Scientific Trends in Big Data Analytics for Sentiment Insight: A Bibliometric Study in Digital Marketing

This study investigates the intellectual structure and thematic evolution of Big Data research in digital marketing, with a particular focus on the role of sentiment analysis as an emerging analytical domain. Addressing the question of how scholarly production, methodological trends, and global contributions have shaped the field over the past decade, the study hypothesizes that the rapid advancement of computational techniques especially deep learning–based sentiment analysis has significantly influenced digital marketing scholarship. Using a bibliometric design, data were extracted from the Scopus database for the 2015–2025 period, yielding a final sample of 1,076 documents after applying language, subject-area, and publication-type filters. Performance analysis and science-mapping techniques were conducted using R, Bibliometrix, and Biblioshiny to examine publication growth, citation influence, authorship patterns, and thematic clusters. The results indicate sustained annual growth of 8.48%, dominated by contributions from China, India, and the United States. Two major thematic clusters were identified: (1) marketing and business strategy applications, and (2) enabling technologies such as AI, IoT, machine learning, and sentiment analysis techniques. The findings demonstrate that sentiment analysis plays an increasingly central role in extracting consumer insights from large-scale digital interactions, thereby strengthening data-driven marketing decisions. This study contributes to the literature by highlighting the methodological evolution, global dynamics, and strategic significance of sentiment analysis within Big Data–driven digital marketing research, offering a foundation for future investigations into predictive analytics, consumer behavior modeling, and real-time marketing intelligence.