- Original Pdf: pdf
- TL;DR: We introduce FinBERT, a language model based on BERT for financial text classification, where we improved state-of-the-art performance by 14 percentage points.
- Abstract: While many sentiment classification solutions report high accuracy scores in product or movie review datasets, the performance of the methods in niche domains such as finance still largely falls behind. The reason of this gap is the domain-specific language, which decreases the applicability of existing models, and lack of quality labeled data to learn the new context of positive and negative in the specific domain. Transfer learning has been shown to be successful in adapting to new domains without large training data sets. In this paper, we explore the effectiveness of NLP transfer learning in financial sentiment classification. We introduce FinBERT, a language model based on BERT, which improved the state-of-the-art performance by 14 percentage points for a financial sentiment classification task in FinancialPhrasebank dataset.
- Keywords: Financial sentiment analysis, financial text classification, transfer learning, pre-trained language models, BERT, NLP