Geosocial Media's Perspective on Energy: A Text Classification Approach using Natural Language Processing

This repository contains the restricted access Tweet datasets used in the study "Geosocial Media’s Perspective on Energy: A Text Classification Approach using Natural Language Processing". The aim of the study was to examine public opinion on fossil fuels, nuclear energy, and renewable sources (solar and wind) using Twitter data and natural language processing techniques. The following materials are included: Raw Tweet datasets ("Twitter_API_datasets.zip"): Three separate CSV files containing English-language tweets related to fossil energy, nuclear energy, and solar & wind energy, collected using the Twitter Academic Research API v2. Each dataset spans a different time range depending on data availability. Note:These restricted-access Tweet datasets are required to fully execute the analysis provided in the public Zenodo repository, which contains the code, labeled datasets, interactive maps, and supplementary materials used in the study. Users may request access to these raw Twitter datasets here to replicate and validate the study’s findings.