The Analysis
This system uses co-occurrence analysis to map how each speaker uses language. For every word a speaker says, the system records which other words appear near it. This builds a unique linguistic fingerprint for each word in each speaker's vocabulary.
When both speakers use the same word, the system compares these fingerprints. If the surrounding words are similar, the word is shared — both speakers mean roughly the same thing. If the surrounding words are very different, the word is contested — the same word is carrying different meaning in each speaker's world.
AI & Methodology
The speakers' voices are transcribed using AI speech-to-text. After that, the analysis is entirely mathematical — word counting and co-occurrence comparison. There is no AI interpreting what the words mean or drawing conclusions.
This is deliberate. Rather than handing you an AI-generated summary, this system gives you the raw linguistic patterns and invites you to be the analyst. You decide what it means when two people use the same word differently. The interpretation is yours.
Reading the Map
Speaker A only
Speaker B only
Shared context
Contested
Word pills — each word appears as a pill-shaped node on the map. The color indicates its category. Larger pills mean the word was used more frequently.
Pulsing words — contested words glow and pulse. These are the conceptual fault lines where both speakers use the same word but in completely different contexts.
Connecting lines — thin lines between words show co-occurrence. Words that appear near each other in a speaker's speech are linked. The lines reveal clusters of related concepts within each speaker's vocabulary.
Tap a word — opens a detail card showing the word's category, how often each speaker used it, and the actual sentences where it appeared, with the word highlighted in context.
The Tabs
Speaker A / Speaker B — read each speaker's full transcript as it was spoken. Words from the map are highlighted inline so you can see them in their original flow.
Stats — shows word counts, vocabulary overlap percentage, a breakdown of words by category, the top contested words, and a convergence-over-time graph tracking how the speakers' vocabularies have evolved during the performance.
Gestures
Pinch to zoom the map. Drag to pan. Double-tap to reset the view.