Narratological Algorithmic Lenses

Narrative analysis has operated for a century on frameworks that are structurally precise but computationally inert. Vladimir Propp demonstrated in 1928 that Russian wondertales could be decomposed into thirty-one sequential functions — a formal grammar of plot — yet his Propp's morphology Vladimir Propp's 1928 discovery that all Russian fairy tales share the same thirty-one sequential plot functions, forming a universal grammar of narrative structure remained a paper artifact, executed only by human readers marking up texts by hand.^[1] Genette's framework Gerard Genette's systematic taxonomy for analyzing narrative discourse across five dimensions: order, duration, frequency, mood, and voice — distinguishing order, duration, frequency, mood, and voice — provided an analytical apparatus of extraordinary precision, yet it too remained confined to close reading, applicable only at the pace of a single scholar working through a single text.^[2] This project asks what happens when these frameworks stop being interpretive vocabularies and become executable algorithms: typed Python models with diagnostic outputs, confidence scores, and testable assertions. The goal is not to automate literary criticism but to give narrative theoryThe study of how stories are structured and how that structure creates meaning — applied here to system design the same computational infrastructure that other formal disciplines — linguistics, logic, mathematics — have long taken for granted.

The core intellectual challenge is translating humanistic frameworks into computational primitives without flattening the interpretive richness that makes them valuable. Propp's morphologyVladimir Propp's 1928 discovery that all Russian fairy tales share the same thirty-one sequential plot functions, forming a universal grammar of narrative structure provides the clearest entry point: his thirty-one functions (Absentation, Interdiction, Violation, Reconnaissance, and so on) form an ordered sequence with defined transition rules — essentially a finite state machineA model describing all possible states a system can be in and the transitions between them for plot.^[1] Algirdas Julien Greimas's actantial model Greimas's reduction of any narrative to six structural roles (Subject, Object, Sender, Receiver, Helper, Opponent) on three axes of desire, communication, and power abstracts further, reducing any narrative to six actantial roles (Subject, Object, Sender, Receiver, Helper, Opponent) organized into three axes of desire, communication, and power — a structural semantics that applies across genres and media.^[3] Roland Barthes's distinction between five narrative codes Barthes's five channels through which a text produces meaning: hermeneutic (enigma), proairetic (action), semantic (connotation), symbolic (theme), and cultural (shared knowledge) — hermeneutic, proairetic, semantic, symbolic, and cultural — provides yet another decomposition, one that foregrounds the reader's experience of meaning-construction rather than the text's internal grammar.^[4] Each framework becomes a separate analysis module in the core library, with its own typed models, detection heuristics, and output schemas — but all sharing a common interface contract that allows frameworks to be composed, compared, and cross-referenced.

The system's analytical breadth is defined by its compendium — a living library of twenty-eight formalized narrative frameworks spanning classical, film, television, global, interactive, comics, and meta-analytical traditions. Classical frameworks include Aristotle's dramatic structure, Bharata Muni's Natyasastra, Ovid's metamorphic narrative, Plato's dialectical form, Horace's decorum principles, and African oral epic traditions. Film frameworks encode the directorial theories of Tarkovsky (time-pressure), Bergman (interiority), Tarantino (discovery writing), Lynch (dream logic), and Kubrick (non-submersible units). Television frameworks formalize Phoebe Waller-Bridge's layered obstacle technique, Larry David's comedy geometry, and South Park's therefore/but causal structure. Global traditions include Kishotenketsu (the Japanese four-act structure that operates without conflict) and the Heroine's Journey (Murdock's model of internal integration). Interactive narrative frameworks encode the design philosophies of Zelda (exploration-driven) and Final Fantasy (ensemble-driven). Comics frameworks include Alan Moore's formalism, Grant Morrison's hypersigil technique, and Jack Kirby's mythopoeia.^[3] Each framework is stored as both a completed Markdown study (in specs/02-completed-studies/) and a validated JSON extract (in specs/03-structured-data/), with a synchronization mechanism ensuring that edits to the research source are reflected in the computational model.

The monorepo is structured as six distinct packages, each serving a different consumer while sharing the same analytical core. This separation follows the ports-and-adapters An architectural pattern (also called hexagonal architecture) where domain logic lives at the center and all external interfaces are interchangeable adapters plugged into defined ports pattern: the core library contains all domain logic — models, algorithms, diagnostics, the unified compendium of narratological definitions — while the CLI, API, MCP server, VS Code extension, and web dashboard are adapters that expose that logic through different interfaces.^[5] The Python core bundles a unified compendium of narratological algorithms as structured JSON, with a loader that resolves packaged resources first and falls back to repository paths for local development. The CLI (built on Typer) enables terminal-based analysis for researchers who work in scripts and pipelines. The FastAPI service provides programmatic access for downstream ORGAN-II and ORGAN-III systems. The MCP server (built on FastMCP) exposes the analytical engine through the Model Context Protocol, enabling AI assistants to invoke narratological analysis as a tool call. The VS Code extension provides snippets and tagging for researchers working directly in the editor. The React web dashboard enables interactive visual exploration.^[6]

