AI Augmented Approach to Identify Shared Ideas from Large Format Public Consultation

Public data, contributed by citizens, stakeholders and other potentially affected parties, are becoming increasingly used to collect the shared ideas of a wider community. Having collected large quantities text data from public consultation, challenge is often how interpret dataset without resorting lengthy time-consuming manual analysis. One approach gaining ground use Natural Language Processing (NLP) technologies. Based on machine learning technology applied analysis human natural languages, NLP provides opportunity automate for volumes texts at scale that would be virtually impossible analyse manually. Using toolkits, this paper presents novel identifying visualising format consultation. The analyses grammatical structures discover sentences comprising subject + verb object express options. In particular, identified extracting noun, verb, adjective phrases clauses subjects objects, which then categorised urban infrastructure categories terms. results visualised in hierarchy chart word tree using cascade views. illustrated consultation exercise called “Share an Idea” undertaken Christchurch, New Zealand, after 2011 earthquake. has potential upscale participation identify design values associated qualities wide range initiatives including planning.