Diving into recession: the collective knowledge of online users as an early warning system for recessionary expectations
Document Type
Article
Source of Publication
Information and Management
Publication Date
1-1-2026
Abstract
As concerns about economic downturns manifest in online discussions, we investigate whether sentiment extracted from social media can serve as an early warning signal for recessionary pressures. Using a dataset of Twitter (X) posts related to economic prospects, we apply a range of sentiment analysis techniques, including a lexicon and rule-based method (VADER) and deep learning approaches (GPT and BERT). We assess the relationship between online sentiment and key recession indicators, such as the yield curve and GDPNow forecasts, using a combination of econometric and machine learning methods. In addition, we perform a comparative evaluation of sentiment classification techniques, incorporating both traditional models and deep learning architectures. Our results confirm that Twitter discussions precede changes in recessionary indicators and can thus provide forward-looking insights into economic sentiment. Furthermore, the comparative analysis reveals variations in sentiment detection across different methodologies, emphasizing the importance of selecting appropriate approaches in economic forecasting.
DOI Link
ISSN
Publisher
Elsevier BV
Volume
63
Issue
1
Disciplines
Business | Computer Sciences
Keywords
Machine learning, Natural language processing, Recession, Sentiment analysis, Social media, Yield curve
Scopus ID
Recommended Citation
Hayawi, Kadhim; Shahriar, Sakib; Mathew, Sujith Samuel; Polyzos, Efstathios; and Ganguli, Kaustuv Kanti, "Diving into recession: the collective knowledge of online users as an early warning system for recessionary expectations" (2026). All Works. 7497.
https://zuscholars.zu.ac.ae/works/7497
Indexed in Scopus
yes
Open Access
no