A Toolkit for Analyzing Online Conversations for Solutions Based Policy Development

The Intergovernmental Panel on Climate Change (IPCC) 2014 Synthesis Report states that “substantial [greenhouse gas] emissions reductions over the next few decades can reduce climate risks in the 21st century and beyond, increase prospects for effective adaptation, reduce the costs and challenges of mitigation in the longer term, and contribute to climate-resilient pathways for sustainable development.” Yet, despite this imperative, energy conversations in Canada have become fragmented and polarized (Kevins & Soroka, 2018; Lefsrud et al., 2015) for renewable (Hoberg, 2019) and non-renewable energy (Hoberg, 2018) alike. This research examines these fragmented narratives by developing (a) several curated data sets for use in text-analysis research, (b) automated methods and tools for multi-faceted document-similarity estimation and document clustering, and (c) thematic mapping and evolution analysis of textual data streams for incumbent energy sources (hydro, oil and gas, coal, nuclear) and nonincumbent energy sources (solar, wind, geothermal, biomass) by geography. Our objective is understanding (d) the vocabularies, speakers, interlinking of conversations, and associated topics/themes by geography that can (e) draw these narratives together to support solutions-based policy conversations

Faculty Supervisor:

Lianne Lefsrud;Eleni Stroulia;Denilson Barbosa;Joel Gehman

Student:

Candelario Alfonso Gutierrez Gutierrez;Andrea Whittaker

Partner:

Canadian Energy & Climate Nexus

Discipline:

Computer science

Sector:

Education

University:

University of Alberta