A privacy-preserving semantic annotation framework using online social media

Shuo Wang, Richard Sinnott, Surya Nepal

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

Semantic annotation framework that allows enriching locations or trajectories with semantic abstractions of the raw spatiotemporal data benefits understanding the semantic behavior of moving objects. Existing semantic annotation approaches mainly analyze specific parts of a trajectory, e.g. stops, in association with data from 3rd party geographic sources, e.g. (POI) points-of-interest, road networks. However, these semantic resources are static thus miss important dynamic event information. Recent location-based social networking provides a new dynamic and prevalent source of human activity data that can be a potential semantic resource for annotation. However, using the large-scale spatiotemporal data from online social media gives rise to privacy concerns. This paper thus presents a privacy-preserving semantic annotation framework P-SAFE that (i) identifies dynamic region of interest (DRI) from large-scale data provided by location based social networks whilst labelling of DRI into appropriate categories derived from spatial and temporal features of geotags, (ii) aligns trajectories to a set of DRI and enriches trajectories with semantics annotation derived from aligned DRI via THMM model, and (iii) embeds robust privacy-preserving mechanisms under differential privacy in each stage that accesses to raw data. P-SAFE approach tackles the privacy and utility trade-offs for meaningful geographic regions identification and labeling as well as trajectory semantic annotation under differential privacy whilst combining them into a single task. We demonstrate the effectiveness of P-SAFE approach on a dataset of large-scale geotagged tweets and a benchmark trajectory dataset for DRI construction and trajectory semantic annotation evaluation. The experimental results illustrate that P-SAFE not only provides robust privacy guarantees but remains approximate 45–56% accuracy for meaningful geographic regions labelling and 62–76% accuracy for trajectory semantic annotation.

Original languageEnglish
Title of host publicationWeb Services – ICWS 2018
Subtitle of host publication25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings
EditorsHai Jin, Qingyang Wang, Liang-Jie Zhang
Place of PublicationCham Switzerland
PublisherSpringer
Pages353-372
Number of pages20
ISBN (Electronic)9783319942896
ISBN (Print)9783319942889
DOIs
Publication statusPublished - 2018
EventIEEE International Conference on Web Services 2018 - Seattle, United States of America
Duration: 25 Jun 201830 Jun 2018
Conference number: 25th
https://conferences.computer.org/icws/2018/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10966
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

ConferenceIEEE International Conference on Web Services 2018
Abbreviated titleICWS 2018
CountryUnited States of America
CitySeattle
Period25/06/1830/06/18
Internet address

Cite this

Wang, S., Sinnott, R., & Nepal, S. (2018). A privacy-preserving semantic annotation framework using online social media. In H. Jin, Q. Wang, & L-J. Zhang (Eds.), Web Services – ICWS 2018 : 25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings (pp. 353-372). (Lecture Notes in Computer Science ; Vol. 10966). Cham Switzerland: Springer. https://doi.org/10.1007/978-3-319-94289-6_23
Wang, Shuo ; Sinnott, Richard ; Nepal, Surya. / A privacy-preserving semantic annotation framework using online social media. Web Services – ICWS 2018 : 25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings. editor / Hai Jin ; Qingyang Wang ; Liang-Jie Zhang. Cham Switzerland : Springer, 2018. pp. 353-372 (Lecture Notes in Computer Science ).
@inproceedings{b416022ca8be4f59887c117da0ef2e61,
title = "A privacy-preserving semantic annotation framework using online social media",
abstract = "Semantic annotation framework that allows enriching locations or trajectories with semantic abstractions of the raw spatiotemporal data benefits understanding the semantic behavior of moving objects. Existing semantic annotation approaches mainly analyze specific parts of a trajectory, e.g. stops, in association with data from 3rd party geographic sources, e.g. (POI) points-of-interest, road networks. However, these semantic resources are static thus miss important dynamic event information. Recent location-based social networking provides a new dynamic and prevalent source of human activity data that can be a potential semantic resource for annotation. However, using the large-scale spatiotemporal data from online social media gives rise to privacy concerns. This paper thus presents a privacy-preserving semantic annotation framework P-SAFE that (i) identifies dynamic region of interest (DRI) from large-scale data provided by location based social networks whilst labelling of DRI into appropriate categories derived from spatial and temporal features of geotags, (ii) aligns trajectories to a set of DRI and enriches trajectories with semantics annotation derived from aligned DRI via THMM model, and (iii) embeds robust privacy-preserving mechanisms under differential privacy in each stage that accesses to raw data. P-SAFE approach tackles the privacy and utility trade-offs for meaningful geographic regions identification and labeling as well as trajectory semantic annotation under differential privacy whilst combining them into a single task. We demonstrate the effectiveness of P-SAFE approach on a dataset of large-scale geotagged tweets and a benchmark trajectory dataset for DRI construction and trajectory semantic annotation evaluation. The experimental results illustrate that P-SAFE not only provides robust privacy guarantees but remains approximate 45–56{\%} accuracy for meaningful geographic regions labelling and 62–76{\%} accuracy for trajectory semantic annotation.",
author = "Shuo Wang and Richard Sinnott and Surya Nepal",
year = "2018",
doi = "10.1007/978-3-319-94289-6_23",
language = "English",
isbn = "9783319942889",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "353--372",
editor = "Hai Jin and Qingyang Wang and Liang-Jie Zhang",
booktitle = "Web Services – ICWS 2018",

}

Wang, S, Sinnott, R & Nepal, S 2018, A privacy-preserving semantic annotation framework using online social media. in H Jin, Q Wang & L-J Zhang (eds), Web Services – ICWS 2018 : 25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings. Lecture Notes in Computer Science , vol. 10966, Springer, Cham Switzerland, pp. 353-372, IEEE International Conference on Web Services 2018, Seattle, United States of America, 25/06/18. https://doi.org/10.1007/978-3-319-94289-6_23

A privacy-preserving semantic annotation framework using online social media. / Wang, Shuo; Sinnott, Richard; Nepal, Surya.

