• Korean Journal of Soil Science and Fertilizer
• /
• v.32 no.4
• /
• pp.398-404
• /
• 1999

Factor analysis technique was employed to screen the principal indicators influencing soil and water qualities in the intensively cultivated areas of the Han River Basin. Soil chemical parameters were analyzed for the soil samples collected at intensive farming area in Pyungchang-Gun, and water quality monitoring data were obtained from the agricultural small catchments of Han River Basin during 1996 and 1997. Among the $11{\times}11$ cross correlation matrix, 29 correlations were significant out of 55 soil quality indicator pairs. The overall Kaiser's measure of sampling adequacy(KMS) value was acceptable with 0.60. Most indicators except iron were acceptable. Among soil indicators, the first factors showing high factor loadings were pH, Ca and Mg. The factor loading was the highest for Ca. The second factor could be characterized as phosphate and micronutrient. The third factor was organic matter and EC, and the fourth factor was potassium and Fe. Out of 190 water quality indicators, 86 correlations were significant. Overall KMS value was 0.74, but the KMS values for pH, TSS, Cd, Cu and Fe were lower than 50. The first factor of EC accounts 27.1 percents of the total variance, and showed high factor loadings with Na, Ca, $SO_4$, Mg, K, Cl, $NO_3$, and T-N. The second factor showed high loadings with Zn, Fe, Mn and Cd. The third to seventh factors could be characterized as $PO_4$, TSS, inorganic nitrogen, pH and T-P, and Cu factors, respectively. The factor score for EC was the highest in Kuri, followed by Chunchon, Dunnae and Daegwanryng. The factor score for heavy metals were the highest in the Daegwanryng. The results demonstrated that the factor analysis could be useful to select the most principal factor influencing soil and water qualities in the agricultural watershed.

• Tuberculosis and Respiratory Diseases
• /
• v.56 no.1
• /
• pp.51-66
• /
• 2004

Objectives : The matrix metalloproteinases (MMPs) that participate in the extracellular matrix metabolism play a important role in the progression of pulmonary fibrosis. The effects of the MMPs are regulated by several factors including Th-1 cytokines, $interferon-{\gamma}$ ($IFN-{\gamma}$). Up to now, $IFN-{\gamma}$ is known to inhibit pulmonary fibrosis, but little is known regarding the exact effect of $IFN-{\gamma}$ on the regulation of the MMPs. This study investigated the effects of $interferon-{\gamma}$ on the pulmonary fibrosis and the expression of the lung MMP-2,-9, TIMP-1,-2, and Th-2 cytokines in aa rat model of bleomycin induced pulmonary fibrosis. Materials and methods : Male, specific pathogen-free Sprague-Dawley rats were subjected to an intratracheal bleomycin instillation. The rats were randomized to a saline control, a bleomycin treated, and a bleomycin+$IFN-{\gamma}$ treated group. The bleomycin+$IFN-{\gamma}$ treated group was subjected to an intramuscular injection of $IFN-{\gamma}$ for 14 days. At 3, 7, 14, and 28 days after the bleomycin instillation, the rats were sacrificed and the lungs were harvested. In order to evaluate the effects of the $IFN-{\gamma}$ on lung fibrosis and inflammation, the lung hydroxyproline content, inflammation and fibrosis score were measured. Western blotting, zymography and reverse zymography were performed at 3, 7, 14, 28 days after bleomycin instillation in order to evaluate the MMP-2,-9, and TIMP-1,-2 expression level. ELISA was performed to determine the IL-4 and IL-13 level in a lung homogenate. Results : 1. 7 days after bleomycin instillation, inflammatory changes were more severe in the bleomycin+$IFN-{\gamma}$ group than the bleomycin group (bleomycin group : bleomycin+$IFN-{\gamma}$ group=$2.08{\pm}0.15:2.74{\pm}0.29$, P<0.05), but 28 days after bleomycin instillation, lung fibrosis was significantly reduced as a result of the $IFN-{\gamma}$ treatment (bleomycin group : bleomycin+$IFN-{\gamma}$ group=$3.94{\pm}0.43:2.64{\pm}0.13$, P<0.05). 