Skill Requirements Analysis for Data Analysts Based on Named Entities Recognition

Currently, with the surge in demand for data analysts, it is beneficial to grasp the social requirement for talents by deeply mining the job requirements of data science. This study used crawlers to acquire the job advertisements from 51job.com and selected data science related positions. Then, the specialty and skill entities in job requirement were annotated manually, and two kinds of Named Entities Recognition models, the Bert-BiLSTM-CRF model and BiLSTM-CRF were applied to extract skill entities and specialty entities from the text data of job requirement. It was found that, the model based on Bert pre-training vector was better. At last, the characteristics of the demand from the perspective of skills and profession were analyzed.