hristijanpeshov/SHAP-Explainable-Lexicon-Model
This project proposes a novel methodology to automatically learn financial lexicons that outperform the benchmark Loughran-McDonald lexicon in sentiment analysis tasks
This project helps financial analysts and researchers improve sentiment analysis of financial text. It takes financial news articles, reports, or other text as input and generates a custom financial lexicon. This lexicon provides more accurate sentiment scores than standard lexicons, helping users better understand market sentiment or company performance.
No commits in the last 6 months.
Use this if you need to perform highly accurate sentiment analysis on financial documents and want a transparent, interpretable model.
Not ideal if you primarily work with non-financial text or prefer using pre-built sentiment models without needing to generate a custom lexicon.
Stars
15
Forks
3
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jan 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hristijanpeshov/SHAP-Explainable-Lexicon-Model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GunjanDhanuka/stocks-trading-bot
A multi-purpose repository with Sentiment Analysis of Stocks news, and Reinforcement learning...
tetratensor/Stock-Market-News-Sentiment-Analysis
A Python-based news sentiment analysis using Hugging Face Sentiment Analysis Model and Dataset.
timvvvht/HKEX-Announcement-Classifier
A project on data exploration, analysis and using a neural network to classify disclosure...
tmro98/financial-news-classification
binary topic and 3-class sentiment classification of full-length news articles
orbenh/sentiment-signal-nasdaq
Forecasting NASDAQ trends using financial news sentiment analysis with NLP, GPT-2 augmentation,...