Assessfy Pvt. Ltd Moderate 7 milestones 50 marks

Sentiment Analysis of Placement Data for Job Classification Using Naive Bayes and Suppo...

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

Sentiment Analysis of Placement Data for Job Classification Using Naive Bayes and Support Vector Machine

Objective: Classify job placement sentiment using Naive Bayes and Support Vector Machine algorithms.

Context: Understanding student placement sentiment helps colleges and recruiters in India tailor support and opportunities, addressing the gap between education and employability. Automated sentiment analysis can reveal trends and concerns in placement data.

What you'll build: You will collect and preprocess placement-related text data, perform tokenization and vectorization, and build classification models using Naive Bayes and SVM in Python (NLTK, scikit-learn). The project involves comparing model performance and visualizing results with matplotlib, all within Jupyter or Google Colab environments.

Deliverables: Outputs include a working sentiment classifier, performance metrics, visualizations, and a concise report summarizing findings and methodology.

Milestones

No submission required for this milestone.

2. Data collection and preparation

5 marks 5d

Collect a labeled dataset of placement-related text data (e.g., student feedback, interview experiences) with corresponding job classification or sentiment labels. Submit the raw data file (CSV or Excel) and document the data sources, label definitions, and any initial cleaning steps performed. Ensure the dataset is suitable for supervised sentiment analysis.

3. Preprocessing (tokenization, stop-word removal, vectorization)

5 marks 5d

Preprocess the collected text data by applying tokenization, stop-word removal, and vectorization (e.g., TF-IDF or CountVectorizer). Submit your preprocessing script and a sample of the transformed feature matrix. Demonstrate that text is cleaned, tokenized, and converted into numerical vectors ready for model input.

4. Train/test split

5 marks 5d

Split your preprocessed dataset into training and testing sets, clearly indicating the proportion used for each (e.g., 80/20 split). Submit the code used and summary statistics (e.g., class distribution) for both sets to confirm that the split maintains label balance and data integrity.

5. Model building: Naive Bayes and SVM

5 marks 5d

Build and train both a Naive Bayes classifier and a Support Vector Machine (SVM) on your training data. Submit your model training scripts and evidence (e.g., training logs or model summaries) that both models have been fit to the data without errors.

6. Performance comparison (accuracy, precision, recall)

15 marks 5d

Evaluate both models on the test set, reporting accuracy, precision, and recall for each. Submit a comparison table of metrics and brief comments interpreting which model performs better and why, based on your placement sentiment data.

7. Report and visualization

15 marks 5d

Compile a concise report summarizing your workflow, results, and key findings. Include visualizations such as confusion matrices, ROC curves, and metric bar charts for both models. Submit the report as a PDF and all relevant plots, ensuring clarity and insight into model performance and implications for job classification.

Open internships using this project -->

Upcoming sessions

Session	Window	Enrolled
Sentiment Analysis of Placement Data for Job Classificati...	11 Jun 2026 to 10 Jun 2028	0

Skills you'll learn

Natural Language Processing (NLP)Machine Learning (Naive BayesSVM)Python ProgrammingData Cleaning & TokenizationText Classification

Tools used

Python (NLTKscikit-learnpandasmatplotlib) Jupyter Notebooks Google Colab (for execution) CSV or survey datasets

Prerequisites

Basics of NLP Understanding of supervised learning Python basics and libraries (scikit-learnpandas)

Available mentors

Priyang Kumar

Free

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

Sentiment Analysis of Placement Data for Job Classification…

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.

Moderate

Sentiment Analysis of Placement Data …

Assessfy

Auto-issued on completion One-click LinkedIn add