• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.6
• /
• pp.2996-3011
• /
• 2017

With rapid growth of web technology and dissemination of smart devices, social networking service(SNS) is widely used. As a result, huge amount of data are generated from SNS such as Twitter, and sentiment analysis of SNS data is very important for various applications and services. In the existing sentiment analysis based on the $Na{\ddot{i}}ve$ Bayes algorithm, a same number of attributes is usually employed to estimate the weight of each class. Moreover, uncountable and meaningless attributes are included. This results in decreased accuracy of sentiment analysis. In this paper two methods are proposed to resolve these issues, which reflect the difference of the number of positive words and negative words in calculating the weights, and eliminate insignificant words in the feature selection step using Multinomial $Na{\ddot{i}}ve$ Bayes(MNB) algorithm. Performance comparison demonstrates that the proposed scheme significantly increases the accuracy compared to the existing Multivariate Bernoulli $Na{\ddot{i}}ve$ Bayes(BNB) algorithm and MNB scheme.

• Journal of Information Technology Applications and Management
• /
• v.15 no.4
• /
• pp.221-245
• /
• 2008

Recently, mobile internet technologies are enabling the possibility of radically new computing services which can share information and communicate with others on the move. In this situation, prior studies have attempted to identify of what factors make people use mobile internet. However, prior researches focused on investigating the factors affecting users' adoption to Mobile Internet. In order to offer beneficial materials to mobile internet companies, we investigated important factors to increase mobile users' value from the viewpoints of customer. In particular, this study was progressed how characteristics of mobile contents affect users' intrinsic attributes and how perceived users' network effects affect users' value in the mobile computing environments. To empirically test proposed hypotheses, we have analyzed 285 survey data gathering from mobile internet users and verified hypotheses by using SEM (structural equation modeling). Based on the results of this study, we found that content accessibility and content quality have significant impacts on users' intrinsic attributes such as perceived usefulness and perceived enjoyment. In addition, this study also revealed that perceived usefulness and perceived enjoyment were positively related to users' emotional value. Moreover, this study found that perceived users' network effects could affect users' monetary value by mediating expected benefits. Based on our findings, we can understand that this perspective can provide a deeper understanding of the mobile users' value adoption by bridging the gap between mobile internet studies and actual practice.

• Journal of Information Technology Services
• /
• v.5 no.2
• /
• pp.59-78
• /
• 2006

This research is to suggest the factor which is effecting on the information system audit fidelity in the perspective of audit procurer, to develop the measure to evaluate it, to investigate the audit performance and project performance for comparison the audit fidelity between the audit teams. As the analysis results, we found that the audit service factors can be divided to the expert knowledge of auditor and the project attributes itself. It means these factors are the major measures for the audit fidelity. In this research, the hypothesis of this study model is verified throughout the factor and corelation analysis, and the structured equation model is applied. Analysis results show that all relations between the factors are significant statistically. The audit service factors has an effect on audit fidelity. Also the information system audit fidelity can be affect on the project performance, audit performance and customer satisfaction. So, in conclusion, we need to judge closely the audit service factors affecting the audit fidelity for the enhancement of the project performance, audit performance and customer satisfaction.

• Journal of Information Technology Services
• /
• v.17 no.2
• /
• pp.101-110
• /
• 2018

Analytic Hierarchy Process (AHP) is a systematic and objective decision method that stratifies multiple criteria to determine various evaluation factors' order of priority. Since AHP requires several stages of analysis with complicated attributes, they normally rely on computer programs for the execution of such analyses. However, the existing AHP analytic tools carry the inconvenience of having to repeatedly input massive amounts data generated in every stage. This repetitious data entry process results in prolonged analysis times and higher possibility of errors, leading to decreased reliability of the results. Thus, in this study, we develop an analytic tool that effectively simplifies the data entry process in AHP analysis, for the purpose of reducing analysis times and increasing the reliability of the results.

• Journal of Information Technology Services
• /
• v.1 no.1
• /
• pp.45-55
• /
• 2002

This paper suggests a new approach to IT project management based on a regular project meeting results to consider the recent project environment. The greater part of recent IT projects are related to e-business transformation. Transforming to e-business is a new problem very different from those they have been worked, in several point of views. Under e-business era, therefore any IT project is being implemented in more complex, dynamic and uncertain environment than traditional. That is, project leaders must consider more factors to control projects including resources, quality, risks, and technologies, and human resources. The project organizations and software corporations thus need to develop and establish new concepts or methodologies to manage e-business projects. In this point of view, an entropy model in this study is introduced for estimating and managing the uncertainty in project control using multi-attributes of project meeting. This paper proposes a new frame work based on entropy model using project meeting results to consider eIT project environment with a small pilot study.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.163-178
• /
• 2005

The ultimate objective of Personal Information Management (PIM) is to collect, handle and manage wanted information in a systematic way that enables individuals to search the information more easily and effectively, However, existing personal information management systems are usually based on a traditional hierarchical directory model for storing information, limiting effective organization and retrieval of information as well as providing less support in search by associative interrelationship between objects (documents) and their attributes, To improve these problems, in this paper we propose a personal information management model based on the concept lattice of Formal Concept Analysis (FCA) to easily build and maintain individuals' own information on the Web, The proposed system can overcome the limitations of the traditional hierarchy approach as well as supporting search of other useful information by the inter-relationships between objects and their attributes in the concept lattice of FCA beyond a narrow search.

