This study provides a comprehensive review of two decades of research in opinion mining and sentiment analysis, addressing the fragmentation of prior work across methodologies, application domains, and data sources. The evolution of the field is traced from pre-1990 rule-based systems to lexicon heuristics, statistical learning, machine learning, deep learning, and the current wave of transformer-driven, multimodal, and generative models. Applications are examined across marketing, finance, politics, and social media, with emphasis on how methodological innovations have improved accuracy and enabled broader adoption. Best practices – including transformer fine-tuning, prompt engineering, zero-shot and few-shot learning, multimodal fusion, and domain adaptation – are analyzed to distill evidence-based guidelines for researchers and practitioners. The synthesis shows how sentiment analysis has shaped critical areas, including brand management, investor decision-making, political discourse, and online user engagement. Findings highlight the effectiveness of transformer-based approaches, particularly when combined with domain adaptation and prompt engineering, in delivering state-of-the-art performance. Beyond methodological and applied insights, the study identifies promising directions for future research, including real-time customer journey analytics, explainability in generative AI, robustness across multiple languages, ethical implications, and sustainability considerations. By consolidating dispersed knowledge into a unified account, this review provides both historical grounding and a structured roadmap that advances theoretical understanding and informs managerial practice.
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号