Algorithmic ‘Idea’ clustering via natural language processing

Niall Curtis


Supervised by Alun D Preece; Moderated by Steven Arthur

During my industry year, the company I worked for produced web software for other companies in order to enable them to conduct challenge-based innovation, through crowdsourcing ideas from their employees. In many cases, a single challenge might amass a large number of idea contributions from staff, which is a problem for a small staff team to process manually. This project aims to address part of this problem through creating a system that uses advanced techniques (such as natural language processing) to automatically process and generate clusters of ideas based on topic similarity in order to allow staff to more readily navigate and consume the data collected in their challenges. I propose the project could include further work - such as providing controls around idea affinity to change the granularity of the outputs. The project would also focus on HCI for the client, with a well-justified user experience/interface to maximise usability and usefulness for users dealing with a large dataset.

Initial Plan (03/02/2020) [Zip Archive]

Final Report (15/05/2020) [Zip Archive]

Publication Form