Toponym disambiguation in online social network profiles

Abstract

In online social networks individuals are given the option to reveal on their online profiles some personal information about themselves including, among others, their home location that, if specified, is typically referred to with a toponym. A toponym disclosed by an individual on her profile, or self-reported toponym (e.g., "London"), is often ambiguous and may be interpreted as the name of different geographic locations ("London, U.K.", "London, Ontario, Canada", "London, Arkansas, USA"). The determination of the right interpretation of a self-reported toponym is challenging because the profile of an individual usually lacks the contextual information that can be used to disambiguate the toponym. In this paper, we propose LocusRank, an algorithm for the disambiguation (or resolution) of the self-reported toponyms in online social network profiles. More precisely, LocusRank chooses the right interpretation of a self-reported toponym of an individual by using the (possibly ambiguous) self-reported toponyms of her friends. Besides, LocusRank can also be used to infer with good accuracy the home location of profiles that do not even have a self-reported toponym. We evaluated LocusRank with good results on a dataset of profiles obtained from two real social networks, namely Flickr and LiveJournal.