This research investigates how changes in public discourse on social media (particularly Twitter, now X) influence the financial performance of companies listed on the e-commerce XTCRT index of Borsa Istanbul amid the COVID-19 pandemic. Utilizing a unique 4-layer network structure integrating daily closing prices, highest and lowest values, and trading volume data with Twitter discussions on six categories (culture, economy, health, politics, technology, world affairs), and employing multilayer network analysis, LSTM architecture, and NARDL analysis, the study finds a high responsiveness of the e-commerce index to social media content, particularly discussions related to health, technology, and world affairs. Social media discussions significantly shape index composition, resulting in shifts in market dynamics.

Larissa M. Batrancea, Mehmet Ali Balcı, Ömer Akgüller, Anca Nichita