Doing research online (by SAGE Research Methods): A Mixed-Method to Explain How Extreme Opinions Infiltrate Online Discussions

Andrei was interviewed by SAGE Research Methods for the Doing Online Research case study collection. He discusses a case study using qualitative approaches and machine learning to map online problematic content, including blending digital ethnography and advanced machine learning, data collection, dataset augmentation, results, lessons learned, and recommendations.

There is a strong focus on the interdisciplinarity of the work – a collaboration with digital communication scientists Amelia Johns and Francesco Bailo, literary scientist Emily Booth, and computer scientists Quyu Kong and Marian-Andrei Rizoiu.

The interview is based on our recent paper published in ICWSM 2022, where we propose a complete solution to accelerate the qualitative analysis of problematic online speech — with a specific focus on opinions emerging from online communities — by leveraging machine learning algorithms.

Paper citation:

Quyu Kong, Emily Booth, Francesco Bailo, Amelia Johns, and Marian-Andrei 
Rizoiu. Slipping to the Extreme: A Mixed Method to Explain How Extreme 
Opinions Infiltrate Online Discussions. In AAAI International Conference 
on Web and Social Media (Vol. 16, pp. 524–535), 2022.

(see full paper here: https://arxiv.org/pdf/2109.00302.pdf, and a full description of the research in this blogpost)

Acknowledgements:
This research was partially funded by the University of Technology of Sydney through a cross-faculty grant, Facebook Research under the Content Policy Research Initiative, and the Commonwealth of Australia (represented by the Defence Science and Technology Group) through a Defence Science Partnerships Agreement.