PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Mini Project
Sarcasm Detection
Flags sarcastic news headlines with classic and neural models
1-2 weeks build
Overview
Classifies headlines as sarcastic or sincere using the public News Headlines Dataset for Sarcasm Detection on Kaggle, which pairs satirical and real news sources. A TF-IDF logistic regression baseline is compared with a bidirectional LSTM, and the report discusses what the models actually learn, including the risk of learning the source rather than the sarcasm.
What makes it stand up
- 01Headline dataset with clean labels from satirical and real outlets
- 02TF-IDF baseline and bidirectional LSTM compared
- 03Pretrained GloVe embeddings for the neural model
- 04Error analysis of headlines both models get wrong
- 05Streamlit demo with a confidence bar
Module breakdown
- 01
Data
Loading, deduplication and stratified splits.
- 02
Baseline
TF-IDF features with logistic regression.
- 03
Neural model
Embedding layer and bidirectional LSTM.
- 04
Evaluation
Precision, recall, F1 and ROC curves for both models.
- 05
Demo
Type a headline and see the predicted label.
After this, you will be able to
- Explain why sarcasm is hard for word-level models
- Discuss dataset bias and what the model may really learn
- Demo predictions on headlines the examiner writes
Technology stack
- Python
- scikit-learn
- TensorFlow
- Pandas
- Streamlit
- Level
- Mini Project
- Domain
- Machine Learning
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support