Kiran Garimella

Kiran Garimella · Tue, 21.02.2017

Our paper titled “Reducing Controversy by Connecting Opposing Views” was accepted at The 10th ACM International Conference on Web Search and Data Mining (WSDM 2017). I visited Cambridge, UK to present this work.

In the recent months, we’ve seen an ever-increasing polarization on social media, with real world examples such as the Brexit vote or the election of Donald Trump. Most often, such polarization is manifested on social media in the form of controversial discussions. Our paper tries to address this issue of increasing polarization by proposing algorithms that connect people with opposing viewpoints.  We designed and implemented this algorithm on Twitter datasets to show that our algorithm can do better than existing algorithms both in terms of speed and quality of recommendations.

This work was in collaboration with Aris Gionis (Aalto University, my PhD supervisor), Gianmarco De Francisci Morales (Qatar Computing Research Institute), and Michael Mathioudakis (Aalto University). The conference (WSDM) is one of the best in the areas of Data Mining, and it was a great honor to also receive the Best Student Research Paper Award  at the conference. This paper is an integral part of my PhD thesis and attending the conference was a great experience, since I could get valuable feed back on potential next steps as well as suggestions on improving the paper.

I wrote a short blog post on our group blog describing the paper, and it has received attention from the media (see Aalto press release).