Social Network Analysis and Applications (SoNAA)
☕ Where Graphs Collaborates with Machine Learning for Problem Solving ☕
Research Threads
Graph is the central to all the threads we investigate
Fake News Detection
Can use of scemantic graph improve fake news detection accuracy?
Query Focused Summarization
How do we summarize if we have multiple documents in multiple language and a perticular question?
Information Difusion
What if two competing information is spreading simultonously?
Aggression Detection
Aggression spreads on network, how do we predict the future states of user behaviour?
Generative AI for Education
Can GenAI be an useful tool for new age pedagogy.
Visualization for Feature Engineering
Can graph visualization can also be used for feature generation for GNN?
We are coming to AAAI 2025
Paper ‘TSGAN: Temporal Social Graph Attention Network for Aggressive Behaviour Forecasting’ by Swapnil, Suman and Rajesh acepted for presentation
- First model to forecast individual aggression in social networks.
- TSGAN integrates social influence (via active peers) and temporal decay (via exponential attention) into a unified attention module.
- 24.8% improvement over baselines in daily aggression forecasting on X. State-of-the-art results on cross-platform Flickr for user popularity prediction.
- Proposed LLM-based aggression content detection model (92.87% F1).
- Efficiently scales to moderately large networks and is tolerant to aggression content detection noise.
- Provides actionable forecasts for platforms to mitigate aggression-driven harms (e.g., cyberbullying, offline violence).
Our Paper at WACV 2025
Paper ‘CaMN: Cross-aligned Fusion For Multimodal Understanding’ by Abhishek, Shubham and Suman is acepted for presentation
- A novel denoising based multi-modal architecture that seamlessly integrates vision, text, and graph representation through a proposed guided cross attention mechanism
- Designed a new objective function to align modalities within a unified semantic space, thereby improving the model’s coherence for better classification.
- Superior performance on the publicly available dataset, outperforming existing state-of-the-art methodologies
Checkout our latest publications
Forecasting aggressive behavior in social networks using TSGAN to create safer digital spaces.
Feb 16, 2025
Hugo Blox is designed to give technical content creators a seamless experience. You can focus on the content and Hugo Blox handles the rest. Use popular tools such as Plotly, Mermaid, and data frames.
Jan 14, 2025