---
title: "Construction of Japanese Prefectural — Takamaru 2026"
description: "Minutes of Japanese local assemblies are a large, legally mandated record of subnational political talk."
authors: ["Keiichi Takamaru", "Hokuto Ototake", "Yuzu Uchida", "Yasutomo Kimura"]
year: 2026
venue: "Proceedings of the Fifteenth Language Resources and Evaluation Conference"
source: "https://aclanthology.org/2026.lrec-1.492/"
doi: "10.63317/5hsgnayssvei"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/takamaru-2026-construction-japanese-prefectural-assembly-minutes/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/takamaru-2026-construction-japanese-prefectural-assembly-minutes/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/) / Construction of Japanese Prefectural Assembly Minutes Datasets across Three Electoral Terms: Comparative Analysis of 2011, 2015, and 2019 Four-Year Periods

# Construction of Japanese Prefectural Assembly Minutes Datasets across Three Electoral Terms: Comparative Analysis of 2011, 2015, and 2019 Four-Year Periods

**Authors:** Keiichi Takamaru, Hokuto Ototake, Yuzu Uchida, Yasutomo Kimura · **Year:** 2026 · **Venue:** Proceedings of the Fifteenth Language Resources and Evaluation Conference · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.lrec-1.492/) · [PDF](https://aclanthology.org/2026.lrec-1.492.pdf) · [DOI 10.63317/5hsgnayssvei](https://doi.org/10.63317/5hsgnayssvei) · [OpenAlex](https://openalex.org/W7160049406)

**Citations:** 0 citations (openalex-snapshot · 2026-10-14)

## Summary
Minutes of Japanese local assemblies are a large, legally mandated record of subnational political talk. They remain underused because each prefecture publishes them in its own format. The authors finish a 12-year series of datasets covering plenary sessions in all 47 prefectural assemblies. The series spans three four-year electoral terms (2011, 2015, 2019), with the 2019 term newly added.

They wrote a custom crawler for each prefecture's search system and split the minutes into individual remarks. Each remark was tagged with speaker, meeting and date. Members received persistent IDs and were linked to candidate data (gender, birth date, district) from the Seijiyama election site. Name variants were reconciled by hand.

Comparing the terms shows fewer members aged 25–44 and a gradual rise in female representation. Women also produce longer speeches than men. The authors illustrate the corpus's value through three uses: gender/age discourse analysis, AI-based dialectology and a web search/visualization tool. The resource supports political science, sociolinguistics and NLP work on a non-Western democracy.

