The Discourse Processing Lab is involved in a number of projects:
- a study of online news comments
- a project on detecting fake news and misinformation
- the Gender Gap Tracker
Moderating online news comments
We are interested in the language of online news comments. This is a corpus and computational project.
- Corpus 1: SOCC, the SFU Opinion and Comments Corpus. More than 630,000 comments posted on the site of The Globe and Mail. Publicly available.
- Corpus 2: the Constructive Comments Corpus, 12,000 comments annotated for constructiveness.
- Computational work: a system to moderate comments, identifying constructive comments -- those that contribute to the conversation, creating civil dialogue.
Detecting misinformation and fake news
We are working on methods to identify whether a news article is an instance of misinformation. Work in progress includes:
- MisInfoText, a dataset of fact-checked news articles.
- A system to detect fake news online.
The Gender Gap Tracker
The Gender Gap Tracker, developed within our lab and in collaboration with Informed Opinions, monitors the proportion of women and men quoted in news stories in mainstream Canadian media (in English).
We have had great media coverage for this tool. You can check the Conversation piece for an explanation of the tracker, and see other media mentions:
- Tracking the gender gap in Canadian media (The Conversation)
- Online tool gives media outlets incentive to achieve gender parity (The Toronto Star)
- SFU partners with Informed Opinions to create Gender Gap Tracker (SFU News)
- In numbers there is strength (Ottawa Citizen and Montreal Gazette)
We have also produced a research-oriented dashboard, with the ability to analyze one text at a time and with a monthly analysis of topics and gender.