Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]

Pengfei Li, Hua Lu, Nattiya Kanhabua, Sha Zhao, Gang Pan

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceabstrakt i proceedingForskningpeer review

Resumé

This study explores the problem of inferring locations for individual tweets. We scrutinize Twitter user timelines in a novel fashion. First of all, we split each user's tweet timeline temporally into a number of clusters, each tending to imply a distinct location. Subsequently, we adapt machine learning models to our setting and design classifiers that classify each tweet cluster into one of the pre-defined location classes at the city level. Extensive experiments on a large set of real Twitter data suggest that our models are effective at inferring locations for non-geotagged tweets and outperform the state-of-the-art approaches significantly in terms of inference accuracy.
OriginalsprogEngelsk
TitelProceedings of the 35th IEEE International Conference on Data Engineering (ICDE)
Publikationsdato2019
Sider2111-2112
StatusUdgivet - 2019

Fingerprint

Learning systems
Classifiers
Experiments

Citer dette

Li, P., Lu, H., Kanhabua, N., Zhao, S., & Pan, G. (2019). Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]. I Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE) (s. 2111-2112)
Li, Pengfei ; Lu, Hua ; Kanhabua, Nattiya ; Zhao, Sha ; Pan, Gang. / Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]. Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE). 2019. s. 2111-2112
@inbook{7e230e258e07401d90027b2db064eddf,
title = "Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]",
abstract = "This study explores the problem of inferring locations for individual tweets. We scrutinize Twitter user timelines in a novel fashion. First of all, we split each user's tweet timeline temporally into a number of clusters, each tending to imply a distinct location. Subsequently, we adapt machine learning models to our setting and design classifiers that classify each tweet cluster into one of the pre-defined location classes at the city level. Extensive experiments on a large set of real Twitter data suggest that our models are effective at inferring locations for non-geotagged tweets and outperform the state-of-the-art approaches significantly in terms of inference accuracy.",
author = "Pengfei Li and Hua Lu and Nattiya Kanhabua and Sha Zhao and Gang Pan",
year = "2019",
language = "English",
pages = "2111--2112",
booktitle = "Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE)",

}

Li, P, Lu, H, Kanhabua, N, Zhao, S & Pan, G 2019, Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]. i Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE). s. 2111-2112.

Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]. / Li, Pengfei; Lu, Hua; Kanhabua, Nattiya; Zhao, Sha; Pan, Gang.

Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE). 2019. s. 2111-2112.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceabstrakt i proceedingForskningpeer review

TY - ABST

T1 - Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]

AU - Li, Pengfei

AU - Lu, Hua

AU - Kanhabua, Nattiya

AU - Zhao, Sha

AU - Pan, Gang

PY - 2019

Y1 - 2019

N2 - This study explores the problem of inferring locations for individual tweets. We scrutinize Twitter user timelines in a novel fashion. First of all, we split each user's tweet timeline temporally into a number of clusters, each tending to imply a distinct location. Subsequently, we adapt machine learning models to our setting and design classifiers that classify each tweet cluster into one of the pre-defined location classes at the city level. Extensive experiments on a large set of real Twitter data suggest that our models are effective at inferring locations for non-geotagged tweets and outperform the state-of-the-art approaches significantly in terms of inference accuracy.

AB - This study explores the problem of inferring locations for individual tweets. We scrutinize Twitter user timelines in a novel fashion. First of all, we split each user's tweet timeline temporally into a number of clusters, each tending to imply a distinct location. Subsequently, we adapt machine learning models to our setting and design classifiers that classify each tweet cluster into one of the pre-defined location classes at the city level. Extensive experiments on a large set of real Twitter data suggest that our models are effective at inferring locations for non-geotagged tweets and outperform the state-of-the-art approaches significantly in terms of inference accuracy.

M3 - Conference abstract in proceeding

SP - 2111

EP - 2112

BT - Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE)

ER -

Li P, Lu H, Kanhabua N, Zhao S, Pan G. Location Inference for Non-geotagged Tweets in User Timelines [Extended Abstract]. I Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE). 2019. s. 2111-2112