2. 28 days after bleomycin instillation, the lung hydroxyproline content was significantly reduced as a result of $IFN-{\gamma}$ treatment (bleomycin group : bleomycin+$IFN-{\gamma}$ group=$294.04{\pm}31.73{\mu}g/g:194.92{\pm}15.51{\mu}g/g$, P<0.05). 3. Western blotting showed that the MMP-2 level was increased as a result of the bleomycin instillation and highest in the 14 days after bleomycin instillation. 4. In zymography, the active forms of MMP-2 were significantly increased as a result of the $IFN-{\gamma}$ treatment 3 days after the bleomycin instillation, bleomycin+$IFN-{\gamma}$ group (bleomycin group : bleomycin+$IFN-{\gamma}$ group=$209.63{\pm}7.60%:407.66{\pm}85.34%$, P<0.05), but 14 days after the bleomycin instillation, the active forms of MMP-2 were significantly reduced as a result of the $IFN-{\gamma}$ treatment (bleomycin group : bleomycin+$IFN-{\gamma}$ group=$159.36{\pm}20.93%:97.23{\pm}12.50%$, P<0.05). 5. The IL-4 levels were lower in the bleomycin and bleomycin+$IFN-{\gamma}$ groups but this was not significant, and the IL-13 levels showed no difference between the experiment groups. Conclusion : The author found that lung inflammation was increased in the early period but the pulmonary fibrosis was inhibited in the late stage as a result of $IFN-{\gamma}$. The inhibition of pulmonary fibrosis by $IFN-{\gamma}$ appeared to be associated with the inhibition of MMP-2 activation by $IFN-{\gamma}$. Further studies on the mechanism of the regulation of MMP-2 activation and the effects of MMP-2 activation on pulmonary fibrosis is warranted in the future.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Childhood Kidney Diseases
• /
• v.2 no.2
• /
• pp.138-144
• /
• 1998

Purpose : The use of cyclosporine and mitomycin in various immunologic or neoplastic disorders has been known to cause wide-ranged nephrotoxic effects including thrombotic microangiopathy. However, the mechanism of nephrotoxicity of these drugs has not been studied adequately, so that present experimental study has been undertaken to find out whether these drugs can cause direct damage to the kidney and to clarify the pathogenetic mechanism of nephrotoxic effect of these drugs. Materials and methods : Sprague-Dawley rats weighing 250-300 gm were used for experimental animals and unilateral renal perfusion technique, modified from the method described by Hoyer et al was used. Isolation of left kidney from systemic circulation was made by clamping aorta and left renal vein and a hole was punctured in the anterior wall of the left renal vein. Cyclosporine (2.5 mg in 4 ml solution) and mitomycin (1.6 mg in 4ml solution) were infused through left renal artery and normal saline was used in control rats. Forty-eight hours after infusion of the drugs, animals were sacrificed and left kidney removed and processed for histologic examination. Total ischemic time of left kidney was less than 15 minutes: Results : Cyclosporine-perfused group showed severe swelling of glomerular endothelial ceil along with swelling of glomerular epithelial cell and interstitial vascular endothelial cell. Mitomycin-perfused group also showed severe swelling of glomerular endothelial and epithelial cells. And in addition to these findings, they demonstrated platelets aggregation, swelling and degranulation of platelets and fibrin accumulation in some of the capillaries, indicating occurrance of thrombotic microangiopathy. Conclusion : present experiment indicates that cyclosporine and mitomycin can cause direct toxic injury to renal endothelial cell. And this direct toxic damage to endothelial cell seems to be an important initiating event for the development of thrombotic microangiopathy.

