Methodology
Introduction
This application presents a historical and current overview of the discourse around urban sustainability in Zürich.
Our goals are to enable everyone in Zürich to:
Stay informed about what is happening and what has happened in urban sustainability
Find the right organizations to connect to to become active.
To create this application, we built an automated process, which reads through many years worth of media data from the year 2012 on.
Our computers:
Split newspaper articles into paragraphs
Filter out paragraphs that are related to an urban sustainability target. Currently implemented is Sustainable transport systems (> SDG 11.2 )
Identify what discourse topics occur in these paragraphs related to a sustainability target
Identify what organizations occur in these paragraphs
Organizations can be from all societal sectors (administration, private sector, civil society, politics, science)
Identify the stances organizations take in the media regarding key policy issues (not yet implemented)
Paragraph Splitting
Split newspaper articles into paragraphs for further analysis.
Filtering
Filter out paragraphs related to urban sustainability targets.
Extraction
Identify discourse topics and organizations mentioned related to sustainability targets.
More Details
Find out more technical details about the processing pipeline, including a publication with evaluation metrics and open sourced classification models at the link below:
Media Data
For this project, use was made of media data made available via Swissdox@LiRI by the Linguistic Research Infrastructure of the University of Zurich.
Team
Created by a project team at the Digital Society Initiative of the University of Zürich: Mario Angst, Neitah Noemi Müller, Viviane Walker, Myriam Pham-Truffert.
Funding
This project was financed as part of a bridge postdoc grant by the DIZH.
Get in touch
We are able to provide API access to the endpoints of our processing pipeline feeding this application for anyone wanting to build on it (we are not allowed to share the raw data).
mario.angst@uzh.ch