Web Services – ICWS 2018 : 25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings. ed. / Hai Jin; Qingyang Wang; Liang-Jie Zhang. Cham Switzerland : Springer, 2018. p. 353-372 (Lecture Notes in Computer Science ; Vol. 10966).

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

TY - GEN

T1 - A privacy-preserving semantic annotation framework using online social media

AU - Wang, Shuo

AU - Sinnott, Richard

AU - Nepal, Surya

PY - 2018

Y1 - 2018

N2 - Semantic annotation framework that allows enriching locations or trajectories with semantic abstractions of the raw spatiotemporal data benefits understanding the semantic behavior of moving objects. Existing semantic annotation approaches mainly analyze specific parts of a trajectory, e.g. stops, in association with data from 3rd party geographic sources, e.g. (POI) points-of-interest, road networks. However, these semantic resources are static thus miss important dynamic event information. Recent location-based social networking provides a new dynamic and prevalent source of human activity data that can be a potential semantic resource for annotation. However, using the large-scale spatiotemporal data from online social media gives rise to privacy concerns. This paper thus presents a privacy-preserving semantic annotation framework P-SAFE that (i) identifies dynamic region of interest (DRI) from large-scale data provided by location based social networks whilst labelling of DRI into appropriate categories derived from spatial and temporal features of geotags, (ii) aligns trajectories to a set of DRI and enriches trajectories with semantics annotation derived from aligned DRI via THMM model, and (iii) embeds robust privacy-preserving mechanisms under differential privacy in each stage that accesses to raw data. P-SAFE approach tackles the privacy and utility trade-offs for meaningful geographic regions identification and labeling as well as trajectory semantic annotation under differential privacy whilst combining them into a single task. We demonstrate the effectiveness of P-SAFE approach on a dataset of large-scale geotagged tweets and a benchmark trajectory dataset for DRI construction and trajectory semantic annotation evaluation. The experimental results illustrate that P-SAFE not only provides robust privacy guarantees but remains approximate 45–56% accuracy for meaningful geographic regions labelling and 62–76% accuracy for trajectory semantic annotation.

AB - Semantic annotation framework that allows enriching locations or trajectories with semantic abstractions of the raw spatiotemporal data benefits understanding the semantic behavior of moving objects. Existing semantic annotation approaches mainly analyze specific parts of a trajectory, e.g. stops, in association with data from 3rd party geographic sources, e.g. (POI) points-of-interest, road networks. However, these semantic resources are static thus miss important dynamic event information. Recent location-based social networking provides a new dynamic and prevalent source of human activity data that can be a potential semantic resource for annotation. However, using the large-scale spatiotemporal data from online social media gives rise to privacy concerns. This paper thus presents a privacy-preserving semantic annotation framework P-SAFE that (i) identifies dynamic region of interest (DRI) from large-scale data provided by location based social networks whilst labelling of DRI into appropriate categories derived from spatial and temporal features of geotags, (ii) aligns trajectories to a set of DRI and enriches trajectories with semantics annotation derived from aligned DRI via THMM model, and (iii) embeds robust privacy-preserving mechanisms under differential privacy in each stage that accesses to raw data. P-SAFE approach tackles the privacy and utility trade-offs for meaningful geographic regions identification and labeling as well as trajectory semantic annotation under differential privacy whilst combining them into a single task. We demonstrate the effectiveness of P-SAFE approach on a dataset of large-scale geotagged tweets and a benchmark trajectory dataset for DRI construction and trajectory semantic annotation evaluation. The experimental results illustrate that P-SAFE not only provides robust privacy guarantees but remains approximate 45–56% accuracy for meaningful geographic regions labelling and 62–76% accuracy for trajectory semantic annotation.

UR - http://www.scopus.com/inward/record.url?scp=85049378322&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-94289-6_23

DO - 10.1007/978-3-319-94289-6_23

M3 - Conference Paper

SN - 9783319942889

T3 - Lecture Notes in Computer Science

SP - 353

EP - 372

BT - Web Services – ICWS 2018

A2 - Jin, Hai

A2 - Wang, Qingyang

A2 - Zhang, Liang-Jie

PB - Springer

CY - Cham Switzerland

ER -

Wang S, Sinnott R, Nepal S. A privacy-preserving semantic annotation framework using online social media. In Jin H, Wang Q, Zhang L-J, editors, Web Services – ICWS 2018 : 25th International Conference Held as Part of the Services Conference Federation, SCF 2018 Seattle, WA, USA, June 25–30, 2018 Proceedings. Cham Switzerland: Springer. 2018. p. 353-372. (Lecture Notes in Computer Science ). https://doi.org/10.1007/978-3-319-94289-6_23