Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature

Jean Barré, Olga Seminck, Antoine Bourgois, Thierry Poibeau

TL;DR

This work tackles how the detective archetype is constructed across 150 years of French literature by applying distant-reading methods to a large French fiction corpus. It builds a supervised detector using both Bag-of-Words and CamemBERT-based character embeddings, with LOGO validation to ensure temporal and authorial independence, and demonstrates that CamemBERT+SVM achieves stateful performance. The study reveals a durable, underlying textual signature for detectives while showing three semantic phases corresponding to rational-puzzle, empathic-procedural, and hardboiled-moral-ambiguous iterations, and it links these shifts to broader genre evolutions such as Série Noire and néo-polar. Overall, the approach provides a scalable framework for analyzing archetypes, offering actionable insights for literary theory and enabling cross-genre character typology assessments.

Abstract

This research explores the evolution of the detective archetype in French detective fiction through computational analysis. Using quantitative methods and character-level embeddings, we show that a supervised model is able to capture the unity of the detective archetype across 150 years of literature, from M. Lecoq (1866) to Commissaire Adamsberg (2017). Building on this finding, the study demonstrates how the detective figure evolves from a secondary narrative role to become the central character and the "reasoning machine" of the classical detective story. In the aftermath of the Second World War, with the importation of the hardboiled tradition into France, the archetype becomes more complex, navigating the genre's turn toward social violence and moral ambiguity.

Modeling the Construction of a Literary Archetype: The Case of the Detective Figure in French Literature

TL;DR

This work tackles how the detective archetype is constructed across 150 years of French literature by applying distant-reading methods to a large French fiction corpus. It builds a supervised detector using both Bag-of-Words and CamemBERT-based character embeddings, with LOGO validation to ensure temporal and authorial independence, and demonstrates that CamemBERT+SVM achieves stateful performance. The study reveals a durable, underlying textual signature for detectives while showing three semantic phases corresponding to rational-puzzle, empathic-procedural, and hardboiled-moral-ambiguous iterations, and it links these shifts to broader genre evolutions such as Série Noire and néo-polar. Overall, the approach provides a scalable framework for analyzing archetypes, offering actionable insights for literary theory and enabling cross-genre character typology assessments.

Abstract

This research explores the evolution of the detective archetype in French detective fiction through computational analysis. Using quantitative methods and character-level embeddings, we show that a supervised model is able to capture the unity of the detective archetype across 150 years of literature, from M. Lecoq (1866) to Commissaire Adamsberg (2017). Building on this finding, the study demonstrates how the detective figure evolves from a secondary narrative role to become the central character and the "reasoning machine" of the classical detective story. In the aftermath of the Second World War, with the importation of the hardboiled tradition into France, the archetype becomes more complex, navigating the genre's turn toward social violence and moral ambiguity.

Paper Structure

This paper contains 18 sections, 1 equation, 5 figures, 2 tables.

Table of Contents

  1. Introduction
  2. The Detective Archetype
  3. Definition
  4. Origins
  5. The Detective Detector
  6. Corpus and Data Annotation
  7. Character Embeddings
  8. Bag of Words representation:
  9. Contextual Embeddings with CamemBERT:
  10. Supervised Classification
  11. Quantitative Evaluation
  12. Qualitative Evaluation of the Distinctive Attributes of the Detective Archetype
  13. The Emergence of the Detective Figure
  14. The Semantic Trajectory of the Detective Archetype
  15. Discussion
  16. ...and 3 more sections

Figures (5)

  • Figure 1: Model prediction error over time.
  • Figure 2: Attribute distinctiveness of the Detective figure, measured by normalized z-score. A value of $+1$ indicates the most strongly detective-associated attribute and $-1$ the least.
  • Figure 3: Model-predicted detective character ratio over time.
  • Figure 4: Progressive establishment of the detective as the narrative core.
  • Figure 5: Predicted detective clusters.