HisRect: Features from historical visits and recent tweet for co-location judgement

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

doi:10.1109/ICDE48307.2020.00236

HisRect: Features from historical visits and recent tweet for co-location judgement

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

Research output: Contribution to book/anthology/report/conference proceeding › Conference abstract in proceeding › Research › peer-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.

Original language	English
Title of host publication	Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020
Number of pages	2
Publisher	IEEE (Institute of Electrical and Electronics Engineers)
Publication date	Apr 2020
Pages	2034-2035
Article number	9101767
ISBN (Print)	978-1-7281-2904-4
ISBN (Electronic)	978-1-7281-2903-7
DOIs	https://doi.org/10.1109/ICDE48307.2020.00236
Publication status	Published - Apr 2020
Event	36th IEEE International Conference on Data Engineering, ICDE 2020 - Dallas, United States Duration: 20 Apr 2020 → 24 Apr 2020

Conference

Conference	36th IEEE International Conference on Data Engineering, ICDE 2020
Country/Territory	United States
City	Dallas
Period	20/04/2020 → 24/04/2020

Series	Proceedings of the International Conference on Data Engineering
ISSN	1063-6382

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Access to Document

10.1109/ICDE48307.2020.00236

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inbook{1e9b556a1d9c4edbac1cc1d2d55c0126,

title = "HisRect: Features from historical visits and recent tweet for co-location judgement",

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.",

author = "Pengfei Li and Hua Lu and Qian Zheng and Shijian Li and Gang Pan",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 36th IEEE International Conference on Data Engineering, ICDE 2020 ; Conference date: 20-04-2020 Through 24-04-2020",

year = "2020",

month = apr,

doi = "10.1109/ICDE48307.2020.00236",

language = "English",

isbn = "978-1-7281-2904-4",

series = "Proceedings of the International Conference on Data Engineering",

publisher = "IEEE (Institute of Electrical and Electronics Engineers)",

pages = "2034--2035",

booktitle = "Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020",

address = "United States",

}

Li, P, Lu, H, Zheng, Q, Li, S & Pan, G 2020, HisRect: Features from historical visits and recent tweet for co-location judgement. in Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020., 9101767, IEEE (Institute of Electrical and Electronics Engineers), Proceedings of the International Conference on Data Engineering, pp. 2034-2035, 36th IEEE International Conference on Data Engineering, ICDE 2020, Dallas, United States, 20/04/2020. https://doi.org/10.1109/ICDE48307.2020.00236

HisRect: Features from historical visits and recent tweet for co-location judgement. / Li, Pengfei; Lu, Hua; Zheng, Qian et al.
Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020. IEEE (Institute of Electrical and Electronics Engineers), 2020. p. 2034-2035 9101767 (Proceedings of the International Conference on Data Engineering).

Research output: Contribution to book/anthology/report/conference proceeding › Conference abstract in proceeding › Research › peer-review

TY - ABST

T1 - HisRect

T2 - 36th IEEE International Conference on Data Engineering, ICDE 2020

AU - Li, Pengfei

AU - Lu, Hua

AU - Zheng, Qian

AU - Li, Shijian

AU - Pan, Gang

PY - 2020/4

Y1 - 2020/4

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85085857665&partnerID=8YFLogxK

U2 - 10.1109/ICDE48307.2020.00236

DO - 10.1109/ICDE48307.2020.00236

M3 - Conference abstract in proceeding

AN - SCOPUS:85085857665

SN - 978-1-7281-2904-4

T3 - Proceedings of the International Conference on Data Engineering

SP - 2034

EP - 2035

BT - Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020

PB - IEEE (Institute of Electrical and Electronics Engineers)

Y2 - 20 April 2020 through 24 April 2020

ER -

Li P, Lu H, Zheng Q, Li S, Pan G. HisRect: Features from historical visits and recent tweet for co-location judgement. In Proceedings - 2020 IEEE 36th International Conference on Data Engineering, ICDE 2020. IEEE (Institute of Electrical and Electronics Engineers). 2020. p. 2034-2035. 9101767. (Proceedings of the International Conference on Data Engineering). doi: 10.1109/ICDE48307.2020.00236

HisRect: Features from historical visits and recent tweet for co-location judgement

Abstract

Conference

Bibliographical note

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this