Supervising Sentiment Models: Market Signals or Human Expertise?

Nazanin Babolmorad and Nadia Massoud

Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge

Abstract: We build a framework to examine how the training regime-rather than model architecture-drives the performance of financial sentiment models. Using firm-level news and parsimonious classifiers, we compare three supervision regimes: human-only, hybrid, and market-only (fully automated). The framework opens the "black box" of sentiment modeling by tracing how supervision shapes each component of the classifier. Across extensive tests, the hybrid regime consistently outperforms fully automated training in explaining variation in stock returns and trading volume, enhancing interpretability and economic relevance. Human input improves sentiment inference, offering new insights into information processing and price formation in financial markets.

Keywords: Sentiment Analysis; Financial Media News; Investor Sentiment; Stock Markets; Human versus Machine (search for similar items in EconPapers)
JEL-codes: G02 G11 G12 G14 (search for similar items in EconPapers)
Date: 2025-10-31
New Economics Papers: this item is included in nep-mst
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.econ.cam.ac.uk/sites/default/files/pub ... pe-pdfs/cwpe2577.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cam:camdae:2577

Access Statistics for this paper

More papers in Cambridge Working Papers in Economics from Faculty of Economics, University of Cambridge
Bibliographic data for series maintained by Jake Dyer ().