• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.305-316
• /
• 2011

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

• 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 Hospice and Palliative Care
• /
• v.13 no.3
• /
• pp.181-189
• /
• 2010

Purpose: Recently, health policy making is increasingly based on evidence. Therefore, Korean Terminal Cancer Patient Information System (KTCPIS) was developed to meet such need. We aimed to report its developmental process and statistics from 6 months data. Methods: Items for KTCPIS were developed through the consultation with practitioners. E-Velos web-based clinical trial management system was used as a technical platform. Data were collected for patients who were registered to 34 inpatient palliative care services, designated by Ministry of Health, Welfare, and Family Affairs, from $1^{st}$ of January to $30^{th}$ of June in 2009. Descriptive statistics were used for the analysis. Results: From the nationally representative set of 2,940 patients, we obtained the following results. Mean age was $64.8{\pm}12.9$ years, and 56.6% were male. Lung cancer (18.0%) was most common diagnosis. Only 50.3% of patients received the confirmation of terminal diagnosis by two or more physicians, and 69.7% had an insight of terminal diagnosis at the time of admission. About half of patients were admitted to the units on their own without any formal referral. Average and worst pain scores were significantly reduced after 1 week when compared to those at the time of admission. 73.4% faced death in the units, and home-discharge comprised only 13.3%. Mean length of stay per admission was $20.2{\pm}21.2$ days, with median value of 13. Conclusion: Nationally representative data on the characteristics of patients and their caregiver, and current practice of service delivery in palliative care units were obtained through the operation of KTCPIS.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• Journal of Nutrition and Health
• /
• v.50 no.5
• /
• pp.504-518
• /
• 2017

Purpose: The objective of this study was to develop a processed foods database (DB) for estimation of processed food intake in the Korean population using data from the Korea National Health and Nutrition Survey (KNHANES). Methods: Analytical values of processed foods were collected from food composition tables of national institutions (Development Institute, Rural Development Administration), the US Department of Agriculture, and previously reported scientific journals. Missing or unavailable values were substituted, calculated, or imputed. The nutrient data covered 14 nutrients, including energy, protein, carbohydrates, fat, calcium, phosphorus, iron, sodium, potassium, vitamin A, thiamin, riboflavin, niacin, and vitamin C. The processed food DB covered a total of 4,858 food items used in the KNHANES. Each analytical value per food item was selected systematically based on the priority criteria of data sources. Results: Level 0 DB was developed based on a list of 8,785 registered processed foods with recipes of ready-to-eat processed foods, one food composition table published by the national institution, and nutrition facts obtained directly from manufacturers or indirectly via web search. Level 1 DB included information of 14 nutrients, and missing or unavailable values were substituted, calculated, or imputed at level 2. Level 3 DB evaluated the newly constructed nutrient DB for processed foods using the 2013 KNHANES. Mean intakes of total food and processed food were 1,551.4 g (males 1,761.8 g, females 1,340.8 g) and 129.4 g (males 169.9 g, females 88.8 g), respectively. Processed foods contributed to nutrient intakes from 5.0% (fiber) to 12.3% (protein) in the Korean population. Conclusion: The newly developed nutrient DB for processed foods contributes to accurate estimation of nutrient intakes in the Korean population. Consistent and regular update and quality control of the DB is needed to obtain accurate estimation of usual intakes using data from the KNHANES.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.101-116
• /
• 2015