• Journal of Korea Spatial Information System Society
• /
• v.11 no.2
• /
• pp.54-62
• /
• 2009

This paper proposes a framework for personal location based services with personal life content, for example diaries, schedules and to-do lists. A lot of Internet users are recording their personal experiences and knowledge as text and other digital media on the network. Our proposed tool provides users with an environment to store personal records with related place attributes, and to retrieve these personal records at the right place. There are two applications on this tool, a place-enhanced blog and a LBS client on a mobile phone. The place enhanced blog provides users with blog interfaces for inputting place information. The place rem inder is a browser for spatial data on the place enhanced blog. Users can generate place information by writing personal records on their blog. Furthermore, using the LBS client, other users can retrieve personal records at the appropriate spots.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.69-86
• /
• 2021

As artificial intelligence technology advances, personalized recommendation systems using big data have attracted huge attention. In the case of beauty products, product preferences are clearly divided depending on customers' skin types and sensitivity along with individual tastes, so it is necessary to provide customized recommendation services based on accumulated customer data. Therefore, by employing deep learning methods, this study proposes a neural network-based recommendation model utilizing both product search history and context information such as gender, skin types and skin worries of customers. The results show that our model with context information outperforms collaborative filtering-based recommender system models using customer search history.

• Korean Journal of Social Welfare
• /
• v.42
• /
• pp.139-168
• /
• 2000

As the institutions of the Day Care services in Korea have merely focused on developing the issues for caring and education of children, however, other principles in the Day Care services have not been properly delivered. So, it is necessary for the institutions delivering Day Care services to approach inclusively above four perspectives to the broad sense of the child welfare because the institutions for Day care services are dealing with the groups of the parents, who are in difficulty to take care of their children, and the needs of the parents in terms of caring for their children. The study focuses to research the groups of children, which have various and mixed needs and the problems. On the other hand, the socio-economic attributes, the needs and the problems of the groups of the parents are looked for in the research. As the result of the research, the needs for Day Care services are differentiated from the different socio-economic backgrounds of the parents group. The data indicates that the low class families demands more needs than those of the middle class in the research of the categories. Analyzing from the result, the categories of caring, health care, nutritional supplements, extracurricular activities, emotional supports, providing information and referrals and community social services are hard to be defined as the necessary services based on the ages of the children. It is better to be defined as the necessary services demanding from the social needs of the parent group. Thus, the target groups such as the working couple and the low income families should be primarily considered as the beneficiary groups receiving the comprehensive day care services.

• The Journal of Industrial Distribution & Business
• /
• v.11 no.1
• /
• pp.49-57
• /
• 2020

Purpose : The purpose of this study is to examine the effect of the attributes of mobile shopping apps on the purchase intention of fashion products in the steadily growing mobile commerce market and analyze the mediation effect of shopping flow. Research design, data and methodology : In this study, a survey was conducted on users in their 20s to 50s who had experience of fashion products via mobile shopping apps. The questionnaire was analyzed on the final 507. The research issues were verified using Frequency analysis, Exploratory factor analysis, Reliability analysis, Confirmatory factor analysis, and Structural equation model. Results : Among the attributes of mobile shopping apps, reliability, enjoyment and ease of use were found to have a significant impact on shopping flow and fashion product purchase intention, while shopping flow had a significant impact on fashion product purchase intention. Product diversity and usefulness of shopping apps didn't show a significant effect. After examining the mediation effect, reliability, enjoyment, and ease of use were shown to have indirect effects by showing partial mediation effects. Conclusions : Studies show that consumers are not putting much emphasis on how diverse a product line is available and how useful a mobile shopping app is when they shop for fashion products on mobile devices. Factors that affect consumers' purchase intention are reliability, enjoyment and ease of use of shopping apps. These results shows that it is important to provide reliable information about fashion products, provide reliability to customers by setting up means for safe transactions, and provide a wider variety of services and information to make using the mobile shopping app enjoyable. In addition, there is a need to make it easy to find a fashion product that consumers like and make it easy to purchase when consumers find out fashion products that they like, and to configure how to use the app easily. Consequently, consumers become immersed in shopping which is also able to improve consumers' purchase intention on fashion products when a reliable, enjoyable and easy to use mobile shopping app is provided.