FIRE 2026 — Shared Task

Indic Meme Understanding
& Sentiment Analysis (IMUSA)

IMUSA — A pioneering multimodal shared task for sentiment classification of Punjabi memes, addressing low-resource Indic language understanding at FIRE 2026.

📍FIRE 2026
🗓️Opens 30 May 2026
🌐First Edition
3.5k
Total Memes
3002
Training Set
500
Test Set
4
Categories
3
Max Runs

About the Task

IMUSA is the first shared task focused on multimodal sentiment analysis of Punjabi memes a low-resource Indic language combining visual and textual modalities to understand the rich, culturally-embedded communication in social media content.

🧩 Multimodal Challenge

Memes convey meaning through the interplay of images and text. Neither modality alone captures the irony, humour, or emotion. IMUSA challenges participants to build systems that jointly model visual and textual features for accurate sentiment classification.

🌏 Low-Resource Language Focus

Punjabi is an Indo-Aryan language with a large global diaspora. Despite its widespread use, computational resources for Punjabi remain scarce. IMUSA addresses this gap with a manually annotated multimodal Punjabi meme dataset.

🤖 Advanced AI Techniques Encouraged

Participants are encouraged to leverage cutting-edge methods including multimodal BERT variants, CNNs for visual feature extraction, LSTMs/Transformers for text, cross-modal fusion mechanisms, and self-attention-based architectures.

🎯 Real-World Impact

Systems developed in IMUSA will have direct applications in content moderation, automated hate-speech detection, mental health monitoring, and cultural analytics across South Asian social media platforms.

Sentiment Categories

Each Punjabi meme in the dataset is annotated into one of four sentiment categories, designed to capture a wide range of emotional tones and communicative intents.

😏

Sarcasm

Memes where the intended meaning differs from the literal expression. Relies on irony, exaggeration, or indirect references to convey humour or criticism. Example: commentary on social media behavior with a reversed meaning.

😐

Neutral

Memes with no strong emotional tone or opinion. Present general information, everyday situations, or observational content without conveying clear positivity, negativity, or intent to influence emotions.

⚠️

Offensive

Content that is abusive, insulting, or inappropriate. Targets individuals, communities, or social groups and contributes to harmful narratives. Identifying such content is critical for automated moderation systems.

💪

Motivational

Memes intended to inspire or encourage positive thinking. Include uplifting messages, life advice, or emotionally supportive content aimed at motivating individuals and promoting well-being.

Dataset Details

A manually annotated multimodal Punjabi meme dataset of 3,000 images, labelled with the assistance of linguistic experts to ensure accuracy and contextual consistency.

Total Memes 3502
Training Dataset 3002
Test Dataset 500
Language Punjabi (ਪੰਜਾਬੀ)
Modalities Text + Image

Class Distribution

😏 Sarcasm
00
😐 Neutral
00
⚠️ Offensive
00
💪 Motivational
00

* Distribution is approximate; class imbalance reflects real-world social media data.

Task Timeline

15 June 2026

🚀 Registration Opens

Track website goes live. Training data made available to registered participants.

17 June 2026

📦 Training Data Release

Test set distributed to participants for final system evaluation.

10 July 2026

📤 Test Dataset Release

All participant system runs must be submitted. Each team may submit 1–3 runs.

18 July 2026

Run Submission Deadline

Official track results announced and communicated to all participating teams.

6 August 2026

🏆 Results Declaration

Participants submit working notes describing their approach and results.

TBD

📄 Paper Submission Deadline

Final camera-ready copies of working notes and the overview paper are due.

Evaluation Plan

Participant systems will be evaluated using four standard metrics from information retrieval and machine learning, chosen to provide a comprehensive assessment across imbalanced class distributions.

Accuracy

Measures overall correctness — the proportion of correctly predicted samples out of the total. Provides a general sense of system performance.

🎯

Precision

Evaluated per class. Measures how many instances predicted as a particular class are actually correct — indicating the reliability of positive predictions.

🔍

Recall

Evaluated per class. Measures how well the system identifies all relevant instances. Critical for Sarcasm and Offensive categories where misclassification has high impact.

⚖️

F1-Score

The harmonic mean of Precision and Recall. Provides a balanced evaluation especially useful for uneven class distributions, reflecting the trade-off between false positives and negatives.

Organizers

PD

Dr. Pankaj Kundan Dadure

Assistant Professor
UPES, Dehradun, India
HS

Dr. Hitesh Kumar Sharma

Professor & Associate Dean (SCS)
UPES, Dehradun, India
YD

Yash Kumar Dhiman

PhD Scholar
UPES, Dehradun, India