Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987105342> ?p ?o ?g. }
- W2987105342 abstract "Prior research has shown that geolocation can be substantially improved by including user network information. While effective, it suffers from the curse of dimensionality, since networks are usually represented as sparse adjacency matrices of connections, which grow exponentially with the number of users. In order to incorporate this information, we therefore need to limit the network size, in turn limiting performance and risking sample bias. In this paper, we address these limitations by instead using dense network representations. We explore two methods to learn continuous node representations from either 1) the network structure with node2vec (Grover and Leskovec, 2016), or 2) textual user mentions via doc2vec (Le and Mikolov, 2014). We combine both methods with input from social media posts in an attention-based convolutional neural network and evaluate the contribution of each component on geolocation performance. Our method enables us to incorporate arbitrarily large networks in a fixed-length vector, without limiting the network size. Our models achieve competitive results with similar state-of-the-art methods, but with much fewer model parameters, while being applicable to networks of virtually any size." @default.
- W2987105342 created "2019-11-22" @default.
- W2987105342 creator A5029055892 @default.
- W2987105342 creator A5084505122 @default.
- W2987105342 date "2019-01-01" @default.
- W2987105342 modified "2023-09-28" @default.
- W2987105342 title "Dense Node Representation for Geolocation" @default.
- W2987105342 cites W1968625547 @default.
- W2987105342 cites W2111216449 @default.
- W2987105342 cites W2123294561 @default.
- W2987105342 cites W2131744502 @default.
- W2987105342 cites W2137435333 @default.
- W2987105342 cites W2141599568 @default.
- W2987105342 cites W2142191319 @default.
- W2987105342 cites W2142889507 @default.
- W2987105342 cites W2153579005 @default.
- W2987105342 cites W2165442870 @default.
- W2987105342 cites W2250457198 @default.
- W2987105342 cites W2606615323 @default.
- W2987105342 cites W2741226448 @default.
- W2987105342 cites W2757169544 @default.
- W2987105342 cites W2757981529 @default.
- W2987105342 cites W2776671924 @default.
- W2987105342 cites W2908841270 @default.
- W2987105342 cites W2950577311 @default.
- W2987105342 cites W2954211513 @default.
- W2987105342 cites W2962756421 @default.
- W2987105342 cites W2963631600 @default.
- W2987105342 cites W2963666326 @default.
- W2987105342 cites W2963791934 @default.
- W2987105342 cites W2964347896 @default.
- W2987105342 cites W2986978353 @default.
- W2987105342 cites W2989033225 @default.
- W2987105342 doi "https://doi.org/10.18653/v1/d19-5529" @default.
- W2987105342 hasPublicationYear "2019" @default.
- W2987105342 type Work @default.
- W2987105342 sameAs 2987105342 @default.
- W2987105342 citedByCount "3" @default.
- W2987105342 countsByYear W29871053422019 @default.
- W2987105342 countsByYear W29871053422021 @default.
- W2987105342 crossrefType "proceedings-article" @default.
- W2987105342 hasAuthorship W2987105342A5029055892 @default.
- W2987105342 hasAuthorship W2987105342A5084505122 @default.
- W2987105342 hasBestOaLocation W29871053421 @default.
- W2987105342 hasConcept C110484373 @default.
- W2987105342 hasConcept C111030470 @default.
- W2987105342 hasConcept C11413529 @default.
- W2987105342 hasConcept C119857082 @default.
- W2987105342 hasConcept C124101348 @default.
- W2987105342 hasConcept C127413603 @default.
- W2987105342 hasConcept C134306372 @default.
- W2987105342 hasConcept C136764020 @default.
- W2987105342 hasConcept C151201525 @default.
- W2987105342 hasConcept C17744445 @default.
- W2987105342 hasConcept C188198153 @default.
- W2987105342 hasConcept C199539241 @default.
- W2987105342 hasConcept C22041718 @default.
- W2987105342 hasConcept C2776359362 @default.
- W2987105342 hasConcept C33923547 @default.
- W2987105342 hasConcept C41008148 @default.
- W2987105342 hasConcept C62611344 @default.
- W2987105342 hasConcept C66938386 @default.
- W2987105342 hasConcept C78519656 @default.
- W2987105342 hasConcept C80444323 @default.
- W2987105342 hasConcept C94625758 @default.
- W2987105342 hasConceptScore W2987105342C110484373 @default.
- W2987105342 hasConceptScore W2987105342C111030470 @default.
- W2987105342 hasConceptScore W2987105342C11413529 @default.
- W2987105342 hasConceptScore W2987105342C119857082 @default.
- W2987105342 hasConceptScore W2987105342C124101348 @default.
- W2987105342 hasConceptScore W2987105342C127413603 @default.
- W2987105342 hasConceptScore W2987105342C134306372 @default.
- W2987105342 hasConceptScore W2987105342C136764020 @default.
- W2987105342 hasConceptScore W2987105342C151201525 @default.
- W2987105342 hasConceptScore W2987105342C17744445 @default.
- W2987105342 hasConceptScore W2987105342C188198153 @default.
- W2987105342 hasConceptScore W2987105342C199539241 @default.
- W2987105342 hasConceptScore W2987105342C22041718 @default.
- W2987105342 hasConceptScore W2987105342C2776359362 @default.
- W2987105342 hasConceptScore W2987105342C33923547 @default.
- W2987105342 hasConceptScore W2987105342C41008148 @default.
- W2987105342 hasConceptScore W2987105342C62611344 @default.
- W2987105342 hasConceptScore W2987105342C66938386 @default.
- W2987105342 hasConceptScore W2987105342C78519656 @default.
- W2987105342 hasConceptScore W2987105342C80444323 @default.
- W2987105342 hasConceptScore W2987105342C94625758 @default.
- W2987105342 hasLocation W29871053421 @default.
- W2987105342 hasOpenAccess W2987105342 @default.
- W2987105342 hasPrimaryLocation W29871053421 @default.
- W2987105342 hasRelatedWork W1544177091 @default.
- W2987105342 hasRelatedWork W2360309522 @default.
- W2987105342 hasRelatedWork W2735265293 @default.
- W2987105342 hasRelatedWork W2767460050 @default.
- W2987105342 hasRelatedWork W2771035597 @default.
- W2987105342 hasRelatedWork W2796988304 @default.
- W2987105342 hasRelatedWork W2798756592 @default.
- W2987105342 hasRelatedWork W2809219720 @default.
- W2987105342 hasRelatedWork W2908027240 @default.
- W2987105342 hasRelatedWork W2910109410 @default.
- W2987105342 hasRelatedWork W2940882578 @default.