• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권11호
• /
• pp.5344-5356
• /
• 2018

Nowadays with the help of Location-Based Social Networks (LBSNs), users of Point-of-Interest (POI) recommendation service in LBSNs are able to publish their geo-tagged information and physical locations in the form of sign-ups and share their experiences with friends on POI, which can help users to explore new areas and discover new points-of-interest, and promote advertisers to push mobile ads to target users. POI recommendation service in LBSNs is attracting more and more attention from all over the world. Due to the sparsity of users' activity history data set and the aggregation characteristics of sign-in area, conventional recommendation algorithms usually suffer from low accuracy. To address this problem, this paper proposes a new recommendation algorithm based on a novel Preference-Content-Region Model (PCRM). In this new algorithm, three kinds of information, that is, user's preferences, content of the Point-of-Interest and region of the user's activity are considered, helping users obtain ideal recommendation service everywhere. We demonstrate that our algorithm is more effective than existing algorithms through extensive experiments based on an open Eventbrite data set.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1570-1594
• /
• 2017

Social network services have recently changed from environments for simply building connections among users to open platforms for generating and sharing various forms of information. Existing user reputation computation methods are inadequate for determining the trust in users on social media where explicit ratings are rare, because they determine the trust in users based on user profile, explicit relations, and explicit ratings. To solve this limitation of previous research, we propose a user reputation computation method suitable for the social media environment by incorporating implicit as well as explicit ratings. Reliable user reputation is estimated by identifying malicious information raters, modifying explicit ratings, and applying them to user reputation scores. The proposed method incorporates implicit ratings into user reputation estimation by differentiating positive and negative implicit ratings. Moreover, the method generates user reputation scores for individual categories to determine a given user's expertise, and incorporates the number of users who participated in rating to determine a given user's influence. This allows reputation scores to be generated also for users who have received no explicit ratings, and, thereby, is more suitable for social media. In addition, based on the user reputation scores, malicious information providers can be identified.

• International journal of advanced smart convergence
• /
• 제2권2호
• /
• pp.23-26
• /
• 2013

Social networking services that connect a person to other people are attracting people's attention and various types of services are provided on the Internet. Library has been playing a role of social media by providing us with materials such as books and magazines, and with a place for reading, studying, getting lectures, etc. In this paper, we present a method for finding candidates of groups of the library's patrons who share interest areas by utilizing the loan records, which are obtainable in every library. Such a homogeneous group can become a candidate for a study group, a community for exchange ideas, and other activity group. We apply the method to a collection of loan records of a university library, find some problems to be solved, and propose measures for more detailed solutions. Even though the potential group finding problem still remains a lot of issues to be solved, its potential importance is very high and thus to be studies even more for future applications.

• International Journal of Internet, Broadcasting and Communication
• /
• 제6권1호
• /
• pp.5-8
• /
• 2014

Social networking services that connect a person to other people are attracting our attention and various types of on-the-network services are provided. Library has been playing a role of social media by providing with materials such as books and magazines, and with a place for reading, studying, getting lectures, etc. In this paper, we present a method for finding candidates of groups of the library's patrons who share interest areas by utilizing the loan records, which are obtainable by every library. Such a homogeneous group can become a candidate for a study group, a community for exchange ideas, and other activity group. We apply the method to a collection of loan records of a university library, find some problem to be solved, and propose measures for more detailed solutions. Even though the potential group finding problem still remains a lot of problems to be solved, its potential importance is very high and thus to be studies even more for future applications.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권12호
• /
• pp.3197-3218
• /
• 2012

Compared with traditional itinerary planning, intention-oriented itinerary recommendations can provide more flexible activity planning without requiring the user's predetermined destinations and is especially helpful for those in unfamiliar environments. The rank and classification of points of interest (POI) from location-based social networks (LBSN) are used to indicate different user intentions. The mining of vehicles' physical trajectories can provide exact civil traffic information for path planning. This paper proposes a POI category-based itinerary recommendation framework combining physical trajectories with LBSN. Specifically, a Voronoi graph-based GPS trajectory analysis method is utilized to build traffic information networks, and an ant colony algorithm for multi-object optimization is implemented to locate the most appropriate itineraries. We conduct experiments on datasets from the Foursquare and GeoLife projects. A test of users' satisfaction with the recommended items is also performed. Our results show that the satisfaction level reaches an average of 80%.

