The paper entitled “bias goggles - Graph-based Computation of the Bias of Web Domains through the Eyes of Users” that was presented by Panagiotis Papadakos, received the Best Long Paper Award at the 42th European Conference on Information Retrieval (ECIR 2020 - Lisbon, Portugal, April 14-17, 2020).
This work introduces the bias goggles model, that allows the computation of the bias characteristics of web domains to user-defined concepts, based on the structure of the web graph. The bias scores are computed by exploiting well-known propagation models, and the introduced Biased-PR PageRank algorithm that models various behaviors of biased surfers. A preliminary evaluation over a subset of the greek web graph shows the applicability of the model even in real-time for small graphs, and showcases rather promising and interesting results. A constantly evolving prototype of the bias goggles system is readily available at http://pangaia.ics.forth.gr/bias-goggles/
The authors of the paper are Panagiotis Papadakos, a post-doctoral researcher and member of the Information Systems Laboratory of the Institute of Computer Science, Foundation for Research and Technology – Hellas (FORTH) and visiting lecturer at the Computer Science Department of University of Crete, and Giannis Konstantakis, an undergraduate student during the paper submission time in the Computer Science Department of University of Crete.
