Fuel Costs and the EV Conversation: Tracking Public Sentiment Through Social Media
Keywords:
knowledge management, electric vehicle, gas price, topic mining, Latent Dirichlet Allocation (LDA), sentiment analysis, Natural Language Processing (NLP), word cloud, VADER, NLTK, Python, machine learningAbstract
This study investigates the impact of gas prices on public sentiment toward electric vehicles (EVs) through Social Media data analysis. Using Natural Language Processing (NLP) techniques, we collected and pre-processed posts related to EVs, employing tools such as NLTK, VADER, and Python-based machine learning methods. Topic mining was conducted using Latent Dirichlet Allocation (LDA), and sentiment analysis and word cloud visualizations were applied to identify patterns in public online discourse. We hypothesized that rising gas prices would reduce barriers to EV adoption, resulting in more positive sentiment and increased EV-related discussion. Our findings support this hypothesis, while also revealing that positive sentiment correlates more strongly with gas prices during periods of decline than during increases.
