GeoAttn: Localization of social media messages via attentional memory network

Sha Li, Chao Zhang, Dongming Lei, Ji Li, Jiawei Han

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent studies have demonstrated inspiring success in leveraging geo-tagged social media data for applications such as event detection, location recommendation and mobile healthcare. However, in most real-life social media streams, only a small percentage of data have explicit geo-location metadata, which hinders the power of social media from being fully unleashed. We study the problem of inferring geo-locations from social media messages. While a number of text-based geo-locating techniques have been proposed, they either fall short of automatically identifying indicative keywords from noisy social media posts or do not integrate rich prior knowledge of geological regions. We propose an attentive memory network called GeoAttn for localization of social media messages. To capture indicative keywords for location inference, GeoAttn consists of an attentive message encoder, which selectively focuses on location-indicative terms to derive a discriminative message representation. The message embedding is then fed into a memory network, which selectively attends to relevant Points-of-Interest (POIs) for location prediction. The message encoder and key-value memory network are jointly trained in an end-to-end manner. The attention mechanisms in GeoAttn not only alleviate noisy information for higher prediction accuracy, but also provide interpretable attention scores that rationalize the predictions. Our experiments on a million-scale geo-tagged tweet dataset show that GeoAttn outperforms previous state-of-the-art location prediction methods by 15.5% in mean error distance, and is capable of locating over half of the tweets within 5km.

Original languageEnglish (US)
Title of host publicationSIAM International Conference on Data Mining, SDM 2019
PublisherSociety for Industrial and Applied Mathematics Publications
Pages64-72
Number of pages9
ISBN (Electronic)9781611975673
StatePublished - Jan 1 2019
Event19th SIAM International Conference on Data Mining, SDM 2019 - Calgary, Canada
Duration: May 2 2019May 4 2019

Publication series

NameSIAM International Conference on Data Mining, SDM 2019

Conference

Conference19th SIAM International Conference on Data Mining, SDM 2019
CountryCanada
CityCalgary
Period5/2/195/4/19

Fingerprint

Data storage equipment
Metadata
Experiments

ASJC Scopus subject areas

  • Software

Cite this

Li, S., Zhang, C., Lei, D., Li, J., & Han, J. (2019). GeoAttn: Localization of social media messages via attentional memory network. In SIAM International Conference on Data Mining, SDM 2019 (pp. 64-72). (SIAM International Conference on Data Mining, SDM 2019). Society for Industrial and Applied Mathematics Publications.

GeoAttn : Localization of social media messages via attentional memory network. / Li, Sha; Zhang, Chao; Lei, Dongming; Li, Ji; Han, Jiawei.

SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications, 2019. p. 64-72 (SIAM International Conference on Data Mining, SDM 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, S, Zhang, C, Lei, D, Li, J & Han, J 2019, GeoAttn: Localization of social media messages via attentional memory network. in SIAM International Conference on Data Mining, SDM 2019. SIAM International Conference on Data Mining, SDM 2019, Society for Industrial and Applied Mathematics Publications, pp. 64-72, 19th SIAM International Conference on Data Mining, SDM 2019, Calgary, Canada, 5/2/19.
Li S, Zhang C, Lei D, Li J, Han J. GeoAttn: Localization of social media messages via attentional memory network. In SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications. 2019. p. 64-72. (SIAM International Conference on Data Mining, SDM 2019).
Li, Sha ; Zhang, Chao ; Lei, Dongming ; Li, Ji ; Han, Jiawei. / GeoAttn : Localization of social media messages via attentional memory network. SIAM International Conference on Data Mining, SDM 2019. Society for Industrial and Applied Mathematics Publications, 2019. pp. 64-72 (SIAM International Conference on Data Mining, SDM 2019).
@inproceedings{3051f542a67844488fcf37746db1b04f,
title = "GeoAttn: Localization of social media messages via attentional memory network",
abstract = "Recent studies have demonstrated inspiring success in leveraging geo-tagged social media data for applications such as event detection, location recommendation and mobile healthcare. However, in most real-life social media streams, only a small percentage of data have explicit geo-location metadata, which hinders the power of social media from being fully unleashed. We study the problem of inferring geo-locations from social media messages. While a number of text-based geo-locating techniques have been proposed, they either fall short of automatically identifying indicative keywords from noisy social media posts or do not integrate rich prior knowledge of geological regions. We propose an attentive memory network called GeoAttn for localization of social media messages. To capture indicative keywords for location inference, GeoAttn consists of an attentive message encoder, which selectively focuses on location-indicative terms to derive a discriminative message representation. The message embedding is then fed into a memory network, which selectively attends to relevant Points-of-Interest (POIs) for location prediction. The message encoder and key-value memory network are jointly trained in an end-to-end manner. The attention mechanisms in GeoAttn not only alleviate noisy information for higher prediction accuracy, but also provide interpretable attention scores that rationalize the predictions. Our experiments on a million-scale geo-tagged tweet dataset show that GeoAttn outperforms previous state-of-the-art location prediction methods by 15.5{\%} in mean error distance, and is capable of locating over half of the tweets within 5km.",
author = "Sha Li and Chao Zhang and Dongming Lei and Ji Li and Jiawei Han",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
series = "SIAM International Conference on Data Mining, SDM 2019",
publisher = "Society for Industrial and Applied Mathematics Publications",
pages = "64--72",
booktitle = "SIAM International Conference on Data Mining, SDM 2019",
address = "United States",

