Treasure Legends Emotion Analysis
Emotion Analysis

Treasure Emotion Analysis

Emotion pipeline results for 6,195 Estonian treasure legends — RunoVerse

Press 19 to jump to sections, ? for help

Table of Contents

1 Domain Landscape

Treemap of 13 canonical emotion domains sized by wordform count.

2 Motif-Type Emotion Profiles

Top 30 P-types with strongest emotion signals (total annotated tokens across all domains).

3 Geographic Hotspots

Top 20 parishes by emotion word density (emotion words per 1,000 tokens).

4 System A vs System B Comparison

How the two detection systems overlap in discovered emotion words.

5 Discovery Depth Analysis

E-word counts by discovery depth (System A expansion rounds), coloured by domain.

6 Cross-Validation Strength

Distribution of hit_rate (fraction of PPMI sources confirming the word) across all System A words.

7 Runosong Comparison

Domain distribution overlap between runosong poetry and treasure prose emotion lexicons.

8 High-Impact Words

Top 50 emotion words ranked by corpus frequency × confidence score.

9 Emotion Co-occurrence

How often pairs of emotion domains appear in the same record (out of 6,195 records).

10 Narrative Position

Average position (quartile 1–4) of emotion words within each record. Q1 = beginning, Q4 = end.

11 Seed Bias Analysis

Discovered E-words: PPMI score (distance from nearest seed) vs hit_rate. Higher PPMI = closer to seeds.

12 Emotion Profiles by Legend Type

Each of the 93 treasure-legend types carries a distinct emotional signature. This explorer normalises the raw emotion signals (mentions, not poems) so large and small types are comparable — in the default view every row sums to 100 %. Switch to Over/under-index to see how far a type departs from the corpus average, the clearest measure of what makes a legend type emotionally distinctive. Distinctiveness is most reliable above the record floor (default ≥ 40); raw counts and corpus comparisons appear on hover. Data: treasure_emotion_by_type.json (loaded live).

Loading…
Link copied!

Keyboard Shortcuts

1Jump to Domain Landscape 2Jump to Motif-Type Profiles 3Jump to Geographic Hotspots 4Jump to System A vs B 5Jump to Discovery Depth 6Jump to Cross-Validation 7Jump to Runosong Comparison 8Jump to High-Impact Words 9Jump to Emotion Co-occurrence 0Jump to Narrative Position -Jump to Seed Bias Analysis /Focus search (if present) SShare current URL ?Toggle this help EscClose help overlay

About This Dashboard

This dashboard presents emotion pipeline results for 6,195 Estonian treasure legends (varandusemuistendid). Emotion words were detected using two complementary systems: System A (PPMI-based seed expansion) and System B (TES dictionary matching), covering 13 canonical emotion domains. Charts show domain distribution, geographic patterns, motif-type profiles, system overlap, and validation metrics.