Matches in ScholarlyData for { <https://w3id.org/scholarlydata/inproceedings/eswc2015/paper/research/89> ?p ?o. }
Showing items 1 to 15 of
15
with 100 items per page.
- 89 creator amit-sheth.
- 89 creator krishnaprasad-thirunarayan.
- 89 creator pavan-kapanipathi.
- 89 creator revathy-krishnamurthy.
- 89 type InProceedings.
- 89 label "Knowledge Enabled Approach to Predict the Location of Twitter Users".
- 89 sameAs 89.
- 89 abstract "The use of knowledge bases have been shown 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 address challenges in analyzing social data. A key challenge in this domain has been that of identifying the geographic footprint of online users in a social network such as Twitter. Existing approaches to predict the location of users, based on their tweets, solely rely on social media features or probabilistic language models. These approaches are purely data-driven and require large training dataset of geo-tagged tweets to build statistical models that predict the location of a user. As most Twitter users are reluctant to publish their location, the collection 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. We utilize Wikipedia as the source of our knowledge base by exploiting its hyperlink structure which alleviates the dependence on training data set. Our experiments, on a publicly available dataset demonstrate an improvement of 3\% in the accuracy of prediction, over the state of the art supervised techniques.".
- 89 hasAuthorList authorList.
- 89 isPartOf proceedings.
- 89 keyword "Location Prediction".
- 89 keyword "Semantics".
- 89 keyword "Twitter".
- 89 keyword "Wikipedia".
- 89 title "Knowledge Enabled Approach to Predict the Location of Twitter Users".