MetaFraming: A Methodology for Democratizing Heritage Interpretation through Wiki Surveys

This paper introduces MetaFraming, a participatory methodology using three distinct AI pipelines (powered by GPT-3.5) to democratize heritage study. The first generates hundreds of 'seed' propositions for a wiki survey from background research, controlled for tone and topic. The second interprets user-submitted comments by providing the LLM with crucial context about their preceding interactions. The third automatically codes comments for sentiment and topics, which speeds up qualitative analysis and aids in abuse detection. The methodology was developed through a case study on Le Corbusier’s Unité d’habitation. Read the full paper here ↗.