MétaCan
Menu
Back to cohort
Record W2784791047 · doi:10.16995/dscn.295

Is Falstaff Falstaff? Is Prince Hal Henry V?: Topic Modeling Shakespeare’s Plays

2018· article· en· W2784791047 on OpenAlexaffvenue
Laura Estill, Luís Meneses

Bibliographic record

VenueDigital Studies / Le champ numérique · 2018
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsUniversity of Victoria
Fundersnot available
KeywordsDictionHenry IV, Holy Roman EmperorComedyAssertionLiteratureWindsorArtHumanitiesPhilosophyHistoryArt historyPerformance artComputer sciencePoetry

Abstract

fetched live from OpenAlex

This essay demonstrates how topic modeling can be fruitfully applied to TEI-encoded plays, which allows scholars to analyze speeches by individual characters. Our analysis centers on Shakespeare’s corpus and characters who reappear in multiple plays. Specifically, we use topic models to show that young Prince Hal (in 1 and 2 Henry IV) does not speak the same language as his later self, Henry V (in his titular play): his linguistic shift mirrors his shift in status. Hal himself announces, “I have turned away my former self”—his change in diction bears out his assertion. Conversely, topic models reveal that Falstaff is Falstaff across multiple plays and genres (notably, 1 and 2 Henry IV and The Merry Wives of Windsor), despite scholarly claims to that the Falstaff of comedy is a watered-down version of the braggart drunk of the history plays. Ultimately, we hope that this algorithmically-informed analysis of Shakespeare’s plays is not taken as a final answer, but, instead, as a prompt. As this research reveals, topic modeling plays with attention to each speaker opens the door for new comparisons, and in turn, expands on previous interpretations of literature. Cet essai démontre que les modèles à thèmes (topic model) peuvent être appliqués avec succès à des pièces encodées en TEI, ce qui permet aux érudits d’analyser le discours de personnages individuels. Notre analyse se concentre sur le corpus de Shakespeare et sur ses personnages qui réapparaissent dans plusieurs pièces. Particulièrement, nous employons des modèles à thèmes pour montrer que le jeune Prince Hal (1 et 2 Henri IV) ne parle pas le même langage que celui qu’il parle après être devenu Henri V (Henri V): son changement linguistique reflète son changement de standing. Hal, lui-même, annonce: « j’ai renoncé à mon passé » —son changement de diction confirme cette affirmation. Inversement, les modèles à thèmes révèlent que Falstaff est Falstaff à travers plusieurs pièces et genres (notamment, 1 et 2 Henri IV et Les Joyeuses Commères de Windsor), malgré des affirmations érudites que le Falstaff dans la comédie est une version édulcorée du vantard ivre des pièces d’histoire. Finalement, nous espérons que cette analyse algorithmique des pièces de Shakespeare n’est pas considérée comme une solution finale, mais plutôt comme une réplique. Comme cette recherche le montre, l’usage de modèles à thèmes pour analyser des pièces, ce qui se concentre sur chaque personnage, offre de nouvelles voies de comparaisons et étoffe donc nos interprétations de la littérature. Mots-clés: Shakespeare; pièces de théâtre; modèle thématique; modèles à thèmes; Falstaff; Prince Hal; Henry V; Henri IV; Joyeuses commères de Windsor

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.011
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.017
Threshold uncertainty score0.034

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.011
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0070.006
Open science0.0010.001
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.083
GPT teacher head0.372
Teacher spread0.290 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations5
Published2018
Admission routes2
Has abstractyes

Explore more

Same venueDigital Studies / Le champ numériqueSame topicComputational and Text Analysis MethodsFrench-language works237,207