The system's output is not a label but a diagnostic — a structured report that tells the analyst not just what was detected but how confident the detection is, what evidence supports it, and what structural relations connect it to other detections. When the engine runs a Proppian analysis, it does not simply say "this is a hero's journey." It reports precisely which morphological functions were detected, at what confidence level, with what ordering violations (if any), and which functions are expected but absent.^[7] Moretti's argument for " distant reading Franco Moretti's method of analyzing literature computationally across thousands of texts to reveal patterns invisible to close reading of individual works " — analyzing literature not through close attention to individual texts but through computational aggregation of patterns across thousands — requires exactly this kind of structured, machine-readable output. The diagnostic model enables composability: an actantial analysis can be cross-referenced with a Proppian analysis to identify where Greimas's Subject maps onto Propp's Hero function, revealing structural homologies that close reading might miss.^[8] Jockers's macroanalytic method depends on the ability to aggregate and compare structured outputs across corpora — the diagnostic format is designed to feed precisely this kind of computational literary scholarship.

The most powerful analytical results emerge not from applying a single framework but from composing multiple frameworks against the same text and examining where their outputs converge, diverge, or complement each other. A Proppian analysis detects sequential plot functions; an actantial analysis detects role assignments on axes of desire, communication, and power; a Genettean analysis detects focalization Genette's term for the narrative perspective through which events are perceived, distinguishing who sees from who speaks in a story shifts and temporal ordering. When all three run against the same narrative segment, the diagnostic engine can map Propp's "Hero" function onto Greimas's Subject role and Genette's internal focalizationGenette's term for the narrative perspective through which events are perceived, distinguishing who sees from who speaks in a story, revealing that a protagonist's agency is simultaneously a plot function, a structural position, and a perspective anchor.^[2] This compositional approach reflects a design principle borrowed from software architecture: each framework is a module with a stable interface, and the system's value grows combinatorially as modules are composed rather than linearly as they are added.^[5] Cross-referencing also surfaces disagreements — cases where frameworks assign contradictory structural roles to the same entity — and these disagreements are diagnostically valuable, pointing to genuine ambiguities in the narrative rather than analytical errors.

The narratological lenses project occupies a specific position within the eight-organ system: it is ORGAN-I (Theoria) infrastructure that enables work in ORGAN-II (Poiesis) and ORGAN-III (Ergon). When narrative theoryThe study of how stories are structured and how that structure creates meaning — applied here to system design is encoded as executable algorithms with typed outputs, those outputs become inputs for generative systems. A Proppian analysis that identifies the "Villainy" and "Lack" functions at specific text positions can drive a generative music system to shift harmonic mode at those structural inflection points. An actantial analysis that maps Subject-Object-Opponent relations can inform the spatial layout of an interactive visualization, positioning entities according to their structural roles.^[9] Murray's vision of the computer as a medium for procedural, participatory, spatial, and encyclopedic storytelling requires exactly this kind of machine-readable narrative intelligence — not stories generated by algorithms, but analytical structures that algorithms can consume and transform. The lenses project makes theory operational: it turns ORGAN-I's scholarly frameworks into API endpoints that ORGAN-II's art tools and ORGAN-III's product prototypes can call.^[10] Manovich's thesis that software has become the engine of cultural production implies that the boundary between analysis and generation is permeable — the same typed models that describe a narrative's structure can be used to synthesize new structures that satisfy the same constraints.

The digital humanities have produced remarkable tools for corpus analysis — topic modelingAn unsupervised machine learning technique that discovers abstract thematic clusters across a collection of documents, sentiment analysis, named entity recognition — but these tools largely bypass the rich structural vocabularies that narratologists have spent a century developing. Propp's functions, Greimas's actants, Genette's focalizationGenette's term for the narrative perspective through which events are perceived, distinguishing who sees from who speaks in a story categories, and Barthes's codes represent decades of careful theoretical work about how stories actually organize meaning, yet computational literary studies have largely ignored them in favor of statistical methods borrowed from natural language processing.^[4] This project fills that gap by encoding narratological frameworks as first-class computational objects — not approximations or metaphors, but faithful implementations with typed models, validation logic, and confidence scoring. The result is a system where disagreements between frameworks become debuggable, where analytical claims are testable assertions, and where the entire history of narrative theoryThe study of how stories are structured and how that structure creates meaning — applied here to system design becomes a composable toolkit rather than a bibliography.^[3] When a narratological claim is encoded as a function with assertions, scholarly debate gains a new modality: not just argument and counter-argument, but test case and counter-example.