• International journal of advanced smart convergence
• /
• 제10권3호
• /
• pp.131-142
• /
• 2021

Recently, there has been an active service that provides customized news to news subscribers. In this study, we intend to design a customized news service system through Deep Learning-based Social Network Service (SNS) activity analysis, applying real news and avoiding fake news. In other words, the core of this study is the study of delivery methods and delivery devices to provide customized news services based on analysis of users, SNS activities. First of all, this research method consists of a total of five steps. In the first stage, social network service site access records are received from user terminals, and in the second stage, SNS sites are searched based on SNS site access records received to obtain user profile information and user SNS activity information. In step 3, the user's propensity is analyzed based on user profile information and SNS activity information, and in step 4, user-tailored news is selected through news search based on user propensity analysis results. Finally, in step 5, custom news is sent to the user terminal. This study will be of great help to news service providers to increase the number of news subscribers.

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.570-575
• /
• 2013

Enhancing utilization of buildings is gaining in importance in response to a challenging economy; thus, there is a need for a method that analyzes space, user, and user activity in an integrated way to provide project stakeholders with utilization information to support their decision-making about buildings. Conventional methods, such as architectural programming and post-occupancy evaluation, lack a formal relationship between user activity and other information, and therefore, are coarse-grained. This relationship has been formalized by two relatively new methods that provide fine-grained utilization information: workplace planning and space-use analysis. We characterize these two methods with focuses on their usage in different phases (i.e., planning, design, occupancy), required information that needs to be gathered, and the achievement and limitations in terms of three criteria, i.e., consistency, efficiency, and transparency. This characterization would not only help project stakeholders select and use a method that best meets their purposes for enhancing utilization of their buildings, but also provide researchers with promising research topics regarding enhancing utilization of buildings.

• 한국도서관정보학회지
• /
• 제43권1호
• /
• pp.221-239
• /
• 2012

도서관 이용자의 복잡한 환경과 이용패턴에 따라 생성된 정보는 지식구조화를 통해 이용자에게 적합한 상황인지 정보서비스에 활용된다. 따라서, 도서관 이용자의 다양한 컨텍스트를 정의하고 상호 관련된 컨텍스트의 지식구조화를 위한 컨텍스트 모델 구축이 필수적인 요건이다. 본 연구에서는 컨텍스트의 개념 및 컨텍스트 모델링을 고찰하고, Engestrom의 행위이론의 개념을 활용하여 도서관 이용자의 행위 모델을 1) 주체, 2) 목적, 3) 도구, 4) 노동단위, 5) 커뮤니티, 그리고 6) 규칙으로 설계하였다. 또한, 도서관 이용자의 컨텍스트를 분석하기 위하여 행위정보를 수집하여 그들의 행태를 관찰 및 기록하는 사용자 추적법 (Shadow Tracking)을 활용하였고 수집된 행위정보는 CAbAT(Context Analysis based on Activity Theory)의 방법론을 활용하여 도서관 이용자의 컨텍스트를 설계하였다.

• 한국빅데이터학회지
• /
• 제1권2호
• /
• pp.1-8
• /
• 2016

사용자로그는 많은 숨겨진 정보를 포함하고 있지만 데이터 정형화가 이루어지지 않았고, 데이터 크기도 너무 방대하여 처리하기 까다로워서 아직 밝혀져야 할 부분들을 많이 내포하고 있다. 특히 행동마다의 모든 시간정보를 포함하고 있어서 이를 응용하여 많은 부분을 밝혀낼 수 있다. 하지만 로그데이터 자체를 바로 분석으로 사용할 수는 없다. 유저 행동 모델 분석을 위해서는 별도의 프레임워크를 통한 변환과정들이 필요하다. 이 때문에 유저 행동모델 분석 프레임워크를 먼저 파악을 하고 데이터에 접근해야 한다. 이 논문에서는, 우리는 유저 행동모델을 효과적으로 분석하기 위한 프레임워크 모델을 제안한다. 본 모델은 대규모 데이터를 빨리 처리하기 위한 분산환경에서의 MapReduce 프로세스와 유저별 행동분석을 위한 데이터 구조 설계에 대한 부분을 포함한다. 또한 실제 온라인 서비스 로그의 구조를 바탕으로 어떤 방식으로 MapReduce를 처리하고 어떤 방식으로 유저행동모델을 분석을 위해 데이터 구조를 어떤식으로 변형할지 설명하고, 이를 통해 어떤 방식의 모델 분석으로 이어질지에 대해 상세히 설명한다. 이를 통해 대규모 로그 처리방법과 분석모델 설계에 대한 기초를 다질 수 있을 것이다.

• 지식경영연구
• /
• 제16권3호
• /
• pp.81-102
• /
• 2015

With the rapid development of digital media, there has been a huge change in a way of communication, a process of information diffusion and a role of traditional media. Not like mass media, social media enables users to generate and tap into the opinions of a larger world. From that reason, social media is impacting marketing strategies. However, still social media marketing researches just focus on case study, analysis of users motivation or analysis of power user's usage pattern. Word-of-mouth has always been important especially in marketing area. In social media, word-of-mouth depends on each user that's why this research focuses on individual user's activity in SNS. I defined 4 factors (produce, diffusion, network size, activity of network size enlarge) that are effect on activity and verified hypothesis by multiple regression analysis, hierarchical regression analysis and moderated multiple regression.

