Sentiment analysis applications using deep learning advancements in social networks: A systematic review

Sentiment analysis is required to extract insights from social media content affecting decision-making and personalized services. The enormous volume of social network information has to be technically processed to extract relevant knowledge. Sentiment analysis is the most widely used method for this purpose. The current techniques of sentiment analysis have made significant progress in various fields. However, the potential of social networks to better understand human emotions and the recent advancements in deep learning necessitate the review and use of advanced sentiment analysis techniques that still require more attention from researchers in this field. In this regard, this review presents a systematic literature review (SLR) on the advancements of sentiment analysis using deep learning techniques in social networks from 2019 to May 2024. Furthermore, this review emphasizes that sentiment analysis can provide meaningful insights into information extracted from large and diverse datasets such as social media, which is extremely important for decision-making and personalized services. It also highlights mental health concerns as one of the windows into the emotional atmosphere of social networks. In addition, this SLR provides a technical taxonomy and comparison of various deep learning approaches. This SLR not only provides a comprehensive overview of the most advanced techniques and methodologies now used in sentiment analysis but also highlights forthcoming challenges and open issues that need to be addressed in the future. This study helps researchers and practitioners use deep learning to improve sentiment analysis applications and digital social well-being.