• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1043-1044
• /
• 2023

'MO:TIVE'는 AI 및 IoT를 활용하여 자기계발을 촉진하는 모바일 서비스로, 사용자 정보 학습과 정밀한 추천을 제공하며 생성형 AI를 활용한 개인화 조언을 제공한다. 이를 통해 사용자는 스마트 워치를 통해 자투리 시간을 효과적으로 활용하여 자기계발과 삶의 질을 향상을 기대할 수 있으며 지속적인 개선과 학습을 통해 더 나은 사용자 경험을 제공한다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.249-263
• /
• 2023

Collaborative Filtering, a representative recommendation system methodology, consists of two approaches: neighbor methods and latent factor models. Among these, the latent factor model using matrix factorization decomposes the user-item interaction matrix into two lower-dimensional rectangular matrices, predicting the item's rating through the product of these matrices. Due to the factor vectors inferred from rating patterns capturing user and item characteristics, this method is superior in scalability, accuracy, and flexibility compared to neighbor-based methods. However, it has a fundamental drawback: the need to reflect the diversity of preferences of different individuals for items with no ratings. This limitation leads to repetitive and inaccurate recommendations. The Adaptive Deep Latent Factor Model (ADLFM) was developed to address this issue. This model adaptively learns the preferences for each item by using the item description, which provides a detailed summary and explanation of the item. ADLFM takes in item description as input, calculates latent vectors of the user and item, and presents a method that can reflect personal diversity using an attention score. However, due to the requirement of a dataset that includes item descriptions, the domain that can apply ADLFM is limited, resulting in generalization limitations. This study proposes a Generalized Adaptive Deep Latent Factor Recommendation Model, G-ADLFRM, to improve the limitations of ADLFM. Firstly, we use item ID, commonly used in recommendation systems, as input instead of the item description. Additionally, we apply improved deep learning model structures such as Self-Attention, Multi-head Attention, and Multi-Conv1D. We conducted experiments on various datasets with input and model structure changes. The results showed that when only the input was changed, MAE increased slightly compared to ADLFM due to accompanying information loss, resulting in decreased recommendation performance. However, the average learning speed per epoch significantly improved as the amount of information to be processed decreased. When both the input and the model structure were changed, the best-performing Multi-Conv1d structure showed similar performance to ADLFM, sufficiently counteracting the information loss caused by the input change. We conclude that G-ADLFRM is a new, lightweight, and generalizable model that maintains the performance of the existing ADLFM while enabling fast learning and inference.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.157-173
• /
• 2021