}

TY - GEN

T1 - GeoAttn

T2 - Localization of social media messages via attentional memory network

AU - Li, Sha

AU - Zhang, Chao

AU - Lei, Dongming

AU - Li, Ji

AU - Han, Jiawei

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Recent studies have demonstrated inspiring success in leveraging geo-tagged social media data for applications such as event detection, location recommendation and mobile healthcare. However, in most real-life social media streams, only a small percentage of data have explicit geo-location metadata, which hinders the power of social media from being fully unleashed. We study the problem of inferring geo-locations from social media messages. While a number of text-based geo-locating techniques have been proposed, they either fall short of automatically identifying indicative keywords from noisy social media posts or do not integrate rich prior knowledge of geological regions. We propose an attentive memory network called GeoAttn for localization of social media messages. To capture indicative keywords for location inference, GeoAttn consists of an attentive message encoder, which selectively focuses on location-indicative terms to derive a discriminative message representation. The message embedding is then fed into a memory network, which selectively attends to relevant Points-of-Interest (POIs) for location prediction. The message encoder and key-value memory network are jointly trained in an end-to-end manner. The attention mechanisms in GeoAttn not only alleviate noisy information for higher prediction accuracy, but also provide interpretable attention scores that rationalize the predictions. Our experiments on a million-scale geo-tagged tweet dataset show that GeoAttn outperforms previous state-of-the-art location prediction methods by 15.5% in mean error distance, and is capable of locating over half of the tweets within 5km.

AB - Recent studies have demonstrated inspiring success in leveraging geo-tagged social media data for applications such as event detection, location recommendation and mobile healthcare. However, in most real-life social media streams, only a small percentage of data have explicit geo-location metadata, which hinders the power of social media from being fully unleashed. We study the problem of inferring geo-locations from social media messages. While a number of text-based geo-locating techniques have been proposed, they either fall short of automatically identifying indicative keywords from noisy social media posts or do not integrate rich prior knowledge of geological regions. We propose an attentive memory network called GeoAttn for localization of social media messages. To capture indicative keywords for location inference, GeoAttn consists of an attentive message encoder, which selectively focuses on location-indicative terms to derive a discriminative message representation. The message embedding is then fed into a memory network, which selectively attends to relevant Points-of-Interest (POIs) for location prediction. The message encoder and key-value memory network are jointly trained in an end-to-end manner. The attention mechanisms in GeoAttn not only alleviate noisy information for higher prediction accuracy, but also provide interpretable attention scores that rationalize the predictions. Our experiments on a million-scale geo-tagged tweet dataset show that GeoAttn outperforms previous state-of-the-art location prediction methods by 15.5% in mean error distance, and is capable of locating over half of the tweets within 5km.

UR - http://www.scopus.com/inward/record.url?scp=85066086658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066086658&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85066086658

T3 - SIAM International Conference on Data Mining, SDM 2019

SP - 64

EP - 72

BT - SIAM International Conference on Data Mining, SDM 2019

PB - Society for Industrial and Applied Mathematics Publications

ER -