Topics Covered (Day-wise)

Day 1: Foundations of NLP & Text Preprocessing

• What is NLP? – Applications in real life (chatbots, search engines, sentiment analysis)
• NLP pipeline overview
• Introduction to NLTK & spaCy – Installing libraries
• Basic Text Preprocessing: Tokenization, Stopword removal, Lemmatization vs stemming, Lowercasing, punctuation removal
• Hands-on Practice: Clean a small dataset or user input text, extract tokens, lemmas using NLTK and spaCy

Day 2: Text Representation & Feature Engineering

• Text Vectorization Techniques: Bag of Words (BoW), TF-IDF, N-grams
• Using scikit-learn for text features: CountVectorizer, TfidfVectorizer
• Hands-on Practice: Vectorize cleaned text, Compare BoW vs TF-IDF on sample text

Day 3: Text Classification with Machine Learning

• Basics of Text Classification: Supervised learning pipeline (train/test split, modeling, evaluation)
• Modeling with Scikit-learn: Naive Bayes, Logistic Regression (brief)
• Model Evaluation: Accuracy, Precision, Recall, Confusion Matrix

Registration Fee

• Indian Participants: ₹499
• Foreign Participants: $10

Certificate & Recordings

Participants will receive an e-certificate and access to the full workshop recordings after completion.

Resource Person

Dr. Shanti Verma
Director,
Lokmanya Institute of Management and Computer Applications,
Gujarat Technological University, Ahmedabad