September 30, 2022Contemporary Accounting ResearchOpen Access

FinBERT: A Large Language Model for Extracting Information from Financial Text*

View Full Paper

Ask AI

Bookmark

FinBERT exceeds standard sentiment classification baselines by detecting at least 18% more textual informativeness from corporate earnings conference calls.
Benchmark on researcher-labeled analyst reports compares the domain-adapted model against support vector machine and convolutional neural network baselines.
Implications extend to market regulators and investors, supporting the specialized large language model for contextual information retrieval across disclosures.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Machine learning evaluation demonstrates superior sentiment classification in financial disclosures, highlighting improved textual informativeness over generic models.

Cite This Study

Huang et al. (2022) studied this question.

synapsesocial.com/papers/6940a69282ff3a988e998089 https://doi.org/10.1111/1911-3846.12832

View Full Paper

Ask AI

Bookmark

Implication

Machine learning evaluation demonstrates superior sentiment classification in financial disclosures, highlighting improved textual informativeness over generic models.

FinBERT: A Large Language Model for Extracting Information from Financial Text*

Key Points

Discussion

Implication

Cite This Study

FinBERT: A Large Language Model for Extracting Information from Financial Text*

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider