Skip to content

Analysis of Data Scientist Job Descriptions using Natural Language Processing

Notifications You must be signed in to change notification settings

asai2019/job-description-nlp

Repository files navigation

job-description-nlp

Analysis of Data Scientist Job Descriptions using Natural Language Processing


This repository contains R code to analyze data scientist job descriptions.

Objective Description
1 Classification of statements within job descriptions into responsibilities and qualifications sections using random forest classification, with visualization of feature importance. Dataset includes manually curated text consisting of statements pertaining to each section.
2 Vectorization of terms found in job summaries using the GloVe algorithm for examining semantic similarity. Additional dimensionality reduction performed using multidimensional scaling for visualization purposes. Dataset includes scraped data scientist job summary data from Indeed.