With the development of information technology, the amount of available information increases daily. However, having access to so much information makes it difficult for users to easily find the information they seek. Users want a visualized system that reduces information retrieval and learning time, saving them from personally reading and judging all available information. As a result, recommendation systems are an increasingly important technologies that are essential to the business. Collaborative filtering is used in various fields with excellent performance because recommendations are made based on similar user interests and preferences. However, limitations do exist. Sparsity occurs when user-item preference information is insufficient, and is the main limitation of collaborative filtering. The evaluation value of the user item matrix may be distorted by the data depending on the popularity of the product, or there may be new users who have not yet evaluated the value. The lack of historical data to identify consumer preferences is referred to as data sparsity, and various methods have been studied to address these problems. However, most attempts to solve the sparsity problem are not optimal because they can only be applied when additional data such as users' personal information, social networks, or characteristics of items are included. Another problem is that real-world score data are mostly biased to high scores, resulting in severe imbalances. One cause of this imbalance distribution is the purchasing bias, in which only users with high product ratings purchase products, so those with low ratings are less likely to purchase products and thus do not leave negative product reviews. Due to these characteristics, unlike most users' actual preferences, reviews by users who purchase products are more likely to be positive. Therefore, the actual rating data is over-learned in many classes with high incidence due to its biased characteristics, distorting the market. Applying collaborative filtering to these imbalanced data leads to poor recommendation performance due to excessive learning of biased classes. Traditional oversampling techniques to address this problem are likely to cause overfitting because they repeat the same data, which acts as noise in learning, reducing recommendation performance. In addition, pre-processing methods for most existing data imbalance problems are designed and used for binary classes. Binary class imbalance techniques are difficult to apply to multi-class problems because they cannot model multi-class problems, such as objects at cross-class boundaries or objects overlapping multiple classes. To solve this problem, research has been conducted to convert and apply multi-class problems to binary class problems. However, simplification of multi-class problems can cause potential classification errors when combined with the results of classifiers learned from other sub-problems, resulting in loss of important information about relationships beyond the selected items. Therefore, it is necessary to develop more effective methods to address multi-class imbalance problems. We propose a collaborative filtering model using CGAN to generate realistic virtual data to populate the empty user-item matrix. Conditional vector y identify distributions for minority classes and generate data reflecting their characteristics. Collaborative filtering then maximizes the performance of the recommendation system via hyperparameter tuning. This process should improve the accuracy of the model by addressing the sparsity problem of collaborative filtering implementations while mitigating data imbalances arising from real data. Our model has superior recommendation performance over existing oversampling techniques and existing real-world data with data sparsity. SMOTE, Borderline SMOTE, SVM-SMOTE, ADASYN, and GAN were used as comparative models and we demonstrate the highest prediction accuracy on the RMSE and MAE evaluation scales. Through this study, oversampling based on deep learning will be able to further refine the performance of recommendation systems using actual data and be used to build business recommendation systems.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.25-44
• /
• 2013

Accessing movie contents has become easier and increased with the advent of smart TV, IPTV and web services that are able to be used to search and watch movies. In this situation, there are increasing search for preference movie contents of users. However, since the amount of provided movie contents is too large, the user needs more effort and time for searching the movie contents. Hence, there are a lot of researches for recommendations of personalized item through analysis and clustering of the user preferences and user profiles. In this study, we propose recommendation system which uses ontology based knowledge base. Our ontology can represent not only relations between metadata of movies but also relations between metadata and profile of user. The relation of each metadata can show similarity between movies. In order to build, the knowledge base our ontology model is considered two aspects which are the movie metadata model and the user model. On the part of build the movie metadata model based on ontology, we decide main metadata that are genre, actor/actress, keywords and synopsis. Those affect that users choose the interested movie. And there are demographic information of user and relation between user and movie metadata in user model. In our model, movie ontology model consists of seven concepts (Movie, Genre, Keywords, Synopsis Keywords, Character, and Person), eight attributes (title, rating, limit, description, character name, character description, person job, person name) and ten relations between concepts. For our knowledge base, we input individual data of 14,374 movies for each concept in contents ontology model. This movie metadata knowledge base is used to search the movie that is related to interesting metadata of user. And it can search the similar movie through relations between concepts. We also propose the architecture for movie recommendation. The proposed architecture consists of four components. The first component search candidate movies based the demographic information of the user. In this component, we decide the group of users according to demographic information to recommend the movie for each group and define the rule to decide the group of users. We generate the query that be used to search the candidate movie for recommendation in this component. The second component search candidate movies based user preference. When users choose the movie, users consider metadata such as genre, actor/actress, synopsis, keywords. Users input their preference and then in this component, system search the movie based on users preferences. The proposed system can search the similar movie through relation between concepts, unlike existing movie recommendation systems. Each metadata of recommended candidate movies have weight that will be used for deciding recommendation order. The third component the merges results of first component and second component. In this step, we calculate the weight of movies using the weight value of metadata for each movie. Then we sort movies order by the weight value. The fourth component analyzes result of third component, and then it decides level of the contribution of metadata. And we apply contribution weight to metadata. Finally, we use the result of this step as recommendation for users. We test the usability of the proposed scheme by using web application. We implement that web application for experimental process by using JSP, Java Script and prot$\acute{e}$g$\acute{e}$ API. In our experiment, we collect results of 20 men and woman, ranging in age from 20 to 29. And we use 7,418 movies with rating that is not fewer than 7.0. In order to experiment, we provide Top-5, Top-10 and Top-20 recommended movies to user, and then users choose interested movies. The result of experiment is that average number of to choose interested movie are 2.1 in Top-5, 3.35 in Top-10, 6.35 in Top-20. It is better than results that are yielded by for each metadata.

