CSI SPIT ML Sprint 2026 – Official Competition Rules
ENTRY INTO THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL RULES.
This is a skill-based machine learning competition organized by
Computer Society of India (CSI), Sardar Patel Institute of Technology (SPIT)
. 
Participants must register via the Kaggle competition page to enter. By submitting a solution, you agree to comply with these Official Competition Rules.
1. COMPETITION DETAILS
Competition Title:
CSI SPIT ML Sprint 2026 – Human Emotion Classification
Competition Sponsor:
Computer Society of India (CSI), SPIT Student Chapter
Sponsor Address:
Sardar Patel Institute of Technology, Andheri (West), Mumbai, Maharashtra, India
Competition Website:
https://www.kaggle.com/competitions/[your-competition-link]
Prizes:
Certificates and Recognition will be awarded to the Top 3 teams on the final leaderboard.
Winner License Type:
Non-Exclusive License (see Section 5)
2. COMPETITION OVERVIEW
The objective of this competition is to build a machine learning model capable of classifying tweets into one of the following six human emotions:
Sadness (0)
Joy (1)
Love (2)
Anger (3)
Fear (4)
Surprise (5)
Participants will develop models using natural language processing techniques to accurately classify text data containing informal language and emojis.
Evaluation Metric:
Submissions will be evaluated using
Accuracy
, ensuring balanced performance across all emotion classes.
3. TEAM RULES
Maximum team size:
2 members
.
Team mergers are allowed before the Team Merger Deadline.
The merged team must not exceed the maximum allowed submissions.
4. SUBMISSION RULES
Maximum of
10 submissions per day
.
Participants may select up to
2 final submissions
for final judging.
Final rankings will be based on the
Private Leaderboard
.
5. DATA ACCESS AND USAGE POLICY
Competition Use & Academic Research Only:
The Competition Data may be used only for:
Participating in this competition
Academic learning and research purposes
Discussion on Kaggle forums related to this competition
Commercial usage of the dataset is strictly prohibited.
Participants must not redistribute, share, or publish the dataset outside Kaggle.
6. EXTERNAL DATA & PRETRAINED MODELS
Use of publicly available pretrained models (e.g., BERT, DistilBERT) is allowed.
External datasets are allowed only if they are publicly accessible and free for all participants.
Paid proprietary datasets are NOT allowed.
All external resources must comply with Kaggle’s Reasonableness Standard.
7. WINNER’S OBLIGATIONS
Winners must:
Provide a detailed explanation of their methodology.
Share reproducible code (training + inference).
Describe preprocessing steps, model architecture, hyperparameters, and evaluation strategy.
The Sponsor may request a brief presentation from winning teams during the ML Sprint event.
8. LICENSE AGREEMENT
By participating, winners grant the Competition Sponsor a
worldwide, non-exclusive, royalty-free license
to review, reproduce, and showcase the winning solution for educational and promotional purposes.
9. FAIR PLAY POLICY
Multiple Kaggle accounts are strictly prohibited.
Any attempt to manipulate the leaderboard will result in disqualification.
Private Leaderboard score will determine final ranking.
10. GOVERNING LAW
This competition is governed under the academic and institutional policies of
Sardar Patel Institute of Technology, Mumbai, India
.
The organizers reserve the right to modify rules if necessary to ensure fairness.
We encourage creativity, ethical AI practices, and reproducible machine learning solutions.
Good luck and happy modeling!