Metraipolis › archive › dc_8f45a42fcfc3

Evaluating Financial Sentiment in the Age of AI — arXiv:2609.20198

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20198
License (as archived)
CC0-1.0
Archived
2026-10-10T04:08:55.716Z
SHA-256 of the archived text
11ae8c75984f7a867dbf04dd7212c2a26129c9d7d1fe66a13436e26f7181faee
Stable URL of this page
https://metraipolis.com/documento/dc_8f45a42fcfc3

How to cite

Evaluating Financial Sentiment in the Age of AI — arXiv:2609.20198 — arXiv (en), https://arxiv.org/abs/2609.20198 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f45a42fcfc3 (Metraipolis archive dc_8f45a42fcfc3, sha256 11ae8c75984f7a867dbf04dd7212c2a26129c9d7d1fe66a13436e26f7181faee)
BibTeX
@misc{dc8f45a42fcfc3,
  title = {Evaluating Financial Sentiment in the Age of AI — arXiv:2609.20198},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20198},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f45a42fcfc3; sha256 11ae8c75984f7a867dbf04dd7212c2a26129c9d7d1fe66a13436e26f7181faee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20198. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Financial sentiment measures are widely used in empirical finance, but it remains unclear whether general-purpose large language models (LLMs) improve on existing finance-specific methods. This paper evaluates twelve sentiment models, including dictionary-based methods, finance-specific transformers, and open-source LLMs, using two criteria: linguistic validity and economic validity. We find that general-purpose LLMs achieve classification performance comparable to finance-specific transformer models without task-specific fine-tuning. However, higher classification accuracy does not translate into stronger economic relationships. Several models produce sentiment measures that are significantly associated with earnings surprises, but none is significantly associated with next-day stock returns. Model performance is strongest for announcements with large earnings beats or misses and substantially weaker for announcements with more moderate earnings surprises. These findings suggest that financial sentiment captures information about firms' economic performance but has limited ability to explain short-run market reactions

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.20198 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:48:18.334Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).