## Key points
- Corpus size: 12,236,974 records, 743,147,226 characters and 471,496,688 tokens (tokenized with MeCab + IPADIC). The 2011, 2015 and 2019 terms have about 4.40M, 3.83M and 4.01M records.
- Each term runs April to March over four years, starting with the 2011 term (April 2011–March 2015). Six prefectures, including Tokyo and Okinawa, hold their elections outside the unified cycle.
- Even in 2019, the term with the most women, they made up only about 12% of members. Female members used 20–30% more characters per speech than males in every age group.
- Members who never spoke ranged from under 2% (younger women) to over 10% (men aged 65+). In 2019, total speech volume ranged from 2.14M characters (Yamagata) to 10.86M (Okinawa).
- The data is available to researchers on request, with public querying through a web interface. Integration into the "Giimiru v2" search system is planned.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Linguistics & languages](https://md.research.elamur.ai/free/en/shelves/linguistics/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{takamaru2026construction,
  title = {{Construction of Japanese Prefectural Assembly Minutes Datasets across Three Electoral Terms: Comparative Analysis of 2011, 2015, and 2019 Four-Year Periods}},
  author = {Takamaru, Keiichi and Ototake, Hokuto and Uchida, Yuzu and Kimura, Yasutomo},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5hsgnayssvei},
  url = {https://doi.org/10.63317/5hsgnayssvei}
}
```

- [← previous Construction and Analysis of Japanese Parent-Child Dialogic Reading Corpus for Conversational Agents](https://md.research.elamur.ai/free/en/papers/nakagi-2026-construction-analysis-japanese-parent-child/)
- [next → Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG](https://md.research.elamur.ai/free/en/papers/lingbulk-2026-setiawan-context-volume-drives-performance-tackling/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/3/)

## References

18 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Eduardo Alemán, Margarita M. Ramírez, and Jonathan B. Slapin. 2017. Party strategies, constituency links, and legislative speech. Legislative Studies Quarterly, 42(4):637–664. [find](https://scholar.google.com/scholar?q=Eduardo+Alem%C3%A1n%2C+Margarita+M%2E+Ram%C3%ADrez%2C+and+Jonathan+B%2E+Slapin%2E+2017%2E+Party+strategies%2C+constituency+links%2C+and+legislative+speech%2E+Legislative+Studies+Quarterly%2C+42%284%29%3A637%E2%80%93664%2E)
2. Dallas Card, Serina Chang, Chris Becker, Julia Mendelsohn, Rob Voigt, Leah Boustan, Ran Abramitzky, and Dan Jurafsky. 2022. Computational analysis of 140 years of US political speeches reveals more positive but increasingly polarized framing of immigration. Proceedings of the National Academy of Sci… [find](https://scholar.google.com/scholar?q=Dallas+Card%2C+Serina+Chang%2C+Chris+Becker%2C+Julia+Mendelsohn%2C+Rob+Voigt%2C+Leah+Boustan%2C+Ran+Abramitzky%2C+and+Dan+Jurafsky%2E+2022%2E+Computational+analysis+of+140+years+of+US+political+speeches+reveals+more+po)
3. Elena Frech, Niels D. Goet, and Simon Hug. 2021. Shirking and slacking in parliament. Legislative Studies Quarterly, 46(2):493–514. [find](https://scholar.google.com/scholar?q=Elena+Frech%2C+Niels+D%2E+Goet%2C+and+Simon+Hug%2E+2021%2E+Shirking+and+slacking+in+parliament%2E+Legislative+Studies+Quarterly%2C+46%282%29%3A493%E2%80%93514%2E)
4. Christoph Ivanusch. 2023. Issue competition in parliamentary speeches? a computer-based content analysis of legislative debates in the austrian nationalrat. Legislative Studies Quarterly, 49(1):203–232. [find](https://scholar.google.com/scholar?q=Christoph+Ivanusch%2E+2023%2E+Issue+competition+in+parliamentary+speeches%3F+a+computer%2Dbased+content+analysis+of+legislative+debates+in+the+austrian+nationalrat%2E+Legislative+Studies+Quarterly%2C+49%281%29%3A203%E2%80%9323)