• Journal of the Korean Society of Radiology
• /
• v.14 no.6
• /
• pp.773-780
• /
• 2020

With the development of the 4th industrial, research is being conducted to prevent diseases and reduce damage in various fields of science and technology such as medicine, health, and bio. As a result, artificial intelligence technology has been introduced and researched for image analysis of radiological examinations. In this paper, we will directly apply a deep learning model for classification and detection of pneumonia using chest X-ray images, and evaluate whether the deep learning model of the Inception series is a useful model for detecting pneumonia. As the experimental material, a chest X-ray image data set provided and shared free of charge by Kaggle was used, and out of the total 3,470 chest X-ray image data, it was classified into 1,870 training data sets, 1,100 validation data sets, and 500 test data sets. I did. As a result of the experiment, the result of metric evaluation of the Inception V3 deep learning model was 94.80% for accuracy, 97.24% for precision, 94.00% for recall, and 95.59 for F1 score. In addition, the accuracy of the final epoch for Inception V3 deep learning modeling was 94.91% for learning modeling and 89.68% for verification modeling for pneumonia detection and classification of chest X-ray images. For the evaluation of the loss function value, the learning modeling was 1.127% and the validation modeling was 4.603%. As a result, it was evaluated that the Inception V3 deep learning model is a very excellent deep learning model in extracting and classifying features of chest image data, and its learning state is also very good. As a result of matrix accuracy evaluation for test modeling, the accuracy of 96% for normal chest X-ray image data and 97% for pneumonia chest X-ray image data was proven. The deep learning model of the Inception series is considered to be a useful deep learning model for classification of chest diseases, and it is expected that it can also play an auxiliary role of human resources, so it is considered that it will be a solution to the problem of insufficient medical personnel. In the future, this study is expected to be presented as basic data for similar studies in the case of similar studies on the diagnosis of pneumonia using deep learning.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.10
• /
• pp.1544-1557
• /
• 2020

Objective: Genomic selection (GS) is becoming popular in animals' genetic development. We, therefore, investigated the single-step genomic best linear unbiased prediction (ssGBLUP) as tool for GS, and compared its efficacy with the traditional pedigree BLUP (pedBLUP) method. Methods: A total of 9,952 males born between 1997 and 2018 under Hanwoo proven-bull selection program was studied. We analyzed body weight at 12 months and carcass weight (kg), backfat thickness, eye muscle area, and marbling score traits. About 7,387 bulls were genotyped using Illumina 50K BeadChip Arrays. Multiple-trait animal model analyses were performed using BLUPF90 software programs. Breeding value accuracy was calculated using two methods: i) Pearson's correlation of genomic estimated breeding value (GEBV) with EBV of all animals (r_M1) and ii) correlation using inverse of coefficient matrix from the mixed-model equations (r_M2). Then, we compared these accuracies by overall population, info-type (PHEN, phenotyped-only; GEN, genotyped-only; and PH+GEN, phenotyped and genotyped), and bull-types (YBULL, young male calves; CBULL, young candidate bulls; and PBULL, proven bulls). Results: The r_M1 estimates in the study were between 0.90 and 0.96 among five traits. The r_M1 estimates varied slightly by population and info-type, but noticeably by bull-type for traits. Generally average r_M2 estimates were much smaller than r_M1 (pedBLUP, 0.40 to0.44; ssGBLUP, 0.41 to 0.45) at population level. However, r_M2 from both BLUP models varied noticeably across info-types and bull-types. The ssGBLUP estimates of r_M2 in PHEN, GEN, and PH+ GEN ranged between 0.51 and 0.63, 0.66 and 0.70, and 0.68 and 0.73, respectively. In YBULL, CBULL, and PBULL, the r_M2 estimates ranged between 0.54 and 0.57, 0.55 and 0.62, and 0.70 and 0.74, respectively. The pedBLUP based r_M2 estimates were also relatively lower than ssGBLUP estimates. At the population level, we found an increase in accuracy by 2.0% to 4.5% among traits. Traits in PHEN were least influenced by ssGBLUP (0% to 2.0%), whereas the highest positive changes were in GEN (8.1% to 10.7%). PH+GEN also showed 6.5% to 8.5% increase in accuracy by ssGBLUP. However, the highest improvements were found in bull-types (YBULL, 21% to 35.7%; CBULL, 3.3% to 9.3%; PBULL, 2.8% to 6.1%). Conclusion: A noticeable improvement by ssGBLUP was observed in this study. Findings of differential responses to ssGBLUP by various bulls could assist in better selection decision making as well. We, therefore, suggest that ssGBLUP could be used for GS in Hanwoo proven-bull evaluation program.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.89-115
• /
• 2019

