Authors: Neh Sharma
Abstract: Millions of users share experiences and opinions across social media platforms, review portals, and online health communities, forming a rich but complex digital footprint. These expressions often reflect overlapping emotions—trust, curiosity, hesitation, and belief—rather than clear-cut judgments. As a result, big-data sentiment analysis, supported by fuzzy and uncertainty-aware models, offers a more realistic way to interpret public attitudes than rigid positive–negative classification. Drawing on studies published between 2020 and 2025, the analysis integrates insights from multilingual transformer-based sentiment models, complementary and alternative medicine (CAM) perception research, and the expanding digital health ecosystem. The proposed workflow includes data collection, linguistic preprocessing, fuzzy aspect-level sentiment detection, geotagging, temporal comparison, and topic modelling, allowing sentiment to be represented as a continuum rather than a binary outcome. Across the reviewed studies, Indian users generally express strong and confident positive sentiment toward Ayurveda, shaped by cultural familiarity and routine use. In contrast, global users tend to display graded responses that combine interest with caution, particularly around scientific validation, safety, and standardisation. The paper concludes by outlining policy and communication implications for health and wellness stakeholders, and by identifying future research directions such as multimodal analytics, fuzzy-interpretable models, and real-time sentiment dashboards. Together, these approaches support a more culturally sensitive, evidence-aligned, and uncertainty-aware understanding of Ayurveda’s evolving global presence.