5. Tatiana Lupacheva and Martin Mölder. 2024. A place to speak and be heard? Parliamentary speech and media attention in Estonia, 2011– 2019. Legislative Studies Quarterly, 49(4):905– 924. [find](https://scholar.google.com/scholar?q=Tatiana+Lupacheva+and+Martin+M%C3%B6lder%2E+2024%2E+A+place+to+speak+and+be+heard%3F+Parliamentary+speech+and+media+attention+in+Estonia%2C+2011%E2%80%93+2019%2E+Legislative+Studies+Quarterly%2C+49%284%29%3A905%E2%80%93+924%2E)
6. Corentin Poyet and Tapio Raunio. 2021. Reconsidering the electoral connection of speeches: The impact of electoral vulnerability on legislative speechmaking in a preferential voting system. Legislative Studies Quarterly, 46(4):1087–1114. First published online 27 September 2020. [find](https://scholar.google.com/scholar?q=Corentin+Poyet+and+Tapio+Raunio%2E+2021%2E+Reconsidering+the+electoral+connection+of+speeches%3A+The+impact+of+electoral+vulnerability+on+legislative+speechmaking+in+a+preferential+voting+system%2E+Legislativ)
7. Hiroki Sakaji, Yasutomo Kimura, Izumi Kiyoshi, and Hiroyasu Matsushima. 2019. Extraction of volitional utterances from Japanese local political corpus. The 2nd International Workshop on Cross-disciplinary Data Exchange and Collaboration, pages 24–29. [find](https://scholar.google.com/scholar?q=Hiroki+Sakaji%2C+Yasutomo+Kimura%2C+Izumi+Kiyoshi%2C+and+Hiroyasu+Matsushima%2E+2019%2E+Extraction+of+volitional+utterances+from+Japanese+local+political+corpus%2E+The+2nd+International+Workshop+on+Cross%2Ddiscipli)
8. Jonathan B. Slapin and Justin H. Kirkland. 2020. The sound of rebellion: Voting dissent and legislative speech in the UK house of commons. Legislative Studies Quarterly, 45(2):153–183. [find](https://scholar.google.com/scholar?q=Jonathan+B%2E+Slapin+and+Justin+H%2E+Kirkland%2E+2020%2E+The+sound+of+rebellion%3A+Voting+dissent+and+legislative+speech+in+the+UK+house+of+commons%2E+Legislative+Studies+Quarterly%2C+45%282%29%3A153%E2%80%93183%2E)
9. Keiichi Takamaru. 2013. What topics are discussed in a local assembly?: A text-mining analysis of the minutes of Utsunomiya City Assembly (in Japanese). The annual report of urban and regional economic studies, 13:162–176. [find](https://scholar.google.com/scholar?q=Keiichi+Takamaru%2E+2013%2E+What+topics+are+discussed+in+a+local+assembly%3F%3A+A+text%2Dmining+analysis+of+the+minutes+of+Utsunomiya+City+Assembly+%28in+Japanese%29%2E+The+annual+report+of+urban+and+regional+economi)
10. Keiichi Takamaru and Hokuto Ototake. 2023. An exploratory survey of dialects in minutes of local assemblies: A dialectological study using machine learning and xai (in Japanese). Studies in Dialects, 9:27–51. [find](https://scholar.google.com/scholar?q=Keiichi+Takamaru+and+Hokuto+Ototake%2E+2023%2E+An+exploratory+survey+of+dialects+in+minutes+of+local+assemblies%3A+A+dialectological+study+using+machine+learning+and+xai+%28in+Japanese%29%2E+Studies+in+Dialects%2C+)
11. Yuzu Uchida, Keiichi Takamaru, Hokuto Ototake, and Yasutomo Kimura. 2019. Visualization of activity of local assembly members based on log-likelihood ratio and political vocabulary ratio (in Japanese). Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, 31(2):662–671. 10. [find](https://scholar.google.com/scholar?q=Yuzu+Uchida%2C+Keiichi+Takamaru%2C+Hokuto+Ototake%2C+and+Yasutomo+Kimura%2E+2019%2E+Visualization+of+activity+of+local+assembly+members+based+on+log%2Dlikelihood+ratio+and+political+vocabulary+ratio+%28in+Japanese%29)