This study was conducted to present the stylistic differences between Arthur Conan Doyle and Agatha Christie, famous as writers of classical mystery novels, through data analysis, and further to present the analytical methodology of the study of style based on text mining. The reason why we chose mystery novels for our research is because the unique devices that exist in classical mystery novels have strong stylistic characteristics, and furthermore, by choosing Arthur Conan Doyle and Agatha Christie, who are also famous to the general reader, as subjects of analysis, so that people who are unfamiliar with the research can be familiar with them. The primary objective of this study is to identify how the differences exist within the text and to interpret the effects of these differences on the reader. Accordingly, in addition to events and characters, which are key elements of mystery novels, the writer's grammatical style of writing was defined in style and attempted to analyze it. Two series and four books were selected by each writer, and the text was divided into sentences to secure data. After measuring and granting the emotional score according to each sentence, the emotions of the page progress were visualized as a graph, and the trend of the event progress in the novel was identified under eight themes by applying Topic modeling according to the page. By organizing co-occurrence matrices and performing network analysis, we were able to visually see changes in relationships between people as events progressed. In addition, the entire sentence was divided into a grammatical system based on a total of six types of writing style to identify differences between writers and between works. This enabled us to identify not only the general grammatical writing style of the author, but also the inherent stylistic characteristics in their unconsciousness, and to interpret the effects of these characteristics on the reader. This series of research processes can help to understand the context of the entire text based on a defined understanding of the style, and furthermore, by integrating previously individually conducted stylistic studies. This prior understanding can also contribute to discovering and clarifying the existence of text in unstructured data, including online text. This could help enable more accurate recognition of emotions and delivery of commands on an interactive artificial intelligence platform that currently converts voice into natural language. In the face of increasing attempts to analyze online texts, including New Media, in many ways and discover social phenomena and managerial values, it is expected to contribute to more meaningful online text analysis and semantic interpretation through the links to these studies. However, the fact that the analysis data used in this study are two or four books by author can be considered as a limitation in that the data analysis was not attempted in sufficient quantities. The application of the writing characteristics applied to the Korean text even though it was an English text also could be limitation. The more diverse stylistic characteristics were limited to six, and the less likely interpretation was also considered as a limitation. In addition, it is also regrettable that the research was conducted by analyzing classical mystery novels rather than text that is commonly used today, and that various classical mystery novel writers were not compared. Subsequent research will attempt to increase the diversity of interpretations by taking into account a wider variety of grammatical systems and stylistic structures and will also be applied to the current frequently used online text analysis to assess the potential for interpretation. It is expected that this will enable the interpretation and definition of the specific structure of the style and that various usability can be considered.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Asia pacific journal of information systems
• /
• v.21 no.2
• /
• pp.89-116
• /
• 2011

In collaborative tagging systems such as Delicious.com and Flickr.com, users assign keywords or tags to their uploaded resources, such as bookmarks and pictures, for their future use or sharing purposes. The collection of resources and tags generated by a user is called a personomy, and the collection of all personomies constitutes the folksonomy. The most significant need of the folksonomy users Is to efficiently find useful resources or experts on specific topics. An excellent ranking algorithm would assign higher ranking to more useful resources or experts. What resources are considered useful In a folksonomic system? Does a standard superior to frequency or freshness exist? The resource recommended by more users with mere expertise should be worthy of attention. This ranking paradigm can be implemented through a graph-based ranking algorithm. Two well-known representatives of such a paradigm are Page Rank by Google and HITS(Hypertext Induced Topic Selection) by Kleinberg. Both Page Rank and HITS assign a higher evaluation score to pages linked to more higher-scored pages. HITS differs from PageRank in that it utilizes two kinds of scores: authority and hub