|
移动社交媒体智能推荐环境下信息规避行为影响因素研究
|
Abstract:
随着移动社交媒体的普及,智能推荐系统在提升用户体验、优化信息中发挥着关键作用。然而,这一过程中涉及到的个人信息收集与处理,引发了用户对隐私安全与信息规避行为的担忧。本研究旨在探究移动社交媒体环境下信息规避行为的影响因素,结合定量的文本分析工具word2vec和定性的扎根理论分析方法,以知乎平台为案例,深入分析用户的信息规避行为及其背后的动因。通过对知乎平台上的文本数据应用word2vec模型分析,本研究识别出与信息规避行为相关的关键词及其语义相似词,进而利用扎根理论揭示了影响信息规避行为的深层次因素。结果表明,信息因素、隐私担心、隐私风险感知、移动社交环境各自对移动社交媒体智能推荐环境下信息规避行为产生直接影响。同时,信息因素对隐私风险感知产生直接影响。
With the proliferation of mobile social media, intelligent recommendation systems have become key in enhancing user experience and optimizing the presentation of information. However, the collection and processing of personal data involved in this process have sparked concerns over privacy security and the behavior of information avoidance among users. This study investigates the factors influencing information avoidance behavior within the mobile social media environment. By combining quantitative text analysis tools, such as word2vec, with qualitative grounded theory analysis methods, this research analyzes information avoidance behavior and its underlying motives on the Zhihu platform. Utilizing the word2vec model to analyze text data from the Zhihu platform, the study identifies keywords related to information avoidance behavior and their semantically similar words, subsequently revealing the deep-seated factors affecting information avoidance behavior through grounded theory. The findings indicate that information factors, privacy concerns, perceptions of privacy risk, and the mobile social environment directly impact information avoidance behavior in the context of mobile social media’s intelligent recommendation environments. Moreover, information factors directly influence the perception of privacy risk.
[1] | 杨瑞仙, 沈嘉宁, 许帆, 等. 社交媒体app隐私政策评价指标体系构建及实证研究[J]. 情报理论与实践, 2023, 46(1): 81-89. |
[2] | Kim, M.S. and Kim, S. (2018) Factors Influencing Willingness to Provide Personal Information for Personalized Recommendations. Computers in Human Behavior, 88, 143-152. https://doi.org/10.1016/j.chb.2018.06.031 |
[3] | Zhu, X. and Bao, Z. (2018) Why People Use Social Networking Sites Passively. Aslib Journal of Information Management, 70, 158-175. https://doi.org/10.1108/AJIM-12-2017-0270 |
[4] | 周涛, 刘佳怡, 邓胜利. 基于sor模型的在线知识社区用户潜水行为研究[J]. 情报杂志, 2022, 41(7): 160-165+183. |
[5] | 晏齐宏. 用户算法感知对反馈行为的影响机制研究——基于社会认知理论的分析[J]. 新闻与写作, 2022(7): 76-87. |
[6] | Aiolfi, S., Bellini, S. and Pellegrini, D. (2021) Data-Driven Digital Advertising: Benefits and Risks of Online Behavioral Advertising. International Journal of Retail & Distribution Management, 49, 1089-1110. https://doi.org/10.1108/IJRDM-10-2020-0410 |
[7] | 姜婷婷, 权明喆, 魏子瑶. 信息规避研究: 边界、脉络与动向[J]. 中国图书馆学报, 2020, 46(4): 99-114. |
[8] | Mikolov, T., Chen, K., Corrado, G., et al. (2013) Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:13013781. |
[9] | Jia, K. (2021) Chinese Sentiment Classification Based on Word2vec and Vector Arithmetic in Human-Robot Conversation. Computers and Electrical Engineering, 95, Article ID: 107423. https://doi.org/10.1016/j.compeleceng.2021.107423 |
[10] | Corbin, J. and Strauss, A. (1990) Grounded Theory Research Procedures, Canons, and Evaluative Criteria. Qualitative Sociology, 13, 3-21. https://doi.org/10.1007/BF00988593 |
[11] | Francis, J.J., Johnston, M., Robertson, C., et al. (2010) What Is an Adequate Sample Size? Operationalising Data Saturation for Theory-Based Interview Studies. Psychology & Health, 25, 1229-1245. https://doi.org/10.1080/08870440903194015 |