Text Analytics project repository
We classified the genres of books from the GoodReads dataset, following their summary: https://www.kaggle.com/datasets/meetnaren/goodreads-best-books
- EDA
- Baseline
- Traditional genre classification using BoW, Word2Vec, Doc2Vec, TF-IDF (features) + ML models
- BERT and Transformers for genre classification
- ZSL for genre classification
- ZSL NER to analyze and compare the summaries
- Understanding of Summary Clarity w.r.t. the respective genre