scores. The ranking objects of these pages are limited to Web pages, whereas the ranking objects of a folksonomic system are somewhat heterogeneous(i.e., users, resources, and tags). Therefore, uniform application of the voting notion of PageRank and HITS based on the links to a folksonomy would be unreasonable, In a folksonomic system, each link corresponding to a property can have an opposite direction, depending on whether the property is an active or a passive voice. The current research stems from the Idea that a graph-based ranking algorithm could be applied to the folksonomic system using the concept of mutual Interactions between entitles, rather than the voting notion of PageRank or HITS. The concept of mutual interactions, proposed for ranking the Semantic Web resources, enables the calculation of importance scores of various resources unaffected by link directions. The weights of a property representing the mutual interaction between classes are assigned depending on the relative significance of the property to the resource importance of each class. This class-oriented approach is based on the fact that, in the Semantic Web, there are many heterogeneous classes; thus, applying a different appraisal standard for each class is more reasonable. This is similar to the evaluation method of humans, where different items are assigned specific weights, which are then summed up to determine the weighted average. We can check for missing properties more easily with this approach than with other predicate-oriented approaches. A user of a tagging system usually assigns more than one tags to the same resource, and there can be more than one tags with the same subjectivity and objectivity. In the case that many users assign similar tags to the same resource, grading the users differently depending on the assignment order becomes necessary. This idea comes from the studies in psychology wherein expertise involves the ability to select the most relevant information for achieving a goal. An expert should be someone who not only has a large collection of documents annotated with a particular tag, but also tends to add documents of high quality to his/her collections. Such documents are identified by the number, as well as the expertise, of users who have the same documents in their collections. In other words, there is a relationship of mutual reinforcement between the expertise of a user and the quality of a document. In addition, there is a need to rank entities related more closely to a certain entity. Considering the property of social media that ensures the popularity of a topic is temporary, recent data should have more weight than old data. We propose a comprehensive folksonomy ranking framework in which all these considerations are dealt with and that can be easily customized to each folksonomy site for ranking purposes. To examine the validity of our ranking algorithm and show the mechanism of adjusting property, time, and expertise weights, we first use a dataset designed for analyzing the effect of each ranking factor independently. We then show the ranking results of a real folksonomy site, with the ranking factors combined. Because the ground truth of a given dataset is not known when it comes to ranking, we inject simulated data whose ranking results can be predicted into the real dataset and compare the ranking results of our algorithm with that of a previous HITS-based algorithm. Our semantic ranking algorithm based on the concept of mutual interaction seems to be preferable to the HITS-based algorithm as a flexible folksonomy ranking framework. Some concrete points of difference are as follows. First, with the time concept applied to the property weights, our algorithm shows superior performance in lowering the scores of older data and raising the scores of newer data. Second, applying the time concept to the expertise weights, as well as to the property weights, our algorithm controls the conflicting influence of expertise weights and enhances overall consistency of time-valued ranking. The expertise weights of the previous study can act as an obstacle to the time-valued ranking because the number of followers increases as time goes on. Third, many new properties and classes can be included in our framework. The previous HITS-based algorithm, based on the voting notion, loses ground in the situation where the domain consists of more than two classes, or where other important properties, such as "sent through twitter" or "registered as a friend," are added to the domain. Forth, there is a big difference in the calculation time and memory use between the two kinds of algorithms. While the matrix multiplication of two matrices, has to be executed twice for the previous HITS-based algorithm, this is unnecessary with our algorithm. In our ranking framework, various folksonomy ranking policies can be expressed with the ranking factors combined and our approach can work, even if the folksonomy site is not implemented with Semantic Web languages. Above all, the time weight proposed in this paper will be applicable to various domains, including social media, where time value is considered important.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.1-20
