in international patent class G06F (i.e., electronic digital data processing) from 2000 to 2008. The results show that mean absolute error value for prediction produced by the proposed methodology is lower than the value produced by multiple regression analysis in cases of fusion indexes. However, mean absolute error value of the proposed methodology is slightly higher than the value of multiple regression analysis. These unexpected results may be explained, in part, by small number of patents. Since this study only uses patent data in class G06F, number of sample patent data is relatively small, leading to incomplete learning to satisfy complex artificial intelligence structure. In addition, fusion index per technology and impact index are found to be important criteria to predict promising technology. This study attempts to extend the existing knowledge by proposing a new methodology for prediction technology value by integrating patent information analysis and artificial intelligence network. It helps managers who want to technology develop planning and policy maker who want to implement technology policy by providing quantitative prediction methodology. In addition, this study could help other researchers by proving a deeper understanding of the complex technological forecasting field.