Assessfy Foundation Projects Lab Beginner 5 milestones 100 marks

Fake News Headline Detector

Discipline: AI & Data Level: Foundation Industry: AI & Data Function: Engineering Team: up to 3 Assessment: 5 milestones (100 marks)

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

What you'll build: A beginner text classifier that reads a news headline and predicts whether it looks "real" or "fake/clickbait", trained on a small labelled dataset.

Why it's a good starter: It is a first, self-contained NLP problem with a clear yes/no answer, free public datasets, and an obvious real-world hook.

What you'll learn: Loading a labelled text dataset, cleaning text, turning words into features (bag-of-words / TF-IDF) and training and testing a simple classifier.

Milestones

1. Setup & Plan

10 marks 5d

Choose a labelled fake/real headline dataset (e.g. from Kaggle) and load it into a notebook; submit a short note describing the columns and class balance.

2. Clean & prepare the text

30 marks 10d

Lowercase, remove punctuation and stop-words, and convert headlines into TF-IDF features. Submit the notebook cell showing the feature matrix shape and a couple of example rows.

3. Train & evaluate a classifier

30 marks 10d

Split into train/test, train a Logistic Regression or Naive Bayes model, and report accuracy plus a confusion matrix. Done when your model beats a majority-class baseline.

4. Testing & Polish

15 marks 6d

Test on your own 5 headlines you type in and note where it fails; add one improvement (more data or a different feature).

5. Demo & Short Report

15 marks 5d

Record a 2-3 minute demo classifying live headlines and submit a 1-page report with your accuracy and 2 limitations.

Open internships using this project -->

Skills you'll learn

AI & DataPythonNatural Language Processing basicsText cleaningscikit-learnModel evaluation

Tools used

Pythonpandasscikit-learna public fake-news CSVJupyter/Colab

Prerequisites

Basic PythonSchool maths

Available mentors

No mentors have signed up for this project yet.

Be the first to mentor

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

Fake News Headline Detector

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Beginner

Fake News Headline Detector

Assessfy

Auto-issued on completion One-click LinkedIn add