Context over time: Modeling context evolution in social media

Md Hijbul Alam; Woo Jong Ryu; Sang Keun Lee

doi:10.1145/2665994.2665996

Context over time: Modeling context evolution in social media

Md Hijbul Alam
, Woo Jong Ryu
, Sang Keun Lee

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

5 Citations (Scopus)

Abstract

The rise of online social media has led to an explosion in user-generated content. However, user-generated content is difficult to analyze in isolation from its context. Accordingly, context detection and tracking its evolution is essential to understanding social media. This paper presents a statistical model that can detect interpretable topics along with their contexts. A topic is represented by a cluster of words that frequently occur together, and a context is represented by a cluster of hashtags that frequently occur with a topic. The model combines a context with a related topic by jointly modeling words with hashtags and time. Experiments on real datasets demonstrate that the proposed model successfully discovers both meaningful topics and contexts, and tracks their evolution.

Original language	English
Title of host publication	DUBMOD 2014 - Proceedings of the 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, co-located with CIKM 2014
Publisher	ACM
Pages	15-18
Number of pages	4
Volume	2014-November
Edition	November
ISBN (Print)	978-1-4503-1303-2
DOIs	https://doi.org/10.1145/2665994.2665996
Publication status	Published - 2014
Publication type	A4 Article in conference proceedings
Event	3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, DUBMOD 2014, Co-located with 23rd ACM Conference on Information and Knowledge Management, CIKM 2014 - Duration: 1 Jan 2014 → …

Conference

Conference	3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, DUBMOD 2014, Co-located with 23rd ACM Conference on Information and Knowledge Management, CIKM 2014
Period	1/01/14 → …

Keywords

Context and topic evolution
Social media
Topic model

Publication forum classification

Publication forum level 1

Access to Document

10.1145/2665994.2665996

Cite this

@inproceedings{90a17f5bd62942a39a508c69408e7eeb,

title = "Context over time: Modeling context evolution in social media",

abstract = "The rise of online social media has led to an explosion in user-generated content. However, user-generated content is difficult to analyze in isolation from its context. Accordingly, context detection and tracking its evolution is essential to understanding social media. This paper presents a statistical model that can detect interpretable topics along with their contexts. A topic is represented by a cluster of words that frequently occur together, and a context is represented by a cluster of hashtags that frequently occur with a topic. The model combines a context with a related topic by jointly modeling words with hashtags and time. Experiments on real datasets demonstrate that the proposed model successfully discovers both meaningful topics and contexts, and tracks their evolution.",

keywords = "Context and topic evolution, Social media, Topic model, Context and topic evolution, Social media, Topic model",

author = "Alam, \{Md Hijbul\} and Ryu, \{Woo Jong\} and Lee, \{Sang Keun\}",

year = "2014",

doi = "10.1145/2665994.2665996",

language = "English",

isbn = "978-1-4503-1303-2",

volume = "2014-November",

pages = "15--18",

booktitle = "DUBMOD 2014 - Proceedings of the 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, co-located with CIKM 2014",

publisher = "ACM",

address = "United States",

edition = "November",

note = "3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, DUBMOD 2014, Co-located with 23rd ACM Conference on Information and Knowledge Management, CIKM 2014 ; Conference date: 01-01-2014",

}

Alam, MH, Ryu, WJ & Lee, SK 2014, Context over time: Modeling context evolution in social media. in DUBMOD 2014 - Proceedings of the 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, co-located with CIKM 2014. November edn, vol. 2014-November, ACM, pp. 15-18, 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, DUBMOD 2014, Co-located with 23rd ACM Conference on Information and Knowledge Management, CIKM 2014, 1/01/14. https://doi.org/10.1145/2665994.2665996

Context over time: Modeling context evolution in social media. / Alam, Md Hijbul; Ryu, Woo Jong; Lee, Sang Keun.
DUBMOD 2014 - Proceedings of the 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, co-located with CIKM 2014. Vol. 2014-November November. ed. ACM, 2014. p. 15-18.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Context over time: Modeling context evolution in social media

AU - Alam, Md Hijbul

AU - Ryu, Woo Jong

AU - Lee, Sang Keun

PY - 2014

Y1 - 2014

N2 - The rise of online social media has led to an explosion in user-generated content. However, user-generated content is difficult to analyze in isolation from its context. Accordingly, context detection and tracking its evolution is essential to understanding social media. This paper presents a statistical model that can detect interpretable topics along with their contexts. A topic is represented by a cluster of words that frequently occur together, and a context is represented by a cluster of hashtags that frequently occur with a topic. The model combines a context with a related topic by jointly modeling words with hashtags and time. Experiments on real datasets demonstrate that the proposed model successfully discovers both meaningful topics and contexts, and tracks their evolution.

AB - The rise of online social media has led to an explosion in user-generated content. However, user-generated content is difficult to analyze in isolation from its context. Accordingly, context detection and tracking its evolution is essential to understanding social media. This paper presents a statistical model that can detect interpretable topics along with their contexts. A topic is represented by a cluster of words that frequently occur together, and a context is represented by a cluster of hashtags that frequently occur with a topic. The model combines a context with a related topic by jointly modeling words with hashtags and time. Experiments on real datasets demonstrate that the proposed model successfully discovers both meaningful topics and contexts, and tracks their evolution.

KW - Context and topic evolution

KW - Social media

KW - Topic model

KW - Context and topic evolution

KW - Social media

KW - Topic model

U2 - 10.1145/2665994.2665996

DO - 10.1145/2665994.2665996

M3 - Conference contribution

AN - SCOPUS:84937715645

SN - 978-1-4503-1303-2

VL - 2014-November

SP - 15

EP - 18

BT - DUBMOD 2014 - Proceedings of the 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, co-located with CIKM 2014

PB - ACM

T2 - 3rd Workshop on Data-Driven User Behavioral Modeling and Mining from Social Media, DUBMOD 2014, Co-located with 23rd ACM Conference on Information and Knowledge Management, CIKM 2014

Y2 - 1 January 2014

ER -

Context over time: Modeling context evolution in social media

Abstract

Conference

Keywords

Publication forum classification

Access to Document

Fingerprint

Cite this