Navigating the Turbulence: A Bibliometric Study on the Frontiers of Stock Market Volatility Research

Bibliometric and scientometric reviews may provide a useful insight into the evolving trends and this study is a comprehensive bibliometric and scientometric review of the stock market volatility (SMV) literature, encompassing, 1,945 documents published in 2015-2025. The analysis is a combination of Exploratory Data Analysis (EDA), Citation, Collaboration, topic modelling and similarity network Analysis based on the implementation of the latest AI tools, including Embedding Vectors, Topic Modeling, and the most popular pyBibX. Unlike the traditional bibliometric research, we apply machine learning models, i.e., Sentence-BERT and BerTopic to disclose more information about thematic changes, research trends, and methodological progress in SMV. We follow the chronicles of meaningful issues such as the GARCH model, financial crises, investor sentiment, and the effects of cryptocurrencies, as well as note the growing influence of AI in volatility prediction. The results indicate that the research topic has shifted considerably to the analysis of macroeconomic indicators, sentiment analysis, and the development of digital assets. The geographical location of research has also been unveiled in our study where the United States, the United Kingdom, China and India have a significant contribution.