Data Science Meets Fragrance: Analyzing User Reviews to Decode Emotional Connections to Perfume Notes

This paper explores the emotional connections associated with perfumes by analyzing user reviews and fragrance notes for each product.Using a public dataset sourced from the Fragnatica platform, the study applies sentiment analysis techniques to categorize perfumes into six essential emotional groups: Romantic, Energizing, Melancholic, Aggressive, Relaxing, and Neutral.Sentiment analysis models, like VADER, are employed for basic sentiment scoring, while more advanced models including fine-tuned DistilBERT are incorporated to detect nuanced emotions.The emotional tones extracted from user-generated text correlate with consumer ratings and perfume characteristics.The study also investigates the relationship between fragrance notes and user emotions, identifying specific scent profiles that strongly relate to each group.Methodologies applied include sentiment analysis, clustering, and statistical visualization, utilizing a substantial dataset of perfume reviews.These strategies uncover patterns in emotional responses to scent, providing insights into how fragrance compositions influence emotional perceptions.The results bridge the gap between subjective fragrance experiences and objective data analytics, enabling more refined product categorization.Ultimately, this study offers valuable implications for the fragrance industry, helping brands improve product development and marketing strategies by better understanding the emotional resonance, leading to enhanced customer satisfaction and targeted product offerings.