Empowering Sentiment Analysis with Deep Learning Model: Evaluating Social Media's Benefits and Drawbacks

Online social networks (OSNs) have revolutionized communication by facilitating unprecedented information sharing and global connections. Despite these benefits, OSNs also present significant challenges, including the spread of misinformation, increased distraction, and adverse mental health effects. This study examines a dataset of 3,904 user reviews collected from online sources and personal networks, revealing a polarized sentiment distribution with 56% positive, 43.1% negative and 0.9% neutral views on the impact of social platforms. To capture the nuanced sentiments expressed, Long Short-Term Memory (LSTM) enhanced with preprocessing techniques such as tokenization, lemmatization, and word embeddings with Word2Vec was employed. The LSTM model achieved an accuracy of 86.43% in sentiment classification, significantly outperforming traditional baseline methods. These findings provide valuable information for platform developers, policymakers, and researchers aiming to understand and mitigate the social and psychological effects of digital platforms. Future research will focus on expanding the dataset and addressing class imbalance to further refine and enhance sentiment analysis models.