• 복식
• /
• 제56권1호
• /
• pp.56-69
• /
• 2006

The purposes of this study were to identify cosmetics purchasing behavior according the 20-30 year old men's lifestyle. The results were as follows; 1. The factors of men's lifestyle were sense of fashion, participation of social activities, use of web-based information, sense of androgyny, economical efficiency, provision of web-base information, sport activities, and pursuit of change, and they were segmented into a passive stagnant group, a economic web-base information utilizing group, a positive social activity participation group, and a sensitive appearance change pursuit group. 2. Passive stagnant group used less information sources patronized cosmetics specialty store, did not select their cosmetics by themselves, and spent less for their cosmetics. Economic web-base information utilizing group used information sources positively, patronized cosmetics discount store or internet shopping, and spent less for cosmetics. Positive social activity participation group patronized cosmetics specialty store or discount store, but did not select cosmetics by themselves. Sensitive appearance change pursuit group patronized department store or internet shopping for cosmetics, selected cosmetics by themselves, and spent more. 3. Passive stagnant group showed a tendency of older, less educated, and lower incomes, but economic web-base information utilizing group were among the age of 20's, lower educated, and the unmarried with average incomes. Positive social activity participation group showed a tendency of older, highly educated, and the married with jobs, but sensitive appearance change pursuit group were among the age of 20's and university students with more incomes and pocket money.

• 한국콘텐츠학회논문지
• /
• 제21권3호
• /
• pp.68-79
• /
• 2021

소셜 사물 인터넷(SIoT)에서 차량들이 다양한 정보를 생성하고 이를 다른 차량과 공유하고 피드백을 주고 받는 소셜 행위가 이루어진다. 차량 간에 신뢰성 있는 정보를 공유하기 위해서는 차량의 신뢰성을 판별하는 것이 중요하다. 본 논문에서는 차량들 간에 신뢰성 있는 정보를 공유하기 위한 차량 신뢰도 계산 기법을 제안한다. 제안하는 기법은 차량 간 소셜 행위에 기반한 사용자 평판과 네트워크 신뢰도를 고려하여 차량 신뢰도를 판별한다. 차량은 점수 부여, 무시, 재배포 등의 행위를 선택할 수 있으며 이에 따라 사용자 평판이 계산된다. 네트워크 신뢰도를 계산하기 위해 다른 차량과의 거리와 패킷 전송률을 이용한다. 사용자 평판과 네트워크 신뢰도를 이용하여 지역 신뢰도가 계산된다. 이때, 전달되는 데이터의 중복 배포를 방지한다. RSU(Road Side Unit)의 데이터를 활용하여 지역적인 데이터의 한계를 극복하고 전역적인 데이터를 활용하여 보다 더 정확한 차량 신뢰도 계산이 가능하다. 다양한 성능평가를 통해 제안하는 기법이 기존 기법에 비해서 성능이 우수함을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1502-1520
• /
• 2021

This paper attempts to investigate Korean youth Not in Education, Employment and Training (NEET) and how daily activities and community participation may influence their positive emotions and job search desire. First, we conducted a focus group interview with 16 NEETs who participated in the Kakao NEET Company project. The project allowed participants to experience employment by founding a virtual company in which each participant selected a daily activity to perform as part of the company's operations. Second, the interview responses were categorized and assigned emotional values using the card sorting technique and multi-dimensional analysis (MDS). A total of 11 emotional values were derived through this process. Finally, a social network analysis was conducted in order to measure the density of relations among the emotional values. Results suggest that immersion, confidence, belongingness were the three highest values evaluated by participants. Furthermore, network diagrams imply that the stronger participants perceived social support and belongingness with others, the stronger their responsibility grew, further leading them to establish steady goals. In particular, the high eigenvector score for "desire for job" suggests that emotional values are sequentially connected to the immersion-social support-responsibility-goal-job desire. This sequence suggests that digital services that are developed with the aim to enhance social values such as the Kakao NEET Project may engender motivation and confidence in youth NEETs. The overall results suggest that a systematic approach to policymaking should be considered in order to provide fundamental solutions and expand opportunities for social participation and emotional comfort, as social isolation due to low self-esteem has been reported as one of the reasons for NEETs' failure in the labor market.

• 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.

• Asia pacific journal of information systems
• /
• 제30권1호
• /
• pp.53-71
• /
• 2020

The Internet and all of its possibilities and applications have changed individuals' lifestyles in relation to socializing, working, and how they spend their leisure time. Social networking sites (SNSs), such as Facebook or Instagram, are ideal settings for interacting with others but, unfortunately, they are also ideal settings for motivated offenders to commit cybercrimes. Thus SNS users may be more vulnerable to cybercrime. The purpose of this study is to investigate the occurrence of cybercrime victimization, specifically cyber-harassment, cyber-impersonation, and hacking. Self-report surveys collected from a sample of 147 respondents were examined using the moderated multiple regression analysis and a logistic regression analysis to determine possible relationships between SNS lifestyle exposure activities and cybercrime victimization. The results indicate moderate support for the application of lifestyle-routine activity theory (LRAT) to cybercrime victimization. Possible educational and managerial implications, as well as suggestions for future research, are discussed.