Integrating sentiment analysis with graph neural networks for enhanced stock prediction: A comprehensive survey

There has been significant interest in integrating sentiment analysis with graph neural networks (GNNs) for stock prediction tasks. This article thoroughly reviews the application of GNNs in conjunction with sentiment analysis for stock prediction. This study introduces the fundamental concepts of GNNs and sentiment analysis, emphasizing their respective contributions to the stock prediction domain and underlining the limitations of conventional methods. The potential advantages of combining GNNs and sentiment analysis in this context are highlighted. A comprehensive review of the literature on this subject is subsequently undertaken, covering diverse approaches and techniques utilized for sentiment analysis and stock prediction through the application of GNNs. Various graph structures, such as stock and investor networks, are used to represent financial data, and methodologies employed to incorporate sentiment analysis within these networks are explored. Challenges related to data collection, preprocessing, and annotation are discussed, along with the sources of sentiment data, including news articles, social media feeds, and financial reports. Evaluation metrics and performance benchmarks utilized to assess the precision and efficacy of GNN-based stock prediction models are also examined. This article highlights the limitations and unanswered research questions in this field, paving the way for future investigations. This article provides a comprehensive roadmap for utilizing GNNs with sentiment analysis to enhance stock prediction accuracy. It is a valuable resource for researchers and practitioners interested in exploring and advancing this emerging interdisciplinary domain.