Knowledge Enabled Approach to Predict the Location of Twitter Users

TitleKnowledge Enabled Approach to Predict the Location of Twitter Users
Publication TypeConference Proceedings
Year of Publication2015
AuthorsRevathy Krishnamurthy, Pavan Kapanipathi, Amit Sheth, Krishnaprasad Thirunarayan
EditorFabien Gandon, Marta Sabou, Harald Sack, Claudia d’Amato, Philippe Cudré-Mauroux, Antoine Zimmermann
Conference Name12th European Semantic Web Conference (ESWC 2015)
Series TitleThe Semantic Web. Latest Advances and New Domains: 12th European Semantic Web Conference, ESWC 2015, Portoroz, Slovenia, May 31—June 4, 2015. Proceedings
Volume9088
Pagination187-201
PublisherSpringer International Publishing
Conference LocationPortoroz, Slovenia
ISSN Number978-3-319-18817-1
KeywordsKnowledge graphs, Location, Location prediction, Prediction, Semantics, Semantics Social data, twitter, Wikipedia
Abstract

Knowledge bases have been used to improve performance in applications ranging from web search and event detection to entity recognition and disambiguation. More recently, knowledge bases have been used to analyze social data. A key challenge in social data analysis has been the identification of the geographic location of online users in a social network such as Twitter. Existing approaches to predict the loca- tion of users, based on their tweets, rely solely on social media features or probabilistic language models. These approaches are supervised and require large training dataset of geo-tagged tweets to build their models. As most Twitter users are reluctant to publish their location, the col- lection of geo-tagged tweets is a time intensive process. To address this issue, we present an alternative, knowledge-based approach to predict a Twitter user’s location at the city level. Our approach utilizes Wikipedia as a source of knowledge base by exploiting its hyperlink structure. Our experiments, on a publicly available dataset demonstrate an improve- ment of 3% in the accuracy of prediction and a 16% reduction in the average error distance, over the state of the art supervised techniques.

DOI10.1007/978-3-319-18818-8
Related Files: