联系我们

论文查询结果	返回搜索

论文编号：	8422
作者编号：	2120140194
上传时间：	2016/6/11 22:37:58
中文题目：	移动互联网个性化推荐服务接受的影响因素研究
英文题目：	Research on Influence Factors of Mobile Internet Personalized Recommendation System Acceptance
指导老师：	李凯
中文关键字：	移动互联网、个性化推荐服务、技术接受与使用统一理论、感知风险、个体创新性
英文关键字：	Mobile Internet, personalized recommendation service, perceived risk, individual innovation, Unified Theory of Acceptance and Use of Technology
中文摘要：	随着信息技术的高速发展，互联网深入千家万户，电子商务、网站运营、网上交易等各式各样的网络服务成为了人们生活中不能缺少的重要组成部分。然而，随着信息在互联网不断汇集形成海量的信息库，在满足人们对于信息的需求的同时，也出现了信息过载问题。个性化服务通过数据分析与数据挖掘技术，在海量的消费数据中发现有价值的信息与规律，以此来预测消费者的行为和偏好，从而为消费者提供更加符合他们需求的服务。 个性化服务已经成为了移动互联网发展的潮流，但是，个性化服务的进一步发展还面临一些问题。首先，个性化服务还不够个性化。个性化服务需要根据用户的历史数据与位置信息判断用户的需求，没有实现根据用户身处情境的不同而改变；个性化服务往往是根据主流群体行为分析得到的规律来提供服务，没有考虑少数群体的需求。这些都有可能导致个性化服务提供的服务不完全符合用户需求。第二，由于个性化服务需要提供用户的历史浏览信息、个人信息等，有可能导致个人隐私的泄露等一系列后果，消费由于对于个性化服务的风险感知不愿意接受个性化服务。 针对这一问题，需要对用户的个性化推荐服务接受影响因素进行研究。本文基于技术接受与使用统一模型（UTAUT），结合技术接受模型（TAM），增加影响变量感知风险与个体创新性两个变量，建立了移动个性化推荐服务接受模型。在建立模型的基础上，本文通过发放调查问卷，使用结构方程模型的方法对模型进行了验证。揭示了各影响因素对于消费者使用行为的直接与间接影响。努力期望正面影响绩效期望；绩效期望、社群影响、个体创新性正面影响使用意图；感知风险负面影响使用意图；促成因素与使用意图正向影响使用行为。 本文分为六个部分。第一部分说明本文的研究背景、研究内容与研究思路；第二部分针对相关文献与理论进行回顾；第三部分构建移动个性化推荐服务接受模型，提出研究假设；第四部分进行问卷设计与发放；第五部分进行数据分析；最后，总结与展望，在前几部分的基础上，得到了移动个性化推荐服务使用行为的影响因素，并提出了相关建议。
英文摘要：	With the rapid development of information technology, the Internet has become an indispensable part of people's lives, such as electronic commerce, website operation, online trading, and so on. The use of the Internet brings great convenience for life. People at home can obtain the latest information and buy cheap products. However, the huge amount of information database not only meets the needs of people for information, but also brings the information overload problem. In this case, the personalized recommendation system arises at the historic moment. Personalized service uses data analysis and data mining technology in the mass consumption data to find valuable information and behavior rules, so as to predict the behavior and preferences of consumers and to provide consumers with more personalized services. Personalized service has become the trend of the development of mobile Internet, however, the further development of personalized service is still facing some problems. First of all, personalized service is not personalized enough. Personalized service needs the user's historical data and location information to determine the user's needs, but it can’t change according to the situations; personalized service often uses the analysis of the mainstream group behavior rules to provide services without considering the needs of minority groups. Personalized services can’t meet the needs of users fully. Second, the need of user's browsing history information may lead to personal privacy leaks and other consequences. Due to these reasons, the degree of acceptance of personalized recommendation services is limited. In view of this problem, it is necessary to study the influence factors of the user's personalized recommendation service. We established a mobile personalized recommendation service acceptance model based on the unified UTAUT model of acceptance and use of technology, combining the technology of acceptance model (TAM), and increasing the variables of perceived risk and individual innovation. The model is verified by the method of structural equation model. It reveals the direct and indirect effects of various influencing factors on consumer behavior. Effort expectation has a positive impact on performance expectations; performance expectations, social influence, the individual creativity have a positive impact on intention to use; perceived risk negatively influence intention to use; contributing factors and intention to use have a positive influence on use behavior. This paper is divided into six parts. The first part explains the research background, research content and research ideas; in the second part, the theory and related literatures were reviewed; in the third part, construct mobile personalized recommendation services acceptance model and propose research hypotheses; in the fourth part, questionnaire design and scale; in the fifth part, analyze the data; finally, summarize and outlook, conclude the using behavior and the influencing factors of personalized recommendation service, and put forward the relevant suggestions.
查看全文：	预览  下载(下载需要进行登录)