杭州市基层小区保安职业认同影响因素研究——基于集成学习算法视角
A Study on the Factors Influencing Occupational Identity of Grassroots Community Security Guards in Hangzhou—A Perspective Based on Ensemble Learning Algorithms
摘要: 在职业污名化背景下,杭州市基层小区保安常面临职业认同困境,明确其职业认同的核心影响因素是制定有效干预策略的关键。研究基于社会身份认同理论与压力转换理论,以杭州市430名基层小区保安为研究对象,采用随机森林、AdaBoost及XGBoost三种集成学习算法,系统分析基本信息、工作感知、应对策略及支持资源对职业认同的影响,并通过特征重要性排序明确各因素的作用优先级。结果表明:工作感知和应对策略是影响职业认同的核心因素,重要性排名前两位;其次为从业时间和月工资,二者通过职业经验积累与经济安全感间接影响认同水平;支持资源的影响相对较弱,而性别、婚姻状况等基本信息对职业认同的作用不显著。研究通过多算法交叉验证,明确了基层小区保安职业认同的关键影响因素,为针对性提升其职业认同提供了靶向依据。
Abstract: Against the backdrop of occupational stigmatization, grassroots community security guards in Hangzhou often face dilemmas regarding their occupational identity. Identifying the core factors influencing their occupational identity is essential for developing effective intervention strategies. Drawing on Social Identity Theory and Stress Process Theory, this study investigates 430 grassroots community security guards in Hangzhou. Utilizing three ensemble learning algorithms—Random Forest, AdaBoost, and XGBoost—the study systematically analyzes the impacts of demographic characteristics, work perception, coping strategies, and support resources on occupational identity, and determines the priority of these factors through feature importance ranking. The results indicate that work perception and coping strategies are the two most critical factors influencing occupational identity. Length of employment and monthly income rank next in importance, exerting indirect effects on identity levels through the accumulation of professional experience and the sense of economic security. In contrast, support resources show relatively weaker effects, while basic demographic variables such as gender and marital status have no significant impact on occupational identity. Through cross-validation across multiple algorithms, this study identifies the key determinants of occupational identity among grassroots community security guards, providing an empirical basis for developing targeted strategies to enhance their professional identification.
参考文献
|
[1]
|
Breiman, L. (2001) Random Forests. Machine Learning, 45, 5-32. [Google Scholar] [CrossRef]
|
|
[2]
|
Freund, Y. and Schapire, R.E. (1997) A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55, 119-139. [Google Scholar] [CrossRef]
|
|
[3]
|
Chen, T. and Guestrin, C. (2016) XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 13-17 August 2016, 785-794. [Google Scholar] [CrossRef]
|
|
[4]
|
朱永跃, 覃正虹, 欧阳晨慧. 产业工人心理所有权对工作投入的影响——职业认同与员工导向组织文化的作用[J]. 技术经济, 2020, 39(8): 143-151.
|
|
[5]
|
徐光毅. 非体面工作从业者矛盾职业认同研究: 形成机制、影响后效及干预策略[D]: [博士学位论文]. 广州: 华南理工大学, 2022.
|
|
[6]
|
Liou, D., Tu, C. and Chang, S. (2012) Mediating Effect between Supportive Culture and Job Satisfaction in Administrative Services at Higher Education Institutions. Human Factors and Ergonomics in Manufacturing & Service Industries, 24, 627-640. [Google Scholar] [CrossRef]
|
|
[7]
|
Zimet, G.D., Dahlem, N.W., Zimet, S.G. and Farley, G.K. (1988) The Multidimensional Scale of Perceived Social Support. Journal of Personality Assessment, 52, 30-41. [Google Scholar] [CrossRef]
|
|
[8]
|
周晔, 黄旭, 欧阳侃. 主动抑或回避: 职业污名、自我评价和任务绩效[J]. 外国经济与管理, 2020, 42(8): 50-67.
|