evelinesurbakti/Automated-Keywords-Extraction-of-Data-Analyst-Job-Descriptions-from-Indeed-using-NLP

Implements a complete web scraping and NLP pipeline using R's rvest library to extract job postings from Indeed, then applies bag-of-words and GloVe vectorization to identify skill requirements and keyword patterns in data analyst roles. The workflow combines frequency analysis and n-gram extraction (unigrams/bigrams) to surface context-aware terms like "data_analyst" and "data_quality" alongside exploratory visualizations including word clouds and experience distribution charts. Focuses specifically on Dublin-based positions to provide localized job market insights for candidates evaluating required experience levels and in-demand competencies.

No commits in the last 6 months.