12. Language Resource References Tomaž Erjavec, Matyáš Kopp, Nikola Ljubešić, Taja Kuzman, Paul Rayson, Petya Osenova, Maciej Ogrodniczuk, Çağrı Çöltekin, Danijel Koržinek, Katja Meden, Jure Skubic, Peter Rupnik, Tommaso Agnoloni, José Aires, Starkaður Barkarson, Roberto Bartolini, Núria Bel, María Calz… [find](https://scholar.google.com/scholar?q=Language+Resource+References+Toma%C5%BE+Erjavec%2C+Maty%C3%A1%C5%A1+Kopp%2C+Nikola+Ljube%C5%A1i%C4%87%2C+Taja+Kuzman%2C+Paul+Rayson%2C+Petya+Osenova%2C+Maciej+Ogrodniczuk%2C+%C3%87a%C4%9Fr%C4%B1+%C3%87%C3%B6ltekin%2C+Danijel+Kor%C5%BEinek%2C+Katja+Meden%2C+Jure+Skubic%2C+Peter)
13. Yasutomo Kimura, Keiichi Takamaru, Takuma Tanaka, Akio Kobayashi, Hiroki Sakaji, Yuzu Uchida, Hokuto Ototake, and Shigeru Masuyama. 2016. Creating Japanese political corpus from local assembly minutes of 47 prefectures. In Proceedings of the 12th Workshop on Asian Language Resources, pages 78–85. [find](https://scholar.google.com/scholar?q=Yasutomo+Kimura%2C+Keiichi+Takamaru%2C+Takuma+Tanaka%2C+Akio+Kobayashi%2C+Hiroki+Sakaji%2C+Yuzu+Uchida%2C+Hokuto+Ototake%2C+and+Shigeru+Masuyama%2E+2016%2E+Creating+Japanese+political+corpus+from+local+assembly+minutes)
14. Eva Maxfield Brown and Nicholas Weber. 2022. Councils in action: Automating the curation of municipal governance data for research. Proceedings of the Association for Information Science and Technology, 59(1):23–31. [find](https://scholar.google.com/scholar?q=Eva+Maxfield+Brown+and+Nicholas+Weber%2E+2022%2E+Councils+in+action%3A+Automating+the+curation+of+municipal+governance+data+for+research%2E+Proceedings+of+the+Association+for+Information+Science+and+Technolog)
15. Keiyu Nagafuchi, Yasutomo Kimura, Kazuma Kadowaki, and Kenji Araki. 2024. Building a large corpus and pre-trained language models from national and local assembly minutes (in Japanese). Journal of Natural Language Processing, 31(2):707–732. [find](https://scholar.google.com/scholar?q=Keiyu+Nagafuchi%2C+Yasutomo+Kimura%2C+Kazuma+Kadowaki%2C+and+Kenji+Araki%2E+2024%2E+Building+a+large+corpus+and+pre%2Dtrained+language+models+from+national+and+local+assembly+minutes+%28in+Japanese%29%2E+Journal+of+Nat)
16. Hokuto Ototake, Hiroki Sakaji, Keiichi Takamaru, Akio Kobayashi, Yuzu Uchida, and Yasutomo Kimura. 2018. Web-based system for Japanese local political documents. International Journal of Web Information Systems, 14(3):357–371. [find](https://scholar.google.com/scholar?q=Hokuto+Ototake%2C+Hiroki+Sakaji%2C+Keiichi+Takamaru%2C+Akio+Kobayashi%2C+Yuzu+Uchida%2C+and+Yasutomo+Kimura%2E+2018%2E+Web%2Dbased+system+for+Japanese+local+political+documents%2E+International+Journal+of+Web+Informati)
17. Hokuto Ototake, Keiichi Takamaru, Yuzu Uchida, and Yasutomo Kimura. 2025. Overview of the local assembly minutes search system Giimiru v2 (in Japanese). In Proceedings of the 31st Annual Meeting of the Association for Natural Language Processing. [find](https://scholar.google.com/scholar?q=Hokuto+Ototake%2C+Keiichi+Takamaru%2C+Yuzu+Uchida%2C+and+Yasutomo+Kimura%2E+2025%2E+Overview+of+the+local+assembly+minutes+search+system+Giimiru+v2+%28in+Japanese%29%2E+In+Proceedings+of+the+31st+Annual+Meeting+of+th)
18. Takashi Tsutsui, Takuya Gaman, Takashi Oshiro, Kohei Sugawara, Takahiro Nagai, Hideyuki Shibuki, Yasutomo Kimura, and Tatsunori Mori. 2014. Construction of regional assembly minutes corpus and a proposal for annotation scheme for implementing political information system. Journal of Natural Language… [find](https://scholar.google.com/scholar?q=Takashi+Tsutsui%2C+Takuya+Gaman%2C+Takashi+Oshiro%2C+Kohei+Sugawara%2C+Takahiro+Nagai%2C+Hideyuki+Shibuki%2C+Yasutomo+Kimura%2C+and+Tatsunori+Mori%2E+2014%2E+Construction+of+regional+assembly+minutes+corpus+and+a+propo)