Docs / source reviewed

Novel Persona Radar

Watch character impressions change as a novel unfolds

nagoya0 · Sources checked 2026-09-30

Added to this collection 2026-09-30

How this project uses Jev

Input: Japanese novel paragraphs, human-reviewed cast and appearance annotations, and a predefined trait dictionary
Jev decides: For each on-stage character, Jev separately judges textual evidence for a trait and gives a five-level trait score
Code executes: Judgments are generated and saved offline; browser code applies evidence weighting and historical decay to display current and accumulated radar profiles and trait rankings

Evidence and limitations

Jev requests, missing-answer handling and profile accumulation were reviewed without running generation or validating judgments. The site replays stored results rather than calling Jev during reading. It targets desktop browsers and shows a screenshot on narrow screens. Code is MIT, with separate terms for novel text and judgment data. The author’s roughly US$0.03 cost was not reproduced; impressions are not objective personality assessments.

This project has not been run independently here. Author-reported results are not independently verified results.

Original sources

Explore related use cases

Browse this category →