Project Information

  • Title: Vaccination Tweets - Text Normalization and Text Classification
  • Course: Predictive Analytics Project
  • Date: January 2023
  • Skills Demonstrated:
    • Programming Languages: Proficient in Python for data preprocessing, text classification, and analysis.
    • Data Loading: Successfully loaded and prepared the dataset for analysis.
    • Data Labeling: Implemented data labeling techniques using data frames.
    • Handling Null Values: Checked and addressed null values in the dataset.
    • Text Normalization: Performed text normalization on textual data for consistent analysis.
    • Text Classification: Employed text classification techniques for categorizing vaccination-related tweets.
    • Feature Engineering: Utilized TF-IDF (Term Frequency-Inverse Document Frequency) for feature extraction.
    • Model Training: Trained a predictive model using TF-IDFVectorizer.
    • Machine Learning: Achieved model fitting and accuracy using Support Vector Machine (SVM).
    • Model Evaluation: Evaluated model performance using techniques such as Confusion Matrix.
    • Data Visualization: Created informative visualizations, including heatmaps and classification reports.
    • Notebook Documentation: Proficient in Jupyter Notebook for documenting code and project progress.
    • Project Management: Effectively managed project milestones, timelines, and resources.