• Fashion & Textile Research Journal
• /
• v.23 no.6
• /
• pp.790-798
• /
• 2021

With digital technology innovation, increased data access and mobile network use by consumers, products and services are changing toward pursuing differentiated values for personalization, and personalized markets are rapidly emerging in the fashion industry. This study aims to identify trends in digital customized automation technology by deriving types of digital customizing and analyzing cases by type, and to present directions for the development of digital customizing processes and the use of technology in the future. As a research method, a literature study for a theoretical background, a case study for classification and analysis of types was conducted. The results of the study are as follows. The types of digital customizing can be classified into three types: 'cooperative customization', 'selective composition and combination', 'transparent suggestion', and automation technologies shown in each type include 3D printing, 3D virtual clothing, robot mannequin, human automatic measurement program, AR-based fitting service, big data, and AI-based curation function. With the development of digital automation technology, the fashion industry environment is also changing from existing manufacturing-oriented to consumer-oriented, and the production process is rapidly changing with IT and artificial intelligence-based automation technology. The results of this study hope that digital customized automation technology will meet various needs of personalization and customization and present the future direction of digital fashion technology, where fashion brands will expand based on the spread of digital technology.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.179-192
• /
• 2014

Keeping in line with the recent changes in the information technology environment, the online learning environment that supports multiple users' participation such as MOOC (Massive Open Online Courses) has become important. One of the largest professional associations in Information Technology, IEEE Computer Society, announced that "Supporting New Learning Styles" is a crucial trend in 2014. Popular MOOC services, CourseRa and edX, have continued to build active learning environment with a large number of lectures accessible anywhere using smart devices, and have been used by an increasing number of users. In addition, collaborative web services (e.g., blogs and Wikipedia) also support the creation of various user-uploaded learning materials, resulting in a vast amount of new lectures and learning materials being created every day in the online space. However, it is difficult for an online educational system to keep a learner' motivation as learning occurs remotely, with limited capability to share knowledge among the learners. Thus, it is essential to understand which materials are needed for each learner and how to motivate learners to actively participate in online learning system. To overcome these issues, leveraging the constructivism theory and collective intelligence, we have developed a social bookmarking system called WeStudy, which supports learning material sharing among the users and provides personalized learning material recommendations. Constructivism theory argues that knowledge is being constructed while learners interact with the world. Collective intelligence can be separated into two types: (1) collaborative collective intelligence, which can be built on the basis of direct collaboration among the participants (e.g., Wikipedia), and (2) integrative collective intelligence, which produces new forms of knowledge by combining independent and distributed information through highly advanced technologies and algorithms (e.g., Google PageRank, Recommender systems). Recommender system, one of the examples of integrative collective intelligence, is to utilize online activities of the users and recommend what users may be interested in. Our system included both collaborative collective intelligence functions and integrative collective intelligence functions. We analyzed well-known Web services based on collective intelligence such as Wikipedia, Slideshare, and Videolectures to identify main design factors that support collective intelligence. Based on this analysis, in addition to sharing online resources through social bookmarking, we selected three essential functions for our system: 1) multimodal visualization of learning materials through two forms (e.g., list and graph), 2) personalized recommendation of learning materials, and 3) explicit designation of learners of their interest. After developing web-based WeStudy system, we conducted usability testing through the heuristic evaluation method that included seven heuristic indices: features and functionality, cognitive page, navigation, search and filtering, control and feedback, forms, context and text. We recruited 10 experts who majored in Human Computer Interaction and worked in the same field, and requested both quantitative and qualitative evaluation of the system. The evaluation results show that, relative to the other functions evaluated, the list/graph page produced higher scores on all indices except for contexts & text. In case of contexts & text, learning material page produced the best score, compared with the other functions. In general, the explicit designation of learners of their interests, one of the distinctive functions, received lower scores on all usability indices because of its unfamiliar functionality to the users. In summary, the evaluation results show that our system has achieved high usability with good performance with some minor issues, which need to be fully addressed before the public release of the system to large-scale users. The study findings provide practical guidelines for the design and development of various systems that utilize collective intelligence.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.391-406
• /
• 2024

