Poem & Verse Similarity Guide
What is this page?
A reference guide to the similarity system in RunoVerse. It documents all similarity methods (7 poem-level, 5 verse-level), the geography metrics, and the tools that use them to find related poems and verses across 292K poems and 4.3M verse lines.
How to navigate
Each section describes one tool — what it does, its key features, and a direct link to open it. The tables at the bottom explain the poem-level algorithms, the verse-level algorithms, and the geography metrics. Scroll or use the browser's find-in-page (Ctrl/Cmd+F) to jump to a section.
Related explorer pages
Similarity Explorer — poem and verse similarity search · Poem Reader — per-poem similarity tabs · Verse Network Formulaicity — interactive similarity graph · Path Finder — shortest verse chains · Formula Explorer — formulaic patterns · Verse Analysis — cross-algorithm dashboard
RunoVerse provides multiple ways to explore how poems and verses relate to each other across the Finnish and Estonian runosong traditions. Whether you are tracing the spread of a formulaic verse line, comparing thematically related poems from different regions, or mapping cross-lingual parallels, the tools below offer complementary perspectives on the 292,092-poem, 4.3-million-verse corpus.
Poem Reader
The Poem Reader is an interactive viewer for all 292,092 poems from the SKVR (Finnish, published), JR (Finnish, unpublished), and ERAB (Estonian) collections. Each word in a poem is annotated with its standard orthography, English gloss, part-of-speech tag, and a link to its lemma in the dictionary. Clicking a word opens a dictionary lookup panel with full definitions from up to nine lexicographic sources.
- Word-level annotations: standard orthography, English glosses, POS tags, and lemma links for every token
- Dictionary lookups on click, drawing from Estonian and Finnish lexicographic sources
- Per-verse similarity expansion — click the arrow beside any verse line to see similar verses from other poems across the corpus
- Related Poems panel with five similarity algorithm tabs, showing the nearest neighbor poems ranked by each method
- Geographic map displaying where similar poems were collected
- Direct linking via URL — open any poem with
?poem=ID(e.g.,reader.html?poem=SKVR I1 1.)
Similarity Explorer
The Similarity Explorer is a standalone tool for investigating poem and verse
similarity in depth. It provides five exploration views, each showing a different
angle on the corpus. Press ? on the Similarity page for quick reference.
Poem Similarity lets you select any poem and view its nearest neighbors across all seven ranked views — five poem-level algorithms plus the verse-match and combined-RRF fused rankings. Each view displays its top matches with numeric similarity scores. A side-by-side comparison panel lets you read two poems together, line by line with shared words highlighted. A network graph visualizes the similarity neighborhood. Geographic and temporal analytics reveal where and when similar poems were collected.
Verse Similarity lets you search for individual verse lines and see similar verses from across the corpus, with results from five verse-level algorithms plus a combined view. An experimental Semantic neighbours – native embedding panel below each verse’s results finds lines with a similar meaning in any language directly from the original texts — including Estonian–Finnish pairs that share no words; it is separate from the five methods, highlights lines none of the five methods found, and opens by itself when it contains such lines (otherwise it stays collapsed), with a caveat explaining its limits. A research-view control can also reveal the candidate lines its quality rule rejected, each labelled with the reason it was hidden. The Formulaic Patterns browser shows the 200 most widely distributed recurring verse lines.
Verse Pairs browses the 50,000 strongest verse-to-verse connections, with a By Place Pair view grouping pairs by collection location.
Geography offers five map-based submodes: Verse Network (place-to-place connections), Cross-Lingual Formulas (Estonian-Finnish bridges), Poem Connections, Combined (verse + poem layers), and Place Focus (single-place exploration).
Formulaicity reveals the formulaic skeleton of individual poems, scoring each verse by how closely it matches verses elsewhere in the corpus.
- Five poem-level similarity algorithms, plus verse-match and combined-RRF fused rankings, with ranked results and scores
- Side-by-side poem comparison panel with word-level highlighting
- Network graph showing similarity neighborhoods
- Geographic and temporal distribution of similar poems
- Algorithm agreement badges (BOTH) for cross-algorithm matches and ET/FI badges for cross-lingual matches
- Verse search with five algorithms plus combined view
- 50,000 pre-ranked verse pairs with By Place Pair grouping
- Five geography submodes with interactive maps
- Per-verse formulaicity scoring with color strip visualization
- Top 200 formulaic verse patterns
Verse Concordance
The Verse Concordance provides full-text search across 2,906,535 unique verse types drawn from 4.32 million total verse lines. Enter any text fragment to find matching verses. Results include a geographic distribution chart showing where each verse was collected (with a link to the full map view), a language breakdown (Estonian vs. Finnish), and occurrence tables listing which poems contain the verse and how frequently it appears.
- Full-text search across 2.9 million unique verse lines
- Geographic distribution chart for each matching verse
- Language breakdown showing Estonian and Finnish occurrences
- Occurrence tables with poem IDs and frequencies
Verse Network
The Verse Network displays an interactive force-directed graph of verse similarity neighborhoods. Start from any verse and explore multi-hop connections to see how verses are linked through shared similarity across the corpus. Each edge shows a per-algorithm score breakdown, so you can see which similarity measures contribute to each connection. Results can be exported as CSV for further analysis.
- Interactive force-directed graph centered on any starting verse
- Multi-hop exploration — follow chains of similar verses
- Per-algorithm score breakdown on each connection (Jaccard, TF-IDF, Translation, CharBigram, Sentence)
- CSV export of network data
Verse Path Finder
The Verse Path Finder locates the shortest chain of similar verses connecting any two verses in the Finnic runosong corpus. The result is displayed as an interactive chain showing each intermediate verse and the similarity scores between consecutive steps. This reveals how seemingly unrelated verses may be connected through a sequence of incremental textual similarities.
