Inferring the location of authors from words in their texts
This addresses a need in computational dialectology for geographically bound text analysis, but it is incremental as it builds on existing methods for location inference.
The paper tackled the problem of inferring author locations from text when explicit geographic labels are absent, by learning location-indicating words from annotated microblog posts and modeling them with Gaussian distributions, achieving results applied to Swedish language data.
For the purposes of computational dialectology or other geographically bound text analysis tasks, texts must be annotated with their or their authors' location. Many texts are locatable through explicit labels but most have no explicit annotation of place. This paper describes a series of experiments to determine how positionally annotated microblog posts can be used to learn location-indicating words which then can be used to locate blog texts and their authors. A Gaussian distribution is used to model the locational qualities of words. We introduce the notion of placeness to describe how locational words are. We find that modelling word distributions to account for several locations and thus several Gaussian distributions per word, defining a filter which picks out words with high placeness based on their local distributional context, and aggregating locational information in a centroid for each text gives the most useful results. The results are applied to data in the Swedish language.