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 · Major Project
Hotel Review Aspect-Based Sentiment
Scores room, staff, food and location separately in each review
3-4 weeks build
Overview
A single star rating hides the fact that a guest loved the location and hated the breakfast. This kit splits reviews from the public TripAdvisor Hotel Reviews dataset into sentences, assigns each to an aspect with a keyword-plus-embedding classifier, then fine-tunes a transformer to judge sentiment per aspect. A dashboard shows each hotel's strengths and complaints side by side.
What makes it stand up
- 01Aspect detection for room, staff, food, location and value
- 02Sentence-level splitting with spaCy dependency parsing
- 03Fine-tuned DistilBERT for aspect-conditioned sentiment
- 04Lexicon baseline kept alongside for comparison
- 05Hotel dashboard with per-aspect scores and example quotes
Module breakdown
- 01
Segmentation
Breaks reviews into clauses that mention a single aspect.
- 02
Aspect tagging
Seed keywords expanded with sentence embeddings.
- 03
Sentiment model
Fine-tunes a transformer on aspect and sentence pairs.
- 04
API
FastAPI endpoint returning aspect scores for any review.
- 05
Dashboard
React view of aspect scores, trends and supporting quotes.
After this, you will be able to
- Explain how aspect-based sentiment differs from document sentiment
- Defend the labelling strategy used for fine-tuning
- Demo a mixed review being split into opposing aspect scores
Technology stack
- Python
- spaCy
- PyTorch
- Hugging Face Transformers
- FastAPI
- React
- Level
- Major Project
- Domain
- Machine Learning
- Build time
- 3-4 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