Recently, due to the development of smart devices and social media, vast amounts of information with the various forms were accumulated. Particularly, considerable research efforts are being directed towards analyzing unstructured big data to resolve various social problems. Accordingly, focus of data-driven decision-making is being moved from structured data analysis to unstructured one. Also, in the field of recommendation system, which is the typical area of data-driven decision-making, the need of using unstructured data has been steadily increased to improve system performance. Approaches to improve the performance of recommendation systems can be found in two aspects- improving algorithms and acquiring useful data with high quality. Traditionally, most efforts to improve the performance of recommendation system were made by the former approach, while the latter approach has not attracted much attention relatively. In this sense, efforts to utilize unstructured data from variable sources are very timely and necessary. Particularly, as the interests of users are directly connected with their needs, identifying the interests of the user through unstructured big data analysis can be a crew for improving performance of recommendation systems. In this sense, this study proposes the methodology of improving recommendation system by measuring interests of the user. Specially, this study proposes the method to quantify interests of the user by analyzing user's internet usage patterns, and to predict user's repurchase based upon the discovered preferences. There are two important modules in this study. The first module predicts repurchase probability of each category through analyzing users' purchase history. We include the first module to our research scope for comparing the accuracy of traditional purchase-based prediction model to our new model presented in the second module. This procedure extracts purchase history of users. The core part of our methodology is in the second module. This module extracts users' interests by analyzing news articles the users have read. The second module constructs a correspondence matrix between topics and news articles by performing topic modeling on real world news articles. And then, the module analyzes users' news access patterns and then constructs a correspondence matrix between articles and users. After that, by merging the results of the previous processes in the second module, we can obtain a correspondence matrix between users and topics. This matrix describes users' interests in a structured manner. Finally, by using the matrix, the second module builds a model for predicting repurchase probability of each category. In this paper, we also provide experimental results of our performance evaluation. The outline of data used our experiments is as follows. We acquired web transaction data of 5,000 panels from a company that is specialized to analyzing ranks of internet sites. At first we extracted 15,000 URLs of news articles published from July 2012 to June 2013 from the original data and we crawled main contents of the news articles. After that we selected 2,615 users who have read at least one of the extracted news articles. Among the 2,615 users, we discovered that the number of target users who purchase at least one items from our target shopping mall 'G' is 359. In the experiments, we analyzed purchase history and news access records of the 359 internet users. From the performance evaluation, we found that our prediction model using both users' interests and purchase history outperforms a prediction model using only users' purchase history from a view point of misclassification ratio. In detail, our model outperformed the traditional one in appliance, beauty, computer, culture, digital, fashion, and sports categories when artificial neural network based models were used. Similarly, our model outperformed the traditional one in beauty, computer, digital, fashion, food, and furniture categories when decision tree based models were used although the improvement is very small.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.181-199
• /
• 2010

As rapid progress of population aging and strong interest in health, the demand for new healthcare service is increasing. Until now healthcare service has provided post treatment by face-to-face manner. But according to related researches, proactive treatment is resulted to be more effective for preventing diseases. Particularly, the existing healthcare services have limitations in preventing and managing metabolic syndrome such a lifestyle disease, because the cause of metabolic syndrome is related to life habit. As the advent of ubiquitous technology, patients with the metabolic syndrome can improve life habit such as poor eating habits and physical inactivity without the constraints of time and space through u-healthcare service. Therefore, lots of researches for u-healthcare service focus on providing the personalized healthcare service for preventing and managing metabolic syndrome. For example, Kim et al.(2010) have proposed a healthcare model for providing the customized calories and rates of nutrition factors by analyzing the user's preference in foods. Lee et al.(2010) have suggested the customized diet recommendation service considering the basic information, vital signs, family history of diseases and food preferences to prevent and manage coronary heart disease. And, Kim and Han(2004) have demonstrated that the web-based nutrition counseling has effects on food intake and lipids of patients with hyperlipidemia. However, the existing researches for u-healthcare service focus on providing the predefined one-way u-healthcare service. Thus, users have a tendency to easily lose interest in improving life habit. To solve such a problem of u-healthcare service, this research suggests a u-healthcare recommender system which is based on collaborative filtering principle and social network. This research follows the principle of collaborative filtering, but preserves local networks (consisting of small group of similar neighbors) for target users to recommend context aware healthcare services. Our research is consisted of the following five steps. In the first step, user profile is created using the usage history data for improvement in life habit. And then, a set of users known as neighbors is formed by the degree of similarity between the users, which is calculated by Pearson correlation coefficient. In the second step, the target user obtains service information from his/her neighbors. In the third step, recommendation list of top-N service is generated for the target user. Making the list, we use the multi-filtering based on user's psychological context information and body mass index (BMI) information for the detailed recommendation. In the fourth step, the personal information, which is the history of the usage service, is updated when the target user uses the recommended service. In the final step, a social network is reformed to continually provide qualified recommendation. For example, the neighbors may be excluded from the social network if the target user doesn't like the recommendation list received from them. That is, this step updates each user's neighbors locally, so maintains the updated local neighbors always to give context aware recommendation in real time. The characteristics of our research as follows. First, we develop the u-healthcare recommender system for improving life habit such as poor eating habits and physical inactivity. Second, the proposed recommender system uses autonomous collaboration, which enables users to prevent dropping and not to lose user's interest in improving life habit. Third, the reformation of the social network is automated to maintain the quality of recommendation. Finally, this research has implemented a mobile prototype system using JAVA and Microsoft Access2007 to recommend the prescribed foods and exercises for chronic disease prevention, which are provided by A university medical center. This research intends to prevent diseases such as chronic illnesses and to improve user's lifestyle through providing context aware and personalized food and exercise services with the help of similar users'experience and knowledge. We expect that the user of this system can improve their life habit with the help of handheld mobile smart phone, because it uses autonomous collaboration to arouse interest in healthcare.

