The phrase shi towa nani ka (what is poetry?) has recurred frequently in the rhetoric of modern Japanese poetry and poetics, and tracing its history invites a reliance on multiple methodologies in the early twenty-first century. The present study juxtaposes and analyzes critical and poetic works that appear as results in a search for the phrase shi towa nani ka in the database of the National Diet Library of Japan. These various works, as this essay finds, generally do not refer to each other explicitly: despite the common textual element, it seems there is little connection—whether via allusion, citation, critical rejoinder, or appreciative affirmation—between the search results. This assertion, however, invites methodological reflections: should one expect database search results to be discursively related? It should be emphasized that the present study is not an essay in distant reading—the approach to data here is not obviously algorithm-driven, nor is the dataset "big" (although the essay includes reflections on the subject of scale). Nor is it a concept history in the usual acceptation of that term. But the approach taken here—defining and analyzing a corpus of texts that share a common phrasal element—has implications for a distant reading approach to conceptual history, a topic broached in the final paragraphs of the essay.
We discuss a novel approach to Premodern Japanese Language Pedagogy (PJLP) with potential applications in other languages and fields. Drawing inspiration from grassroots initiatives such as the DIY and Maker movements, this paper advocates for an approach to AI in Education that fosters instructional and student agency over the pedagogical process. Specifically, we discuss a tutoring framework for textual analysis in the context of a graduate seminar in premodern Japanese literature, as well as a bilingual interactive dictionary and a conversational partner created for a language course in Classical Japanese. Created through prompt engineering as custom instances of a Large Language Model (LLM), these three tools are designed to counteract the tendency of out-of-the-box LLMs to either bypass student effort through over-explanation or misguide learners via hallucinations. To illustrate how this approach can promote active comprehension and pedagogical alignment, we provide transcripts (logs) of actual exchanges, sample instructions (system prompts), and guidance for instructors curious about exploring this approach in a variety of fields (starter kit).
The phrase shi towa nani ka (what is poetry?) has recurred frequently in the rhetoric of modern Japanese poetry and poetics, and tracing its history invites a reliance on multiple methodologies in the early twenty-first century. The present study juxtaposes and analyzes critical and poetic works that appear as results in a search for the phrase shi towa nani ka in the database of the National Diet Library of Japan. These various works, as this essay finds, generally do not refer to each other explicitly: despite the common textual element, it seems there is little connection—whether via allusion, citation, critical rejoinder, or appreciative affirmation—between the search results. This assertion, however, invites methodological reflections: should one expect database search results to be discursively related? It should be emphasized that the present study is not an essay in distant reading—the approach to data here is not obviously algorithm-driven, nor is the dataset "big" (although the essay includes reflections on the subject of scale). Nor is it a concept history in the usual acceptation of that term. But the approach taken here—defining and analyzing a corpus of texts that share a common phrasal element—has implications for a distant reading approach to conceptual history, a topic broached in the final paragraphs of the essay.
