What is the Semantic Explorer?

This tool lets you explore 704K+ annotated wordforms in the Finnic runosong corpus through three semantic tiers, organized by reliability:

1. Thesaurus Domains (25) — Recommended

Translation-based semantic groupings using English seed keywords. High precision for this corpus because the method relies on dictionary translations rather than NLP models. Domains include: Family & Kinship, Animals, Body & Health, Plants & Crops, Water & Sea, and 20 more.

• Each domain shows top lemmas with frequency, language (ET/FI/both), and POS
• Click seed keyword pills to filter by defining concepts
• Data from thesaurus_index.json (25 domains, 40K+ keywords)

2. Emotion Categories (26) — Reliable

Multi-method emotion vocabulary audit using GoEmotions, SetFit, NRC EmoLex, and EKKD dictionary data. ~90% accurate. Organized into 38 families across 26 domains (e.g., rõõm, viha).

• ML Pipeline (P) — GoEmotions sentiment + SetFit domain classification
• EKKD (E) — Curated emotion vocabulary from the Estonian Emotion Dictionary
• Data consistent with all other emotion pages (Emotion Families, Emotional Geography, Emotion Canvas)

3. NLP Entity Categories (26) — Experimental

Entity categories from NLP models (GLiNER NER, WordNet, thesaurus keyword matching, morphological detection, lemma propagation). These models were trained on modern English/general text and may have lower accuracy on archaic dialectal runosong vocabulary. Results are preliminary — use with caution.

• ML Pipeline (P) — Multi-method NER + WordNet + dictionary + morphological detection
• Thesaurus (T) — 25-domain keyword matching on English translations
• Cross-validation between sources increases confidence

Tabs

• Overview — Corpus-wide stats, provenance breakdown, category bar chart, method donut, co-occurrences.
• Browse — Three-tier sidebar: thesaurus domains (green), emotions (purple), NLP entities (grey/collapsed). Click to explore wordforms, filter by language/confidence/source/method.
• Geography — Map showing where semantic categories concentrate geographically.
• Cross-lingual — Butterfly chart comparing Estonian vs Finnish per category.
• Discoveries — Newly discovered emotion vocabulary, method overlap matrix, geographic outliers.

Confidence Levels

• High (≥0.70) — Multiple methods agree or expert-curated (EKKD E-class).
• Medium (0.40–0.69) — At least one reliable method with moderate support.
• Low (<0.40) — Single weak signal; includes EKKD J-class (neighbor words) at 0.39.