Text mining и история понятий

Text mining и история понятий

by Anton Sergeevich Kotov

Humanities, Social Sciences & Thought Computing & Cybersecurity UXApplied computingUXADigital Humanities
🎙 Anton Sergeevich Kotov 👥 321 📅 November 3, 2025 ⏱ 90 min 👁 68 📄 expert opinion 🧭 2026-08-16
Available in: English (current) Français

Keywords

text miningBegriffsgeschichteTeutonic OrderTF-IDFStylo

Summary

The seminar presents Anton Kotov’s research on applying text mining to the history of concepts, specifically the concept ‘Bund’ in 15th-century Teutonic Order texts. He introduces the theoretical framework of Reinhart Koselleck’s Begriffsgeschichte, focusing on the four characteristics of conceptual change: democratization, temporalization, ideologization, and politicization. Kotov then details the historical context of the Prussian Confederation, a union of estates against the Teutonic Order, and the evolution of the term ‘Bund’ from negative to positive connotations. He describes his methodological approach: using TF-IDF to extract bigrams, Stylo for style comparison, and statistical analysis to correlate term usage with metadata. The results show the effectiveness of text mining in tracing semantic shifts and understanding the influence of actors and events on meaning. The presentation includes a discussion with the discussant Alexander Klimov and the audience.

134 words

Critical Evaluation

Value of the Information & Strength of the Argument

The presentation offers valuable insights into the application of text mining to historical semantics, demonstrating a concrete case study. The argumentation is solid, grounded in both theoretical literature and empirical data. The speaker clearly explains the limitations of traditional approaches and the potential of computational methods. The discussion with the discussant adds depth, addressing methodological and interpretive challenges.

Scientific Rigor, Source Quality, Title Accuracy

The speaker cites relevant literature, including works by Koselleck, Richter, and Bikbov, and references his own recent publication. The sources are appropriate for the topic. The title accurately reflects the content. The presentation is rigorous in its methodology, though some conclusions are tentative. The video description provides links to the speaker’s publication and the institute’s Telegram channel, but no external sources are cited in the video itself.

140 words

Title / Content Match

The title accurately reflects the content, which focuses on applying text mining to the history of concepts.

Quality & Reliability

8/10

The presentation is based on a well-defined theoretical framework (Begriffsgeschichte) and a specific case study, with methodological transparency. The speaker is a PhD in history and demonstrates expertise. However, the video is a seminar recording with limited peer review, and the results are preliminary.

Key Moments

Markers derived by PSI from the transcript: the creator did not define chapters.

Cited Sources

Concurring Sources

  • Koselleck, R. (2004). Futures Past: On the Semantics of Historical Time — Theoretical basis for the history of concepts

Contribution & Novelties

The presentation contributes to the field by demonstrating a practical application of text mining to a historical case study, bridging the gap between theoretical frameworks like Begriffsgeschichte and computational methods. It shows how TF-IDF and stylometric analysis can reveal semantic shifts and actor influence, offering a replicable methodology for similar research.

Pour aller plus loin :

  • Begriffsgeschichte — Overview of the theoretical framework.
  • TF-IDF — Explanation of the term weighting technique.
  • Stylo — R package for stylometric analysis.

78 words

Radar Profile

The radar profile shows high scores in information quantity, quality, and reliability, with a slightly lower technical level, indicating a well-balanced presentation that is both informative and methodologically sound.

Reliability 8/10

💬 No comments were provided for analysis.