SayamAlt / Financial-News-Sentiment-Analysis

Successfully developed a fine-tuned DistilBERT transformer model which can accurately predict the overall sentiment of a piece of financial news up to an accuracy of nearly 81.5%.

Repository from Github https://github.comSayamAlt/Financial-News-Sentiment-Analysis

data-exploration-and-preprocessing distilbert-model fine-tune-bert-tensorflow hugging-face-transformers model-architecture-and-implementation model-inference model-training-and-evaluation multiclass-classification natural-language-processing sentiment-analysis text-preprocessing text-tokenization

About Dataset

Context

This dataset (FinancialPhraseBank) contains the sentiments for financial news headlines from the perspective of a retail investor.

Content

The dataset contains two columns, "Sentiment" and "News Headline". The sentiment can be negative, neutral or positive.

Acknowledgements

Malo, P., Sinha, A., Korhonen, P., Wallenius, J., & Takala, P. (2014). Good debt or bad debt: Detecting semantic orientations in economic texts. Journal of the Association for Information Science and Technology, 65(4), 782-796.

About

Successfully developed a fine-tuned DistilBERT transformer model which can accurately predict the overall sentiment of a piece of financial news up to an accuracy of nearly 81.5%.

Apache License 2.0

Languages

Language:Jupyter Notebook 100.0%