Privacy concerns in social media UGC communities: Understanding user behavior sentiments in complex networks

Abstract In a digital ecosystem where large amounts of data related to user actions are generated every day, important concerns have emerged about the collection, management, and analysis these and, according, privacy. recent years, users been accustomed organizing in relying on communities support achieve their goals. this context, present study aims identify main privacy social media, how affect users’ online behavior. order better understand networks, concerns, connection behavior, we developed an innovative original methodology that combines elements machine learning as technical contribution. First, complex network visualization algorithm known ForceAtlas2 was used through open-source software Gephi visually nodes form belonging sample UGC collected from Twitter. Then, sentiment applied with Textblob, works which experiments were vector classifier (SVC), multinomial naïve Bayes (MNB), logistic regression (LR), random forest, (RFC) under theoretical frameworks computer-aided text (CATA) natural language processing (NLP). As result, total 11 identified: positive protection cybersecurity eCommerce, negative settings, personal information engineering, neutral hacking, false information, impersonation cookies data. The paper concludes discussion results relation behavior environments outline valuable practical insights into some techniques challenges