<scp>FinBERT</scp>: A Large Language Model for Extracting Information from Financial Text*

Huang, Allen; Wang, Hui; Yang, Yi

doi:10.1111/1911-3846.12832

Cited by 157 publications

(85 citation statements)

References 82 publications

(138 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A. Huang et al (2022) use human-annotated sentences of financial text of three sentiment classes (positive, neutral, and negative) to fine-tune FinBERT for sentiment analysis. They report that the overall accuracy of FinBERT is 88.2% for their test sample, substantially higher than that of the dictionary approach (62.1%), NB (73.6%), SVM (72.6%), RF (71.9%), CNN (75.1%), and LSTM (76.3%).…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…A. Huang et al (2022) report the sensitivity of model performances to varying sizes of training sample. FinBERT maintains an 22.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…A. Huang et al (2022) summarize steps for using FinBERT. Many researchers share code, measures, and implementation guidance on their websites or GitHub (or similar).…”

Section: Recommended Resourcesmentioning

confidence: 99%

See 2 more Smart Citations

Textual Analysis in Accounting: What's Next?*

Bochkay

Brown²,

Leone³

et al. 2022

Contemporary Accting Res

View full text Add to dashboard Cite

Natural language is a key form of business communication. Textual analysis is the application of natural language processing (NLP) to textual data for automated information extraction or measurement. We survey publications in top accounting journals and describe the trend and current state of textual analysis in accounting. We organize available NLP methods in a unified framework. Accounting researchers have often used textual analysis to measure disclosure sentiment, readability, and disclosure quantity; to compare disclosures to determine similarities or differences; to identify forward‐looking information; and to detect themes. For each of these tasks, we explain the conventional approach and newer approaches, which are based on machine learning, especially deep learning. We discuss how to establish the construct validity of text‐based measures and the typical decisions researchers face in implementing NLP models. Finally, we discuss opportunities for future research. We conclude that (i) textual analysis has grown as an important research method and (ii) accounting researchers should increase their knowledge and use of machine learning, especially deep learning, for textual analysis.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

“…A. Huang et al (2022) report the sensitivity of model performances to varying sizes of training sample. FinBERT maintains an 22.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Textual Analysis in Accounting: What's Next?*

Bochkay

Brown²,

Leone³

et al. 2022

Contemporary Accting Res

View full text Add to dashboard Cite

show abstract

“…A recent article analyzes FinBERT’s sentiment performance, as well as its advantages over classic BERT large language models (LLMs) [ 43 ]. FLANG models [ 44 ] expand upon FinBERT and benefit from training on a benchmark known as the Financial Language Understanding Evaluation (FLUE) benchmark.…”

Section: Related Workmentioning

confidence: 99%

Integrating Economic Theory, Domain Knowledge, and Social Knowledge into Hybrid Sentiment Models for Predicting Crude Oil Markets

2023

View full text Add to dashboard Cite

For several decades, sentiment analysis has been considered a key indicator for assessing market mood and predicting future price changes. Accurately predicting commodity markets requires an understanding of fundamental market dynamics such as the interplay between supply and demand, which are not considered in standard affective models. This paper introduces two domain-specific affective models, CrudeBERT and CrudeBERT+, that adapt sentiment analysis to the crude oil market by incorporating economic theory with common knowledge of the mentioned entities and social knowledge extracted from Google Trends. To evaluate the predictive capabilities of these models, comprehensive experiments were conducted using dynamic time warping to identify the model that best approximates WTI crude oil futures price movements. The evaluation included news headlines and crude oil prices between January 2012 and April 2021. The results show that CrudeBERT+ outperformed RavenPack, BERT, FinBERT, and early CrudeBERT models during the 9-year evaluation period and within most of the individual years that were analyzed. The success of the introduced domain-specific affective models demonstrates the potential of integrating economic theory with sentiment analysis and external knowledge sources to improve the predictive power of financial sentiment analysis models. The experiments also confirm that CrudeBERT+ has the potential to provide valuable insights for decision-making in the crude oil market.

show abstract

“…The most successful labeling functions we tested utilize large language models (Devlin et al, 2018;Brown et al, 2020;Hoffmann et al, 2022) to achieve one or both of the above tasks. Large language models can achieve impressive results on passage retrieval and information extraction tasks (Agrawal et al, 2022;Huang et al, 2022), although not without limitations and biases (Bender et al, 2021).…”

Section: Core Features and User Interfacementioning

confidence: 99%

Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents

Butcher¹,

Zilka²,

Cook³

et al. 2023

Preprint

View full text Add to dashboard Cite

While humans can extract information from unstructured text with high precision and recall, this is often too time-consuming to be practical. Automated approaches, on the other hand, produce nearly-immediate results, but may not be reliable enough for high-stakes applications where precision is essential. In this work, we consider the benefits and drawbacks of various human-only, human-machine, and machine-only information extraction approaches. We argue for the utility of a human-in-the-loop approach in applications where high precision is required, but purely manual extraction is infeasible. We present a framework and an accompanying tool for information extraction using weak-supervision labeling with human validation. We demonstrate our approach on three criminal justice datasets. We find that the combination of the computer speed and human understanding yields precision comparable to manual annotation while requiring only a fraction of time, and significantly outperforms fully automated baselines in terms of precision.

show abstract

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

Cited by 157 publications

References 82 publications

Textual Analysis in Accounting: What's Next?*

Textual Analysis in Accounting: What's Next?*

Integrating Economic Theory, Domain Knowledge, and Social Knowledge into Hybrid Sentiment Models for Predicting Crude Oil Markets

Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents

Contact Info

Product

Resources

About