• The Korean Journal of Archival Studies
• /
• no.16
• /
• pp.201-256
• /
• 2007

Nowadays Korean main archives and manuscript repositories are planning to develop archival information service for students and teachers in their web sites. This study is aimed at discovering main issues of developing archival information service for students and teachers and finding a solution. The goal of archival information service for students and teachers is the promotion of use through launching service and the gradual growth of archival management program. The customer group is segmented into the students and teachers who are learning and teaching Korean history in classroom. As a result of analyzing curriculum and educational environment, the archival information must be developed into teaching-learning materials. And the processing archival information into archival content is needed. Consequently the character of archival information service for students and teachers is conceptualized as archival content service for teaching-learning materials. At every step of developing archival content service for teaching-learning materials, the next main points are considered and achieved. First, the strategy of customer-focused service must be the same from beginning to end. Second, the growth of traditional archival management(e.g. classification, description and finding aids) must be contributed. Third, the collaboration system leading by professional education staff must be organized. Fourth, the archival information must be related with teaching-learning activities. Fifth, the quality of content is more important than the quantity of it. Sixth, the networking with another agencies for cooperation must be considered.

• The Korean Journal of Archival Studies
• /
• no.16
• /
• pp.147-200
• /
• 2007

Archives provide users with easier and more convenient access to and use of archival data through their Internet websites. Now, archival websites function not only as a tool of information provision or marketing, or as a gateway of Internet-based materials, but also as cyber space for all services of archives, providing users with information and knowledge and direct accessibility to the services in the archives. At present, Korean archives are proceeding with establishing websites or upgrading existing websites, and the use rates and reliability of web services by users are becoming higher. However, although there have been various studies for the evaluation of general websites, few are found with regard to the evaluation of archival websites. It is necessary for archival websites that provide information service to users of every stripe to make more efforts and have more interest in user-centered convenience, right to know, and information provision-centered service. Accordingly, needless to say, it is necessary to study evaluation criteria of websites so that high quality archival websites can be established. With this background, this study establishes evaluation criteria for archival websites, which are appropriate to their objectives and functions and directly evaluates archives, presenting ways to establish and redevelop archival websites. More detailed purposes are as follows: First, analyzes existing theories of evaluation through reviews on previous literature and elicits evaluation criteria for websites, which are appropriate to archives; Second, based on the elicited evaluation criteria for archival websites, examines the current state of domestic archival websites through analytic evaluation; and Third, presents ways to improve archival websites that may be helpful in establishing or improving them in the future. The expectancy effects of this study are as follows: First, it will be helpful when one wishes to identify the current state of archival websites and to improve or redevelop existing websites, or to develop online service through website; Second, it will function as a checklist when a developer who is to establish an archival website wishes to develop evaluation criteria; and Third, it may be used as an inspection tool when an archives contracts out the establishment of its website.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.263-286
• /
• 2022

This study acquires NBA statistical information for a total of 32 years from 1990 to 2022 using web crawling, observes variables of interest through exploratory data analysis, and generates related derived variables. Unused variables were removed through a purification process on the input data, and correlation analysis, t-test, and ANOVA were performed on the remaining variables. For the variable of interest, the difference in the mean between the groups that advanced to the playoffs and did not advance to the playoffs was tested, and then to compensate for this, the average difference between the three groups (higher/middle/lower) based on ranking was reconfirmed. Of the input data, only this year's season data was used as a test set, and 5-fold cross-validation was performed by dividing the training set and the validation set for model training. The overfitting problem was solved by comparing the cross-validation result and the final analysis result using the test set to confirm that there was no difference in the performance matrix. Because the quality level of the raw data is high and the statistical assumptions are satisfied, most of the models showed good results despite the small data set. This study not only predicts NBA game results or classifies whether or not to advance to the playoffs using machine learning, but also examines whether the variables of interest are included in the major variables with high importance by understanding the importance of input attribute. Through the visualization of SHAP value, it was possible to overcome the limitation that could not be interpreted only with the result of feature importance, and to compensate for the lack of consistency in the importance calculation in the process of entering/removing variables. It was found that a number of variables related to three points and errors classified as subjects of interest in this study were included in the major variables affecting advancing to the playoffs in the NBA. Although this study is similar in that it includes topics such as match results, playoffs, and championship predictions, which have been dealt with in the existing sports data analysis field, and comparatively analyzed several machine learning models for analysis, there is a difference in that the interest features are set in advance and statistically verified, so that it is compared with the machine learning analysis result. Also, it was differentiated from existing studies by presenting explanatory visualization results using SHAP, one of the XAI models.