Twitter/X comment and reply scraper with sentiment analysis
NYU Hackathon — We won :)
Deterministic local-first tool for exploring six controlled tone variations of a single line of dialogue.
Three-layer tone classifier (dark / hopeful / cynical) embedding lookup, edge TF-IDF+LogReg inference on Cloudflare Workers, rule-based fallback. Ships with a labeled public domain poetry corpus.
Public app demo showing LLOYD working with GPT-2.
AI-powered tone detection tool for content alignment. Analyzes sample text and compares it to target brand voice traits to flag mismatches and guide refinement. Great for QA in marketing teams.
Twitter/X reply scraper with sentiment analysis
Symbolic emotional middleware for LLMs — tone-shift detection, memory-aware response, metaphor density analysis.
Deterministic reflex-aware conversational middleware: tone tagging → deviation scoring → governance modes (Terminal + React demo, seeded replay, no external APIs).
Auditor and educational tool that analyzes ChatGPT 5.2’s “Karen-style” tone patterns and demonstrates methods for customizing AI behavior.
Add a description, image, and links to the tone-analysis topic page so that developers can more easily learn about it.
To associate your repository with the tone-analysis topic, visit your repo's landing page and select "manage topics."