• /
• 2013

Nowadays, social network is a huge communication platform for providing people to connect with one another and to bring users together to share common interests, experiences, and their daily activities. Users spend hours per day in maintaining personal information and interacting with other people via posting, commenting, messaging, games, social events, and applications. Due to the growth of user's distributed information in social network, there is a great potential to utilize the social data to enhance the quality of recommender system. There are some researches focusing on social network analysis that investigate how social network can be used in recommendation domain. Among these researches, we are interested in taking advantages of the interaction between a user and others in social network that can be determined and known as social relationship. Furthermore, mostly user's decisions before purchasing some products depend on suggestion of people who have either the same preferences or closer relationship. For this reason, we believe that user's relationship in social network can provide an effective way to increase the quality in prediction user's interests of recommender system. Therefore, social relationship between users encountered from social network is a common factor to improve the way of predicting user's preferences in the conventional approach. Recommender system is dramatically increasing in popularity and currently being used by many e-commerce sites such as Amazon.com, Last.fm, eBay.com, etc. Collaborative filtering (CF) method is one of the essential and powerful techniques in recommender system for suggesting the appropriate items to user by learning user's preferences. CF method focuses on user data and generates automatic prediction about user's interests by gathering information from users who share similar background and preferences. Specifically, the intension of CF method is to find users who have similar preferences and to suggest target user items that were mostly preferred by those nearest neighbor users. There are two basic units that need to be considered by CF method, the user and the item. Each user needs to provide his rating value on items i.e. movies, products, books, etc to indicate their interests on those items. In addition, CF uses the user-rating matrix to find a group of users who have similar rating with target user. Then, it predicts unknown rating value for items that target user has not rated. Currently, CF has been successfully implemented in both information filtering and e-commerce applications. However, it remains some important challenges such as cold start, data sparsity, and scalability reflected on quality and accuracy of prediction. In order to overcome these challenges, many researchers have proposed various kinds of CF method such as hybrid CF, trust-based CF, social network-based CF, etc. In the purpose of improving the recommendation performance and prediction accuracy of standard CF, in this paper we propose a method which integrates traditional CF technique with social relationship between users discovered from user's behavior in social network i.e. Facebook. We identify user's relationship from behavior of user such as posts and comments interacted with friends in Facebook. We believe that social relationship implicitly inferred from user's behavior can be likely applied to compensate the limitation of conventional approach. Therefore, we extract posts and comments of each user by using Facebook Graph API and calculate feature score among each term to obtain feature vector for computing similarity of user. Then, we combine the result with similarity value computed using traditional CF technique. Finally, our system provides a list of recommended items according to neighbor users who have the biggest total similarity value to the target user. In order to verify and evaluate our proposed method we have performed an experiment on data collected from our Movies Rating System. Prediction accuracy evaluation is conducted to demonstrate how much our algorithm gives the correctness of recommendation to user in terms of MAE. Then, the evaluation of performance is made to show the effectiveness of our method in terms of precision, recall, and F1-measure. Evaluation on coverage is also included in our experiment to see the ability of generating recommendation. The experimental results show that our proposed method outperform and more accurate in suggesting items to users with better performance. The effectiveness of user's behavior in social network particularly shows the significant improvement by up to 6% on recommendation accuracy. Moreover, experiment of recommendation performance shows that incorporating social relationship observed from user's behavior into CF is beneficial and useful to generate recommendation with 7% improvement of performance compared with benchmark methods. Finally, we confirm that interaction between users in social network is able to enhance the accuracy and give better recommendation in conventional approach.