Book Genre Classification

• 

  Still working on it

Book Genre Classification Inspiration Classifying books manually into genres is time-consuming and inconsistent. This project automates genre classification using Machine Learning and Natural Language Processing (NLP) to improve efficiency.

What We Learned

• Preprocessing textual data for ML models.
• Feature extraction using TF-IDF and word embeddings.
• Training and evaluating a text classification model.
• Handling imbalanced datasets in classification problems.

How We Built It

1. Data Collection:
   • Used an open dataset from Goodreads/OpenLibrary containing book titles, descriptions, and genres.
2. Preprocessing:
   • Removed stopwords, punctuation, and applied lemmatization. 3.Feature Extraction:
   • Converted text into numerical features using TF-IDF (Term Frequency-Inverse Document Frequency.
3. Model Training:
   • Trained Logistic Regression, Random Forest, and SVM classifiers.
4. Evaluation & Optimization:
   • Measured performance using accuracy, precision, recall, and F1-score.

Challenges Faced

• Handling imbalanced data, where some genres had fewer books than others.
• Improving accuracy by choosing the best feature extraction method.
• Optimizing the model to avoid overfitting.

Built With

• Languages & Libraries: Python, Pandas, Scikit-learn, NLTK, Matplotlib
• Dataset: OpenLibrary Dataset / Goodreads Dataset
• Model: Logistic Regression / SVM / Random Forest
• Platform: Google Colab / Jupyter Notebook

Built With

• languages-&-libraries:-python
• nltk
• pandas
• scikit-learn