/cjobs

CJOBS

Primary LanguageJupyter Notebook

Skill Discrepancies Between Research, Education, and Jobs Reveal the Critical Need to Supply Soft Skills for the Data Economy

This repository provides code and data access for the paper "Skill Discrepancies Between Research, Education, and Jobs Reveal the Critical Need to Supply Soft Skills for the Data Economy":

For extracting skills from jobs, courses, and publication data, you will need the following:

  1. TextPreprocess: removing stopwords and punctuation.
  2. Dicts: Lexical resources used in skill extraction algorithms.
  3. Five different algorithms implementation for skill extraction: ExactMatching, MaxMatching, NgramMatching, StandfordLLDA, and StandfordNER.
  4. Measurement: performance evaluation of skill extraction algorithms: precision, recall and F1.
  5. Data: Skill types.
  6. UserStudy: Study instrument.

Contact Xiaozhong Liu liu237@indiana.edu, Olga B. Scrivner obscrivn@indiana.edu, or Shutian Ma mashutian0608@hotmail.com if there are questions or concerns.

For running Granger causality, Hawkes, Poincaré, and Kullback-Leibler Divergence, you will need code from the Code directory. Short descriptions are given in the README file.

Contact James Evans jevans@uchicago.edu or Lingfei Wu wlf850927@gmail.com if there are questions or concerns.