A collaboration platform for enabling industrial symbiosis: Towards creating a self-learning waste-to-resource database for recommending industrial symbiosis transactions using text analytics

Abstract

Industrial Symbiosis (IS) adopts a collaborative approach, which aims to re-channel resources – traditionally considered spent and non-productive – towards alternative value-adding pathways. Empirically, the concept of IS has been rapidly implemented in practice through a facilitated approach, whereby businesses are engaged and “match-made” via a facilitating body. While recommending alternative pathways for companies to establish IS-based transactions is a long-standing practice, recent technological advancement has shifted the nature of this task from one that is based purely on human intellect and reasoning, towards one which leverages intelligent recommendation algorithms to provide relevant suggestions. Traditionally, these recommendation engines rely on manually populated knowledge bases that are not only labor-intensive to build but also costly to maintain. This work presents the creation of a self-learning waste-to-resource database supporting an IS recommendation system by utilizing text analytics techniques. We further demonstrate its practical application to support IS facilitating bodies in their core activity.