• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.706-712
• /
• 2015

These days, much information is provided as a list of summaries through mobile services. In this regard, users consume information in which they are interested by observing the list and not by expressing their interest explicitly or implicitly through rating content or clicking links. Therefore, to appropriately model a user's interest, it is necessary to detect latent interest content. In this study, we propose a method for reasoning latent interest of a user by analyzing mobile content consumption logs of the user. Specifically, since erroneous reasoning will drastically degrade service quality, a unanimity ensemble method is adopted to maximize precision. In this method, an item is determined as the subject of latent interest only when multiple classifiers considering various aspects of the log unanimously agree. Accurate reasoning of latent interest will contribute to enhancing the quality of personalized services such as interest-based recommendation systems.

• KIISE Transactions on Computing Practices
• /
• v.21 no.11
• /
• pp.733-738
• /
• 2015

User demographic information is necessary in order to improve the quality of personalized services such as recommendation systems. Mobile data, especially text data, is known to be effective for prediction of user demographic information. However, mobile text data has privacy issues so that its utilization is limited. In this regard, we introduce an on-device gender prediction framework utilizing mobile text data while minimizing the privacy issue. Discriminative word and emoticon sets of each gender are constructed from web documents written by authors of each gender. After gender prediction is performed by comparing discriminative word and emoticon sets with a user's mobile text data, an ensemble method that combines two prediction results draws a final result. From experiments conducted on real-world mobile text data, the proposed on-device framework shows promising results for gender prediction.

• KIISE Transactions on Computing Practices
• /
• v.21 no.9
• /
• pp.596-603
• /
• 2015

A concept network is an essential knowledge base for semantic search engines, personalized search systems, recommendation systems, and text mining. Recently, studies of extending concept representation using external ontology have been frequently conducted. We thus propose a new way of building 3-dimensional text model-based concept networks using the world knowledge-level Wikipedia ontology. In fact, it is desirable that 'concepts' derived from text documents are defined according to the theoretical framework of formal concept analysis, since relationships among concepts generally change over time. In this paper, concept networks hidden in a given document collection are extracted more reasonably by representing a concept as a term-by-document matrix.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.335-344
• /
• 2021

The purpose of this paper is the development of course data models and learning achievement computation algorithms for enabling the course-embedded assessment(CEA), which is essential of competency-based education in higher education. The previous works related CEA have weakness in the development of the systematic solution for CEA computation. In this paper, we propose data models and algorithms to implement competency-based assessment system. Our data models are composed of a layered architecture of learning outcomes, learning modules and activities, and an associative matrix of learning outcomes and activities. The proposed methods can be applied to the development of the course-embedded assessment system as core modules. We evaluated the effectiveness of our proposed models through applying the models to a practical course, Java Programing. From the result of the experiments we found that our models can be used in the assessment system as a core module.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.537-542
• /
• 2021

Smart TVs provide a variety of services and information compared to existing TVs based on the Internet. In order to provide more personalized services or information, it is necessary to analyze users' viewing patterns and provide customized services or information based on them. The proposed system receives the user's TV viewing pattern, analyzes it, and recommends a TV program or movie as customized information to the user. For this, the system was constructed with a preprocessor and a deep learning model. The preprocessor refines the name of the TV program watched by the user, the date the TV program was watched, and the watched time. Then, the multi-attribute LSTM model trains the refined data and performs prediction.The proposed system is a system that provides customized information to users, and is believed to be a leading technology in digital convergence that combines existing IoT technology and deep learning technology.

• Journal of Information Technology Services
• /
• v.21 no.2
• /
• pp.109-126
• /
• 2022

The number and variety of products and services offered by companies have increased dramatically, providing customers with more choices to meet their needs. As a solution to this information overload problem, the provision of tailored services to individuals has become increasingly important, and the personalized recommender systems have been widely studied and used in both academia and industry. Existing recommender systems face important problems in practical applications. The most important problem is that it cannot clearly explain why it recommends these products. In recent years, some researchers have found that the explanation of recommender systems may be very useful. As a result, users are generally increasing conversion rates, satisfaction, and trust in the recommender system if it is explained why those particular items are recommended. Therefore, this study presents a methodology of providing an explanatory function of a recommender system using a review text left by a user. The basic idea is not to use all of the user's reviews, but to provide them in a summarized form using only reviews left by similar users or neighbors involved in recommending the item as an explanation when providing the recommended item to the user. To achieve this research goal, this study aims to provide a product recommendation list using user-based collaborative filtering techniques, combine reviews left by neighboring users with each product to build a model that combines text summary methods among deep learning-based natural language processing methods. Using the IMDb movie database, text reviews of all target user neighbors' movies are collected and summarized to present descriptions of recommended movies. There are several text summary methods, but this study aims to evaluate whether the review summary is well performed by training the Sequence-to-sequence+attention model, which is a representative generation summary method, and the BertSum model, which is an extraction summary model.

