The paper proposes an LLM-based pipeline to extract and cluster diary-writing purposes from Soviet-era diaries, finding GPT-4o and o1-mini most accurate.
and others: The Impact of Digital Analysis and Large Language Models in Digital Humanity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do LLMs Understand Why We Write Diaries? A Method for Purpose Extraction and Clustering
The paper proposes an LLM-based pipeline to extract and cluster diary-writing purposes from Soviet-era diaries, finding GPT-4o and o1-mini most accurate.