Performance Exploration of Mobile Communication Apps Recommendation Service System：A Group Sequence Decision Approach

• Main Authors: Fei-Yun Cheng, 鄭斐勻
• Other Authors: Wei-Feng Tung
• Format: Others
• Language: zh-TW
• Published: 2013
• Online Access: http://ndltd.ncl.edu.tw/handle/68231761742393451280

碩士 === 輔仁大學 === 國際經營管理碩士學位學程 === 101 === With the advancement of information technology and development of e-commerce, Internet has become a platform that can share service experiences and exchange of ideas about products on the virtual community. The concept of Web2.0 has disseminated in recent years, the shared knowledge also become more great quantity and abundant. In this case, we should make these shared information to create maximum benefits for users. In recent years, network service providers have offered various recommendation systems that provide appropriate recommended contents to users that can achieve the benefits of information search. Thus, the recommended contents can be used to facilitate users’ decision making. The core of the algorithm in recommendation service system in this study adopts a group ranking approach that can be mining maximum consensus sequences from all users’ partial ranking lists. In order for represent the recommended results we select the brand of communication apps. Brand decision is a common problem for the query users. The purpose of this study is to identify factors that influence the user’s intention to adopt the decision aid’s recommendation. In this study, the questionnaire’s data was collected after test the recommendation system. Multiple regression analysis was used to measure the theoretical model. The result shows that the performance of recommendation system has an impact on user to adopt the decision aid’s recommendation. Competence of recommendation system, shared information and relevant feedback all have a positive effect on recommendation system performance. Consequently, the analyzed results argue that the IS developers can focus on three characteristics of recommendation systems ensure the users satisfied with the recommendation system performance. The system can be verified that will promote users information adoption and intention.