• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.29-45
• /
• 2012

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.83-105
• /
• 2016

Measuring an individual's subjective wellbeing in an accurate, unobtrusive, and cost-effective manner is a core success factor of the wellbeing support system, which is a type of medical IT service. However, measurements with a self-report questionnaire and wearable sensors are cost-intensive and obtrusive when the wellbeing support system should be running in real-time, despite being very accurate. Recently, reasoning the state of subjective wellbeing with conventional sentiment analysis and unstructured data has been proposed as an alternative to resolve the drawbacks of the self-report questionnaire and wearable sensors. However, this approach does not consider contextual polarity, which results in lower measurement accuracy. Moreover, there is no sentimental word net or ontology for the subjective wellbeing area. Hence, this paper proposes a method to extract keywords and their contextual polarity representing the subjective wellbeing state from the unstructured text in online websites in order to improve the reasoning accuracy of the sentiment analysis. The proposed method is as follows. First, a set of general sentimental words is proposed. SentiWordNet was adopted; this is the most widely used dictionary and contains about 100,000 words such as nouns, verbs, adjectives, and adverbs with polarities from -1.0 (extremely negative) to 1.0 (extremely positive). Second, corpora on subjective wellbeing (SWB corpora) were obtained by crawling online text. A survey was conducted to prepare a learning dataset that includes an individual's opinion and the level of self-report wellness, such as stress and depression. The participants were asked to respond with their feelings about online news on two topics. Next, three data sources were extracted from the SWB corpora: demographic information, psychographic information, and the structural characteristics of the text (e.g., the number of words used in the text, simple statistics on the special characters used). These were considered to adjust the level of a specific SWB. Finally, a set of reasoning rules was generated for each wellbeing factor to estimate the SWB of an individual based on the text written by the individual. The experimental results suggested that using contextual polarity for each SWB factor (e.g., stress, depression) significantly improved the estimation accuracy compared to conventional sentiment analysis methods incorporating SentiWordNet. Even though literature is available on Korean sentiment analysis, such studies only used only a limited set of sentimental words. Due to the small number of words, many sentences are overlooked and ignored when estimating the level of sentiment. However, the proposed method can identify multiple sentiment-neutral words as sentiment words in the context of a specific SWB factor. The results also suggest that a specific type of senti-word dictionary containing contextual polarity needs to be constructed along with a dictionary based on common sense such as SenticNet. These efforts will enrich and enlarge the application area of sentic computing. The study is helpful to practitioners and managers of wellness services in that a couple of characteristics of unstructured text have been identified for improving SWB. Consistent with the literature, the results showed that the gender and age affect the SWB state when the individual is exposed to an identical queue from the online text. In addition, the length of the textual response and usage pattern of special characters were found to indicate the individual's SWB. These imply that better SWB measurement should involve collecting the textual structure and the individual's demographic conditions. In the future, the proposed method should be improved by automated identification of the contextual polarity in order to enlarge the vocabulary in a cost-effective manner.

• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.1-16
• /
• 2015

Traffic accident is one of the major cause of death worldwide for the last several decades. According to the statistics of world health organization, approximately 1.24 million deaths occurred on the world's roads in 2010. In order to reduce future traffic accident, multipronged approaches have been adopted including traffic regulations, injury-reducing technologies, driving training program and so on. Records on traffic accidents are generated and maintained for this purpose. To make these records meaningful and effective, it is necessary to analyze relationship between traffic accident and related factors including vehicle design, road design, weather, driver behavior etc. Insight derived from these analysis can be used for accident prevention approaches. Traffic accident data mining is an activity to find useful knowledges about such relationship that is not well-known and user may interested in it. Many studies about mining accident data have been reported over the past two decades. Most of studies mainly focused on predict risk of accident using accident related factors. Supervised learning methods like decision tree, logistic regression, k-nearest neighbor, neural network are used for these prediction. However, derived prediction model from these algorithms are too complex to understand for human itself because the main purpose of these algorithms are prediction, not explanation of the data. Some of studies use unsupervised clustering algorithm to dividing the data into several groups, but derived group itself is still not easy to understand for human, so it is necessary to do some additional analytic works. Rule based learning methods are adequate when we want to derive comprehensive form of knowledge about the target domain. It derives a set of if-then rules that represent relationship between the target feature with other features. Rules are fairly easy for human to understand its meaning therefore it can help provide insight and comprehensible results for human. Association rule learning methods and subgroup discovery methods are representing rule based learning methods for descriptive task. These two algorithms have been used in a wide range of area from transaction analysis, accident data analysis, detection of statistically significant patient risk groups, discovering key person in social communities and so on. We use both the association rule learning method and the subgroup discovery method to discover useful patterns from a traffic accident dataset consisting of many features including profile of driver, location of accident, types of accident, information of vehicle, violation of regulation and so on. The association rule learning method, which is one of the unsupervised learning methods, searches for frequent item sets from the data and translates them into rules. In contrast, the subgroup discovery method is a kind of supervised learning method that discovers rules of user specified concepts satisfying certain degree of generality and unusualness. Depending on what aspect of the data we are focusing our attention to, we may combine different multiple relevant features of interest to make a synthetic target feature, and give it to the rule learning algorithms. After a set of rules is derived, some postprocessing steps are taken to make the ruleset more compact and easier to understand by removing some uninteresting or redundant rules. We conducted a set of experiments of mining our traffic accident data in both unsupervised mode and supervised mode for comparison of these rule based learning algorithms. Experiments with the traffic accident data reveals that the association rule learning, in its pure unsupervised mode, can discover some hidden relationship among the features. Under supervised learning setting with combinatorial target feature, however, the subgroup discovery method finds good rules much more easily than the association rule learning method that requires a lot of efforts to tune the parameters.

• Korean Journal of Psychosomatic Medicine
• /
• v.7 no.2
• /
• pp.203-212
• /
• 1999

Objectives : "Alexithymia" mean literally "no word for mood(or emotion)". It is not only a marked constriction in emotional functioning but a deficit in their cognitive processing. We designed this study to investigate the level of alexithymia, psychopathology and personality factors of patients with somatoform disorder and with diabetes mellitus. Methods : The subjects were consisted of patients with somatoform disorder(N=20), patients with diabetes mellitus(N=20), and normal control(N=20). The level of alexithymia, psychopathology and personality factors were assessed by the Toronto Alexithymia Scale(TAS), the Symptom Checklist 90-Revision(SCL 90-R), and the Sixteen Personality Factor Questionnaire(16-PF). And we compared demographic characteristics, psychopathology and personality factors among three groups, and assessed the relationship between alexithymia and psychopathology, and between alexithymia and personality factors. Results : The results were as follows. 1) Patients with somatoform disorder showed significantly higher TAS scores compared to patients with diabetes mellitus and the normal control group. 2) Patients With somatoform disorder showed significantly higher scores of somatization, anxiety scales than patients with diabetes mellitus and the normal control group, and showed significantly higher scores of obsessive-compulsive, depression, phobic anxiety, psychoticism scales than the normal control group by the SCL-90-R. 3) The normal control group showed high intelligence scores only as compared to patients with somatoform disorder by the 16-PF. 4) A significant relationship was found between TAS scores and psychopathology in patients with somatoform disorder. 5) All three groups did not shown any correlation between TAS and 16-PF. Conclusion : Patients with somatoform disorder showed higher TAS scores and more multiple psychopathology than patients with diabetes mellitus and the normal controls. A significant relationship was found between TAS scores and psychopathology in patients with somatoform disorder. We suggest that the therapeutic approach to patients with somatoform disorder to express emotions and manage psychopathology, and that the treatment methods of patients with diabetes mellitus aims to improve firstly physical conditions are more helpful.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.255-277
• /
• 2011

