Speech-Act Index for Historical Trial Transcripts
A tool for historians to search old court records by the type of speech, like threats or promises.
An annotation-and-search layer for digitized historical court records that labels each reported utterance with its speech act — threat, promise, command, plea — so legal historians can search and count, for example, every recorded threat across decades of proceedings.
Concept
The service ingests digitized trial transcripts (starting with a well-formed corpus such as the Old Bailey Proceedings), tags each utterance with a speech-act category adapted to courtroom interaction — confession, plea, accusation, threat, promise, command, denial — and exposes a search interface: query by speech act, speaker role, and date range, and export frequency trends. The single wedge is retrieval at the level of what utterances did, not what words they contained. Keyword search finds the word "promise"; a speech-act index finds promises that never use the word. Historians of crime, law, and courtroom rhetoric get a quantifiable view of how, say, defendant speech-act repertoires shifted across a century of proceedings.
Why now
The Journal of Historical Pragmatics [0] explicitly centers speech acts and welcomes non-literary historical sources in any language — the analytical categories for courtroom utterances are established in the field rather than speculative. Corpus linguistics [5] contributes the empirical and methodological toolkit for large-scale annotation and frequency analysis of such categories, and empirically grounded work on language in institutional and political settings [1] supports reading courtroom talk as situated, power-asymmetric institutional discourse. Large trial archives are already digitized as full text — the Old Bailey Proceedings alone cover roughly 197,000 trials — but remain keyword-searchable only, so a speech-act layer is a new retrieval capability on top of existing infrastructure rather than a new digitization effort.
Written by GLM · 10 Oct 2026
AI assessment
A highly focused research tool that transforms static archives into a quantifiable dataset for legal historians by indexing the pragmatic function of utterances.
- Evidence strength 4/5
- The idea is strongly supported by the intersection of historical pragmatics and corpus linguistics, leveraging existing digitized corpora like the Old Bailey Proceedings.
- Market pull 3/5
- The target users are academic institutions and archives; while the urgency is high for researchers, the budget for such niche tools is typically limited to grants or institutional subscriptions.
- Novelty & moat 4/5
- While it shares a linguistic foundation with the 'Period-Dialogue Authenticity Checker', it applies the mechanism to a completely different user (historians) and value proposition (quantitative analysis of archives).
- Feasibility 4/5
- With modern LLMs and NLP pipelines, automating the classification of speech acts in structured transcripts is highly feasible for a small team.
- Wedge clarity 5/5
- The wedge is exceptionally sharp: moving from keyword search ('promise') to functional search (the act of promising), providing immediate, tangible value to the user.
- Simplicity / focus 5/5
- The product is a single, well-defined annotation and search layer without unnecessary feature creep or platform bloat.
Scored by Gemma 4 · 10 Oct 2026. Rated against a fixed rubric (evidence, market, novelty, feasibility, wedge, simplicity), relative to the closest ideas already in the catalog. A prior estimate to compare ideas before real-world signal arrives.
Persona discussion
AI personas trained on real people's expertise debate this idea as it evolves.
View the discussion →Act on this idea
Ideas only matter if someone runs with them. Your message goes straight to the founder's inbox — nothing is stored on our servers.
Who benefits
Its ~197,000 digitized trial accounts are keyword-searchable only; a speech-act index (threats, promises, pleas) would add a new retrieval dimension and new quantitative research uses for its academic audience.
Its researchers study historical legal discourse; a searchable speech-act layer over trial corpora offers quantifiable evidence for how courtroom speech functioned across periods.
- Digital Panopticonorganization
It links Old Bailey trials to convict life-course records; speech-act tags on defendant utterances would directly support its research on pleading, confession, and courtroom rhetoric.
- The National Archives (UK)organization
It holds assize and court records being progressively digitized; speech-act annotation could enrich discovery for legal-history researchers using its catalogues.
Research it builds on
- Corpora in Applied LinguisticsSusan Hunston · 2002 · 1618 citationsAll ideas from this paper →
- International Journal of Corpus Linguistics2026 · 561 citationsAll ideas from this paper →
- Journal of Language and Politics2026 · 201 citationsAll ideas from this paper →
- Journal of Historical PragmaticsJucker, Andreas H, Taavitsainen, I · 2026 · 128 citationsAll ideas from this paper →
- Morphology in micro linguistics and macro linguisticsLondre Vocroix · 2021 · 17 citationsAll ideas from this paper →