Dialogue Analysis Using a Text Mining Approach: Case Study of Hirono Town

Abstract

This case study examined public participation regarding reconstruction of the disaster-affected areas in the Fukushima Prefecture of Japan following the Great East Japan Earthquake in March 2011. The study aimed at (i) identifying the topics discussed and shared by the residents, and (ii) revealing the contribution of the media to ensuring information transparency in the regional planning process. We applied text mining—in particular, correspondence analysis—to (a) the text data from dialogue sessions with local residents and (b) newspaper articles that appeared in a nation-wide newspaper in order to identify the similarities and differences between the topics discussed by session participants and those that appeared in newspaper articles. It turned out that the newspaper articles did not adequately address some important topics discussed in the dialogues. This implies that the coverage by the mass media has much room for improvement in the transparency of the information it provides and supporting the development and implementation of administrative agendas involving citizens and municipalities.