Product Service System(PSS), which is an integrated combination of product and service, provides new value to customer and makes companies sustainable as well. The objective of this paper draws Critical Successful Factors(CSF) of PSS through multiple case study. First, we review various concepts and types in PSS and Platform business literature currently available on this topic. Second, after investigating various cases with the characteristics of PSS and platform business, we select four cases of 'iPod of Apple', 'Kindle of Amazon', 'Zune of Microsoft', and 'e-book reader of Sony'. Then, the four cases are categorized as successful and failed cases according to criteria of case selection and PSS classification. We consider two methodologies for the case selection, i.e., 'Strategies for the Selection of Samples and Cases' proposed by Bent(2006) and the seven case selection procedures proposed by Jason and John(2008). For case selection, 'Stratified sample and Paradigmatic cases' is adopted as one of several options for sampling. Then, we use the seven case selection procedures such as 'typical', 'diverse', 'extreme', 'deviant', 'influential', 'most-similar', and 'mostdifferent' and among them only three procedures of 'diverse', 'most?similar', and 'most-different' are applied for the case selection. For PSS classification, the eight PSS types, suggested by Tukker(2004), of 'product related', 'advice and consulancy', 'product lease', 'product renting/sharing', 'product pooling', 'activity management', 'pay per service unit', 'functional result' are utilized. We categorize the four selected cases as a product oriented group because the cases not only sell a product, but also offer service needed during the use phase of the product. Then, we analyze the four cases by using cross-case pattern that Eisenhardt(1991) suggested. Eisenhardt(1991) argued that three processes are required for avoiding reaching premature or even false conclusion. The fist step includes selecting categories of dimensions and finding within-group similarities coupled with intergroup difference. In the second process, pairs of cases are selected and listed. The second step forces researchers to find the subtle similarities and differences between cases. The third process is to divide the data by data source. The result of cross-case pattern indicates that the similarities of iPod and Kindle as successful cases are convenient user interface, successful plarform strategy, and rich contents. The differences between the successful cases are that, wheares iPod has been recognized as the culture code, Kindle has implemented a low price as its main strategy. Meanwhile, the similarities of Zune and PRS series as failed cases are lack of sufficient applications and contents. The differences between the failed cases are that, wheares Zune adopted an undifferentiated strategy, PRS series conducted high-price strategy. From the analysis of the cases, we generate three hypotheses. The first hypothesis assumes that a successful PSS system requires convenient user interface. The second hypothesis assumes that a successful PSS system requires a reciprocal(win/win) business model. The third hypothesis assumes that a successful PSS system requires sufficient quantities of applications and contents. To verify the hypotheses, we uses the cross-matching (or pattern matching) methodology. The methodology matches three key words (user interface, reciprocal business model, contents) of the hypotheses to the previous papers related to PSS, digital contents, and Information System (IS). Finally, this paper suggests the three implications from analyzed results. A successful PSS system needs to provide differentiated value for customers such as convenient user interface, e.g., the simple design of iTunes (iPod) and the provision of connection to Kindle Store without any charge. A successful PSS system also requires a mutually benefitable business model as Apple and Amazon implement a policy that provides a reasonable proft sharing for third party. A successful PSS system requires sufficient quantities of applications and contents.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• 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.24 no.2
• /
• pp.243-264
• /
• 2018

Although the worldwide battery market is recently spurring the development of lithium secondary battery, lead acid batteries (rechargeable batteries) which have good-performance and can be reused are consumed in a wide range of industry fields. However, lead-acid batteries have a serious problem in that deterioration of a battery makes progress quickly in the presence of that degradation of only one cell among several cells which is packed in a battery begins. To overcome this problem, previous researches have attempted to identify the mechanism of deterioration of a battery in many ways. However, most of previous researches have used data obtained in a laboratory to analyze the mechanism of deterioration of a battery but not used data obtained in a real world. The usage of real data can increase the feasibility and the applicability of the findings of a research. Therefore, this study aims to develop a model which predicts the battery deterioration using data obtained in real world. To this end, we collected data which presents change of battery state by attaching sensors enabling to monitor the battery condition in real time to dozens of golf carts operated in the real golf field. As a result, total 16,883 samples were obtained. And then, we developed a model which predicts a precursor phenomenon representing deterioration of a battery by analyzing the data collected from the sensors using machine learning techniques. As initial independent variables, we used 1) inbound time of a cart, 2) outbound time of a cart, 3) duration(from outbound time to charge time), 4) charge amount, 5) used amount, 6) charge efficiency, 7) lowest temperature of battery cell 1 to 6, 8) lowest voltage of battery cell 1 to 6, 9) highest voltage of battery cell 1 to 6, 10) voltage of battery cell 1 to 6 at the beginning of operation, 11) voltage of battery cell 1 to 6 at the end of charge, 12) used amount of battery cell 1 to 6 during operation, 13) used amount of battery during operation(Max-Min), 14) duration of battery use, and 15) highest current during operation. Since the values of the independent variables, lowest temperature of battery cell 1 to 6, lowest voltage of battery cell 1 to 6, highest voltage of battery cell 1 to 6, voltage of battery cell 1 to 6 at the beginning of operation, voltage of battery cell 1 to 6 at the end of charge, and used amount of battery cell 1 to 6 during operation are similar to that of each battery cell, we conducted principal component analysis using verimax orthogonal rotation in order to mitigate the multiple collinearity problem. According to the results, we made new variables by averaging the values of independent variables clustered together, and used them as final independent variables instead of origin variables, thereby reducing the dimension. We used decision tree, logistic regression, Bayesian network as algorithms for building prediction models. And also, we built prediction models using the bagging of each of them, the boosting of each of them, and RandomForest. Experimental results show that the prediction model using the bagging of decision tree yields the best accuracy of 89.3923%. This study has some limitations in that the additional variables which affect the deterioration of battery such as weather (temperature, humidity) and driving habits, did not considered, therefore, we would like to consider the them in the future research. However, the battery deterioration prediction model proposed in the present study is expected to enable effective and efficient management of battery used in the real filed by dramatically and to reduce the cost caused by not detecting battery deterioration accordingly.