The current distribution of digital news has the potential to produce politically biased information for users as a result of individual choices and media selection based on those choices. Consequently, this research explored the factors affecting individual news selection and the effects of opinion changes and political participation that can occur when news tailored to users' partisan preferences is recommended. The phenomenon of selective exposure has been shown to be stronger when individuals utilize more limited information processing, experience higher discussion efficacy among groups with similar political beliefs. Furthermore, When a selective exposure group was randomly provided with a one-way message news that matched their partisan leanings, it was found that opinion consolidation, opinion-reinforcing information processing, and online political participation. On the other hand, when they were randomly presented with two-way messaging news in which the media balanced two competing partisan positions, they were found to be more likely to understand the other side's views and arguments, and more willing to adjust their existing opinions. We are confirmed that the balanced use of various opinions is very important in deliberative democratic process.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.265-274
• /
• 2021

This study empirically analyzed the users' experiences with the Netflix thumbnail curation based on the Technology Acceptance Model(TAM). According to the correlation analysis results, the higher the dependence on the thumbnails, the higher the satisfaction with the thumbnail curation. Both Perceived Informational Usefulness(PIU) and Perceived Ease of Use(PEOU) had correlations with the degree of satisfaction with the thumbnail curation. In particular, the factors of relevance in PEOU had the greatest impact on the degree of satisfaction and this result proved that the suitability factors of the thumbnails had significant correlations with the degree of satisfaction. The degree of satisfaction with the thumbnail curation also positively correlated with Netflix's overall degree of satisfaction and behavioral intention to use the Netflix. This study demonstrated the suitability of the TAM as a UX evaluation tool for the Netflix thumbnail curation.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.389-390
• /
• 2002

It is important that acquire information about if customer has some habit in electronic commerce application of internet base that led in recommendation service for customer in dynamic web contents supply. Collaborative filtering that has been used as a standard approach to Web personalization can not get rapidly user's preference change due to static user profiles and has shortcomings such as reliance on user ratings, lack of scalability, and poor performance in the high-dimensional data. In order to overcome this drawbacks, Web usage mining has been prevalent. Web usage mining is a technique that discovers patterns from We usage data logged to server. Specially. a technique that discovers Web usage patterns and clusters patterns is used. However, the discovery of patterns using Afriori algorithm creates many useless patterns. In this paper, the enhanced method for the construction of dynamic user profiles using validated Web usage patterns is proposed. First, to discover patterns Apriori is used and in order to create clusters for user profiles, ARHP algorithm is chosen. Before creating clusters using discovered patterns, validation that removes useless patterns by Dempster-Shafer theory is performed. And user profiles are created dynamically based on current user sessions for Web personalization.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.489-498
• /
• 2012

This paper consists of two parts: In the first part, we describe our work to build hierarchical knowledge base of digital library patron's research interests and learning topics in various scholarly areas through analyzing well classified Electronic Theses and Dissertations (ETDs) of NDLTD Union catalog. Journal articles from ACM Transactions and conference web sites of computing areas also are added in the analysis to specialize computing fields. This hierarchical knowledge base would be a useful tool for many social computing and information service applications, such as personalization, recommender system, text mining, technology opportunity mining, information visualization, and so on. In the second part, we compare four grouping algorithms to select best one for our data mining researches by testing each one with the hierarchical knowledge base we described in the first part. From these two studies, we intent to show traditional verification methods for social community miming researches, based on interviewing and answering questionnaires, which are expensive, slow, and privacy threatening, can be replaced with systematic, consistent, fast, and privacy protecting methods by using our suggested hierarchical knowledge base.