This repository contains a collection of Google Colab notebooks exploring the use of Artificial Intelligence (AI) and Machine Learning (ML) in practical and creative contexts. These experiments are designed to be self-contained, reproducible, and useful as starting points for applying AI to real-world problems.
Notebooks focused on enhancing Agile processes with NLP:
retrospective_sentiment_analysis_colab.ipynb
➤ Perform sentiment analysis on retrospective notes using multilingual nlptown/bert-base-multilingual-uncased-sentiment.
➤ Detect emotional trends in team feedback (positive, neutral, negative).
This notebook explores the differences between general-purpose sentiment analysis models and financial domain-specific models when analyzing financial news headlines.
Comparison between two Hugging Face models:
distilbert-base-uncased-finetuned-sst-2-english→ General sentiment (Positive / Negative).ProsusAI/finbert→ Financial sentiment (Positive / Negative / Neutral).
- Python 3 (Google Colab)
- Transformers (Hugging Face pipelines)
- Scikit-learn, Pandas, Matplotlib, Plotly
To run any notebook:
- Open the notebook in Google Colab.
- Upload your input file when prompted.
- Follow the instructions within each cell.
- Review the outputs and export results (CSV or visualizations).
This repository is licensed under the MIT License.
Ideas, suggestions, and issues are welcome! Feel free to fork and adapt for your team or domain.