• Journal of Intelligence and Information Systems
• /
• v.17 no.2
• /
• pp.97-107
• /
• 2011

Nowadays there are a lot of issues about copyright infringement in the Internet world because the digital content on the network can be copied and delivered easily. Indeed the copied version has same quality with the original one. So, copyright owners and content provider want a powerful solution to protect their content. The popular one of the solutions was DRM (digital rights management) that is based on encryption technology and rights control. However, DRM-free service was launched after Steve Jobs who is CEO of Apple proposed a new music service paradigm without DRM, and the DRM is disappeared at the online music market. Even though the online music service decided to not equip the DRM solution, copyright owners and content providers are still searching a solution to protect their content. A solution to replace the DRM technology is digital audio watermarking technology which can embed copyright information into the music. In this paper, the author proposed a new audio watermarking algorithm with two approaches. First, the watermark information is generated by two dimensional barcode which has error correction code. So, the information can be recovered by itself if the errors fall into the range of the error tolerance. The other one is to use chirp sequence of CDMA (code division multiple access). These make the algorithm robust to the several malicious attacks. There are many 2D barcodes. Especially, QR code which is one of the matrix barcodes can express the information and the expression is freer than that of the other matrix barcodes. QR code has the square patterns with double at the three corners and these indicate the boundary of the symbol. This feature of the QR code is proper to express the watermark information. That is, because the QR code is 2D barcodes, nonlinear code and matrix code, it can be modulated to the spread spectrum and can be used for the watermarking algorithm. The proposed algorithm assigns the different spread spectrum sequences to the individual users respectively. In the case that the assigned code sequences are orthogonal, we can identify the watermark information of the individual user from an audio content. The algorithm used the Walsh code as an orthogonal code. The watermark information is rearranged to the 1D sequence from 2D barcode and modulated by the Walsh code. The modulated watermark information is embedded into the DCT (discrete cosine transform) domain of the original audio content. For the performance evaluation, I used 3 audio samples, "Amazing Grace", "Oh! Carol" and "Take me home country roads", The attacks for the robustness test were MP3 compression, echo attack, and sub woofer boost. The MP3 compression was performed by a tool of Cool Edit Pro 2.0. The specification of MP3 was CBR(Constant Bit Rate) 128kbps, 44,100Hz, and stereo. The echo attack had the echo with initial volume 70%, decay 75%, and delay 100msec. The sub woofer boost attack was a modification attack of low frequency part in the Fourier coefficients. The test results showed the proposed algorithm is robust to the attacks. In the MP3 attack, the strength of the watermark information is not affected, and then the watermark can be detected from all of the sample audios. In the sub woofer boost attack, the watermark was detected when the strength is 0.3. Also, in the case of echo attack, the watermark can be identified if the strength is greater and equal than 0.5.

• 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.