基于文本挖掘的互联网企业岗位对比研究  

Comparative Study of Internet Enterprise Jobs Based on Text Mining

作　　者：袁莉[1] YUAN Li(Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京邮电大学,北京100876

出　　处：《现代信息科技》2022年第7期112-115,119,共5页Modern Information Technology

摘　　要：2022年,高校毕业生人数首次突破1 000万人,求职人数呈逐年递增的趋势,另一方面,疫情当下就业市场需求缩紧,互联网企业掀起裁员浪潮。文章通过网络爬虫获取近17 000条互联网企业招聘数据,运用K-means进行文本聚类,分别得出职位描述、职位要求等六个维度的数据,对比分析互联网企业的人才需求特点,解答入局互联网适宜选择什么岗位、不同岗位对求职者的要求有何区别、校招要求和社招要求有哪些不同这三个重要问题,为求职者高质量就业提供决策指导。In 2022,the number of college graduates will exceed 10 million for the first time,and the number of job seekers shows an increasing trend year by year.On the other hand,demand in the job market is tightening at the moment of the epidemic,and the Internet enterprises set off a wave of layoffs.This paper uses web crawlers to obtain nearly 17 000 recruitment data of Internet enterprises,uses K-means to cluster text,obtains six dimensions of data such as job description and job requirements,compares and analyzes the characteristics of talent demand of Internet enterprises,and answers three important questions:what jobs are suitable for entering the Internet,what are the requirements of different jobs for job seekers,and what are the differences between school recruitment requirements and social recruitment requirements,which provides decision-making basis for high-quality employment of job seekers.

关 键 词：文本挖掘 K-MEANS聚类 职位要求 高质量就业 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]