Word Collocates

What this shows

Co-occurrence analysis of words in Finnic runosong verses. Two words are "collocates" if they frequently appear in the same verse line. The strength of association is measured by PMI (Pointwise Mutual Information) — high PMI means the words appear together much more often than chance would predict.

How to read the results

• PMI score — measures how strongly two words are associated (higher = stronger). PMI naturally downweights common function words.
• Co-occurrence count — how many verses contain both words.
• Mutual badge — shown when both words list each other as top collocates (bidirectional strong association).

Sorting

• By PMI — shows the strongest statistical associations (often rare but very specific pairs)
• By frequency — shows the most common co-occurrences (frequent pairs)

Top Pairs

The "Top Formulaic Pairs" section shows the 200 most notable word pairs across the entire corpus, ranked by combined PMI and frequency. These often represent core runosong formulas like parallelism pairs and refrains.