A collection of Natural Language Processing (NLP) projects demonstrating practical applications of machine learning.
- Objective: Detecting malicious (phishing) emails using NLP techniques to enhance cybersecurity defenses.
- Methodology: TF-IDF Vectorization, Logistic Regression.
- Key Insight: Analyzed email length and keyword patterns to distinguish between safe and phishing content with high accuracy.
- File:
01_Phishing_Email_Detection.ipynb
- Objective: Analyzing customer feedback from Turkish e-commerce platforms to classify sentiment (Positive/Negative).
- Methodology: Custom Text Preprocessing (Turkish-specific), NLTK, TF-IDF.
- Key Insight: Visualized sentiment distribution and achieved robust classification performance on noisy text data.
- File:
02_Sentiment_Analysis_Tr.ipynb
- Libraries:
scikit-learn,pandas,seaborn,nltk,matplotlib - Techniques: Text Preprocessing, Vectorization (TF-IDF), Supervised Learning.
You can view the notebooks directly on GitHub or run them in Google Colab.