MemeStream – AI-Moderated Social Platform

Case study, stack, and technical highlights

MemeStream – AI-Moderated Social Platform

1 image
MemeStream – AI-Moderated Social Platform - Image 1

Project Details

Completed
Web Application

Dedicated meme-sharing platform with Google Gemini multimodal AI for automated meme detection and quality scoring at post time, real-time messaging and notifications over SignalR hubs (1:1 and group chat, read receipts), a multi-signal personalized feed (time decay, diversity interleaving, seen-post tracking) and a gamified 8-tier LaughScore ranking. JWT + BCrypt security, Docker Compose deployment. Published evaluation: 45 ms median API latency, <100 ms real-time delivery, 99.8% uptime — the research behind my first-author ECCT 2026 paper.

Key Features

  • Gemini multimodal content validation
  • SignalR real-time chat + notifications
  • Multi-signal personalized feed
  • 8-tier LaughScore gamification

Achievements

  • First-author peer-reviewed paper accepted at ECCT 2026
  • 45 ms median API latency, 99.8% uptime in published evaluation

Project Info

Status:Completed
Type:Web Application
Category:Full Stack Development
Created:7/15/2026

Comments (0)

Mashrur Rahman

AI Engineer & Full-Stack Developer building real-time voice agents, RAG systems, and modern web platforms. Let's build something amazing together.

Get In Touch

Email

mashrur9550@gmail.com

Location

Dhaka, Bangladesh

© 2026 Mashrur Rahman. All rights reserved.