• Journal of Advanced Technology Convergence
• /
• v.2 no.3
• /
• pp.33-41
• /
• 2023

This study aimed to improve the quality of classes through the application experience analysis after applying the adult nursing simulation practice modules with PBL. Quantitative and qualitative data such as from satisfaction, validity, self-reflection, and lecture evaluation in 68 nursing students were analyzed after the semester. Satisfaction was 4.64 points out of 5 points, and 'I want to recommend this class to other friends' was the highest. It was appropriate for the validity as 64.7% to 100% positve answer. From the qualitative data analysis of lecture evaluation, it was categorized into 5 thematic groups : 'increased immersion related to a lively class environment', 'growth of knowledge and skills through learners' active participation', 'improvement of mutual collaboration skills through team-based problem-solving process', 'Improvement of problem-solving ability through situational crisis coping process' and 'Improvement of individual comprehension through close teaching'. The continuous development of PBL learning strategies and development of various scenarios are required in the future.

• Journal of the Korean Society for information Management
• /
• v.40 no.1
• /
• pp.175-198
• /
• 2023

This study aimed to investigate the difference in response to reading as shown in book reports by personality type and interest type. For this purpose, personality type analysis data, interest type analysis data, and book report data written in subject reading activities were collected from 81 third graders at D Science High School in Daejeon. Topic analysis was conducted on the collected book reports, and the probability of a topic being mentioned was statistically tested according to personality type (thinking type, feeling type) and interest type (investigative type, types other than investigative). Subsequently, the conceptual connection structure of words was measured by keyword network analysis, and the analysis results of topic modeling were complemented by the centrality index. As a result of the study, the topic regression analysis showed statistically significant differences between thinking type (T) and feeling type (F) in topic 2 (understanding and studying) and topic 3 (reading and thinking), and statistically significant differences between investigative type and non-investigative type in topic 2 (understanding and studying). The results of this study can be used as a basis for tailored book recommendations and personalized reading education.

• Informatization Policy
• /
• v.30 no.3
• /
• pp.92-121
• /
• 2023

As music streaming services (MSS) involve various interactions with users during the music consumption process, it is important to understand the user experience and manage the service accordingly. This study developed a user experience model for MSS by theoretically linking the quality characteristics considered important by music service users with the structure of user experience. PLS analysis was then performed using survey data to test the model. As a result, functionality (search, browsing, and personalized recommendation), UI usability, content quality (currentness, sufficiency, relevance), and monetary cost were found to be key experience factors that determine the experience consequence, i.e., user satisfaction. In addition, in a supplementary analysis comparing domestic and global services, differences in user experience were found between the two groups in terms of functionality and content quality. The user experience model of MSS proposed in this study serves as a new foundation for theory-based research in this field and provides meaningful implications for the competitive landscape among music streaming service platforms and for their competitive strategies.

• The Journal of Korean Academy of Prosthodontics
• /
• v.48 no.1
• /
• pp.48-54
• /
• 2010

Purpose: The objective of this study was to evaluate and compare the accuracy of impression body taking by the closed and the open tray impression technique with 3 types of impression tray. Individual tray, metal stock tray and polycarbonate tray were used. Materials and methods: Nine closed tray impressions were taken by individual tray, metal stock tray and polycarbonate stock tray, respectively with polyether impression material. 9 open tray impressions were also acquired by same manner. Precision analysis on the master models was performed by attaching the reference frameworks with alternate single screws and measuring the vertical fit discrepancy of respective analogues in working cast with a stereo microscope. Data were analyzed by 1 way ANOVA and independent t-test. Results: The average fit accuracy of impression bodies was calculated. With the closed tray impression technique, there were significant statistical differences in vertical fit discrepancy according to the types of tray. The individual tray group showed the lowest value and the polycarbonate stock tray group represented the highest. With the open tray impression technique, there was no significant difference in vertical fit discrepancy. Significant statistical difference in vertical fit discrepancy was found between the open and the closed impression technique with the polycarbonate stock tray. Conclusion: From the results above, more precise impressions could be acquired by the rigid individual tray compared with the polycarbonate stock tray. It was hard to get consistent accuracy impressions by the closed tray impression technique with polycarbonate stock trays.