HisRect: Features from Historical Visits and Recent Tweet for Co-Location Judgement

Pengfei Li, Hua Lu, Qian Zheng, Shijian Li, Gang Pan

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

Abstract

This study explores the problem of co-location judgement, i.e., to decide whether two Twitter users are co-located at some point-of-interest (POI). We extract novel features, named HisRect, from users' historical visits and recent tweets: The former has impact on where a user visits in general, whereas the latter gives more hints about where a user is currently. To alleviate the issue of data scarcity, a semi-supervised learning (SSL) framework is designed to extract HisRect features. Moreover, we use an embedding neural network layer to decide co-location based on the difference between two users' His-Rect features. Extensive experiments on real Twitter data suggest that our HisRect features and SSL framework are highly effective at deciding co-locations.
OriginalsprogEngelsk
TitelProceedings 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020, Dallas, TX, USA, April 20-24, 2020
Antal sider2
ForlagIEEE
Publikationsdato2020
Sider2034-2035
ISBN (Elektronisk)978-1-7281-2903-7, 978-1-7281-2904-4
DOI
StatusUdgivet - 2020
Udgivet eksterntJa
Begivenhed36th IEEE International Conference on Data Engineering - Online, Dallas, USA
Varighed: 20 apr. 202024 apr. 2020
Konferencens nummer: 36
https://www.utdallas.edu/icde/

Konference

Konference36th IEEE International Conference on Data Engineering
Nummer36
LokationOnline
LandUSA
ByDallas
Periode20/04/202024/04/2020
AndetOnline konference
Internetadresse
NavnProceedings of the International Conference on Data Engineering
ISSN1063-6382

Citer dette