• 품질경영학회지
• /
• 제44권1호
• /
• pp.199-214
• /
• 2016

Purpose: The present study was designed to examine the casual relationships among performance and arts information service quality, initial trust, user satisfaction, reuse intention and prosumer activity in social network service(SNS). Also, we intended to explore significant factors on use performance of SNS through causal model analysis in the viewpoint of total effect. Methods: As a survey tool, questionnaire has obtained validity and reliability through literature survey, exploratory survey and pretest and sample 403 was selected. For statistical treatment of pretest and main analysis, SPSS18.0 and AMOS18.0 were employed and structural equation model was employed as analysis method. Results: Result of this study shows as follows. Two factors (precision and reciprocal action) have an effect on user satisfaction, initial trust, reuse intention and prosumer activity. We found that with an importance of initial trust, prosumer activity can be a useful and significant factor in causal relationship of SNS. Conclusion: The present study shows that two factors(precision and reciprocal action) in via of initial trust, were important factors that related companies have to emphasize to raise performance, And also we confirmed new factor 'prosumer activity' through this study. However, the present study has some limitations to be studied in the future.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2005년도 춘계 학술발표대회 논문집
• /
• pp.48-49
• /
• 2005

• 대한건축학회논문집:계획계
• /
• 제35권1호
• /
• pp.37-46
• /
• 2019

The energy of the building is influenced by the user 's activity due to the population, society, and economic characteristics of the building user. In order to obtain accurate energy information, the difference in the amount of energy consumption by the activities and characteristics of building users should be identified. The purpose of the study is to identify the difference in the amount of energy consumption by the user's activities in the same building, and to analyse the relationship between user's activities and demographic, social and economic characteristics. For research, energy simulation is performed based on actual user activity schedule. The results of the simulation were clustered by using K-Means clustering, a machine learning technique. As a result, four types of users were derived based on the amount of energy consumption. The more energy used in a cluster, the lower the user's income level and older. The longer a user's indoor activity times, the higher the energy use, and these activities relate to the user's characteristics. There is more than twice the difference between the group that uses the least energy consumption and the group that uses the most energy consumption.

• 국제초고층학회논문집
• /
• 제12권1호
• /
• pp.83-91
• /
• 2023

Under the dual pressure of population growth and land shortage, threedimensional development is the inevitable choice for cities in China. In such a scenario, a mixed-use complex has considerable potential in its realization and research. Based on space syntax and the three-dimensional visibility graph analysis, this paper describes the spatial and functional layout of the Shanghai Super Brand Mall and studies the relationship between spatial visibility and user behaviour through linear regression analysis and correlation analysis. This paper studies three different types of user behaviour, namely, path selection, staying selection, and store selection, and finds that spatial visibility and accessibility have different effects on user behaviour depending on the type and purpose of the activity. This paper reveals the influence of spatial and functional layout on user behaviour and puts forward the corresponding design strategy under the three-dimensional environment.

• 한국조경학회지
• /
• 제30권1호
• /
• pp.29-43
• /
• 2002

The purpose of this paper is to examine atmospherical factors affecting user's satisfaction in natural park to answer the research question: what are the effects of atmosphere on user's satisfaction in natural parks(NP). After reviewing the literature, mechanism of NP, and use elements in NP, We constructed the conceptual framework and have formulated the hypothesis of this research. We had obtained data through a questionnaire, which surveyed 508 visitors at 6 of the 73 NP in Korea in 2001, based on stratified sampling method. We have analyzed the data using descriptive statistical methods, the mean difference test, Pearson's correlation analysis, and the multiple linear regression method. We found that 1) the five atmospheric variables, j.e., number of users(NOU), crowding, damage to park resources(DPR), and maintenance of park resources and facilities(MPRF), encounter level(EL) affecting user's satisfaction, have tuned out to be statistically significant at a five percent level. The direction of the relationship between user's satisfaction and MPRF, NOU, EL is the same as that of the dependent variable and the opposite of crowding, and BPR, 2) in bivariate analysis, the positive relationships between user's satisfaction and park resources, MPRF are fairly high and statistically significant. The higher the value of DPR, and crowing, the lower the degree of user's satisfaction, 3) in multivariate analysis, such variables as NOU, crowding, DPR, EL, and MPRF affecting user's satisfaction have been statistically significant at five percent level, and 4) the relative contribution of MPRF, park resources, park facilities, NOU, crowding, DPR, and size of activity space on user's satisfaction have been determined to have respectively 6.00, 4.78, 2.53, 1.83, 1.64, 1.59 and 2.03 times more important than that of EL. Among the atmospheric variables, MPRF is the most important at 1.26 times higher than that of park resources. The research results suggest that the development of devices for the increase in user's satisfaction and user management program based on the knowledge we have found, be recommended in the planning and development process of natural park. The approach adopted by this research is valid and useful for evaluation criteria of NP. It is recommended that more empirical studies by activity types, activity spaces, and seasons on atmospheric elements affecting user's satisfaction be performed in the future.