Peijing Mou a
a University of California, Los Angeles. United States of America
This article introduces (Un)Natural Language, an art software and an interactive online archive that documents and examines how words make worlds by capturing the underlying ecological threats in government project documents. The project weaves together ecology, linguistics, and computational technology to offer a new analytical lens for language use in urbanization. Through a custom-labeled dataset and a fine-tuned BERT model, the system classifies individual sentences in project appraisal documents, returning visualized analyses that reveal patterns of pro-growth and ecologically detrimental discourse. Merging net art, environmental activism, and natural language processing, (Un)Natural Language offers a novel framework for interpreting public documents by uncovering hidden narratives of extractivism and economic expansion. The article begins by outlining the context and concepts of the work, followed by a description of its operation, design, and technical implementation. It concludes with reflections on the project’s contributions to ecolinguistics, machine learning, and net art. The project reclaims computation as a space for reflection rather than control—inviting viewers to rethink the language shaping our ecological futures.
Peijing Mou a
a University of California, Los Angeles. United States of America
(Un)Natural language: An art software captures underlying ecological threats in documents . (2026). In Degrowth Journal (Vol. 3). https://doi.org/10.36399/Degrowth.003.02.09
“(Un)Natural Language: An Art Software Captures Underlying Ecological Threats in Documents .” Degrowth Journal, vol. 3, Jan. 2026, https://doi.org/10.36399/Degrowth.003.02.09.
“(Un)Natural Language: An Art Software Captures Underlying Ecological Threats in Documents .” 2026. In Degrowth Journal, vol. 3. https://doi.org/10.36399/Degrowth.003.02.09.
“(Un)Natural language: An art software captures underlying ecological threats in documents ”(2026) Degrowth Journal. Available at: https://doi.org/10.36399/Degrowth.003.02.09.
Information
Credits
Transcription