Data retrieval from local heritage books—Is artificial intelligence the solution?
Artificial Intelligence (AI) is rapidly transforming all scientific disciplines. Among its many applications, AI can facilitate data retrieval from a wide range of sources. We evaluate the performance of large language models in extracting data from local heritage books—valuable sources for economic...
| Published in: | Historical Methods Vol. 59; no. 1; pp. 1 - 20 |
|---|---|
| Main Authors: | , |
| Format: | Article |
| Published: |
Taylor & Francis Ltd
Jan-Mar2026
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=191012088&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 191012088 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 01615440 HMT jtl: Historical Methods issn: 01615440 maglogo: N pubinfo: dt: Jan-Mar2026 vid: 59 iid: 1 pid: 377 pub: Taylor & Francis Ltd artinfo: ui: 191012088 10.1080/01615440.2025.2512744 ppf: 1 ppct: 19 formats: tig: atl: Data retrieval from local heritage books—Is artificial intelligence the solution? aug: au: Stelter, Robert Biehler, Rafael affil: Faculty of Business and Economics, University of Basel, Max Planck Institute for Demographic Research Faculty of Business and Economics, University of Basel su: Data extraction Python programming language Demography Textbooks Economic history Information retrieval Language models Artificial intelligence sug: subj: Data extraction Python programming language Demography Textbooks Economic history Information retrieval Language models Artificial intelligence keyword: data retrieval Large language models local heritage books Python programming ab: Artificial Intelligence (AI) is rapidly transforming all scientific disciplines. Among its many applications, AI can facilitate data retrieval from a wide range of sources. We evaluate the performance of large language models in extracting data from local heritage books—valuable sources for economic and demographic history. We compare the results of AI-driven, Python code-based, and manual data retrieval for random samples of observations from three heritage books. Our analysis shows that Python code-based retrieval consistently outperforms AI, particularly in minimizing issues such as omitted or hallucinated data. Furthermore, we show that, with minor modifications our Python code-based methods can be adapted to other local heritage books, highlighting the robustness and scalability of this traditional approach. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2026 holdings: @attributes: islocal: N |
|---|