- Shortest-path search between any two verses
- Interactive chain visualization with intermediate verses
- Similarity scores shown between each step
Formula Explorer
The Formula Explorer lets you browse 200 formulaic verse patterns ranked by frequency and geographic spread. A “formula” here is a cluster of similar verse lines found across many poems — evidence of oral tradition transmission, where singers in different times and places used recognizably similar wording. Each cluster shows its variant texts, the number of member verse occurrences across poems, geographic spread across collection places, and cross-links to the network visualization for further exploration.
- 200 formulaic verse clusters ranked by frequency and geographic spread
- Variant texts within each cluster
- Occurrence counts and poem distribution
- Geographic spread across collection places
- Cross-links to the Verse Network for deeper exploration
Verse Similarity Analysis
The Verse Similarity Analysis is a cross-algorithm dashboard showing how the five verse-level similarity algorithms — Jaccard, TF-IDF, Translation-pivot, CharBigram, and Sentence — compare across the 4.3 million verse lines in the corpus. It includes formulaic cluster analysis and geographic coverage metrics, providing a high-level view of how similarity patterns distribute across the material.
- Cross-algorithm comparison dashboard for five verse similarity measures
- Formulaic cluster analysis
- Geographic coverage metrics
Poem-level similarity algorithms
Seven ranked views identify related poems: five poem-level algorithms plus two fused rankings (verse match and combined RRF). Each captures a different aspect of similarity — from shared vocabulary to cross-lingual thematic overlap to structural verse alignment. Results from all seven are available in the Poem Reader and the Similarity Explorer.
| Algorithm | Basis | Description |
|---|---|---|
| TF-IDF Lemma | Lemma-level | Cosine similarity on TF-IDF vectors of lemmatized poem texts. Captures thematic similarity through shared vocabulary, weighted by corpus-level term importance. |
| Wordform Overlap (Jaccard) | Exact wordforms | Jaccard index over raw wordform sets. Identifies poems sharing exact surface forms, useful for detecting formulaic lines and direct textual parallels. |
| Thematic (Translation) | Cross-lingual | Pivoted cosine similarity over English translations derived from DeepSeek annotations. Enables cross-lingual comparison between Estonian and Finnish poems via a shared semantic space. |
| Alignment | Character n-gram | Verse sequence alignment using character bigram cosine similarity and dynamic programming, from the FILTER project (Janicki, Kallio & Sarv 2023). Captures structural similarity — poems that follow the same verse order score high. |
| Semantic (GloVe) | Embeddings | GloVe 300-dimensional word vectors combined using SIF weighting (Arora et al. 2017) on English translations. Captures broad thematic resemblance even when poems use entirely different words. Cross-lingual by nature. |
| Verse Match | Verse-level fusion | Runs five verse-level algorithms (Jaccard, TF-IDF, Translation, CharBigram, Sentence) on individual verse pairs, aggregates best matches per verse via RRF, then combines into a single poem-level ranking. |
| Combined (RRF) | Meta-ranking | Reciprocal Rank Fusion across TF-IDF, Jaccard, Translation, and Alignment. A poem ranks high only if multiple algorithms agree it is a good match. Scores shown as percentage of theoretical maximum. |
Verse-level similarity algorithms
Five algorithms compare individual verse lines across the corpus. Each captures a different kind of textual similarity. Their results feed into tools like Verse Similarity, Verse Pairs, and the Geography maps, and are also aggregated into the poem-level Verse Match algorithm above.
| Algorithm | What it compares | Description |
|---|---|---|
| Jaccard | Shared words | Counts how many exact words two verses share, divided by the total number of distinct words in both. High scores mean the verses use largely the same vocabulary. |
| TF-IDF | Rare words | Like Jaccard, but weights rare words more heavily than common ones. Two verses sharing an unusual word score higher than two sharing a word that appears everywhere. |
| Translation | Cross-lingual meaning | Compares verses through their English translations, so it works across Estonian and Finnish. Two verses with the same meaning score high even if the original words differ entirely. |
| CharBigram | Letter patterns | Compares how words look letter-by-letter using character bigrams (two-letter pairs). Catches similarities between dialect spellings or closely related word forms that exact-word methods miss. |
| Sentence | Semantic meaning | Compares verse meanings using all-MiniLM-L6-v2 sentence embeddings on English translations. Captures broad thematic resemblance even when the original words differ entirely. Cross-lingual by nature. |
Geography metrics
The Geography section of the Similarity Explorer uses several metrics to measure how strongly two collection places are connected through shared verse material. These metrics appear in the Verse Network and Place Focus map views.
| Metric | Description |
|---|---|
| Normalized surprise | How unexpected a verse connection is between two places, given the sizes of both collections. Large places naturally share more material, so this metric divides the shared count by the geometric mean of both collections’ sizes. A high surprise score means two places share more verses than you would expect from their sizes alone. |
| Combined count | The raw total of shared verse pairs (identical + near-matches) between two places. Bigger numbers mean more shared material, but larger collections naturally produce higher counts. |
| Identical formulas only | Counts only verse lines that appear word-for-word the same in both places. |
| Near-matches only | Counts verse pairs that are algorithmically similar but not identical — dialect variants, minor word substitutions, and partially shared lines. |
| Tradition Strength | An overall quality score for how much poetic material two places share, used in the Place Focus view. Combines the count and diversity of shared verse connections. |