skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Multimodal Event Detection in Twitter Hashtag Networks

Abstract

In this study, event detection in a multimodal Twitter dataset is considered. We treat the hashtags in the dataset as instances with two modes: text and geolocation features. The text feature consists of a bag-of-words representation. The geolocation feature consists of geotags (i.e., geographical coordinates) of the tweets. Fusing the multimodal data we aim to detect, in terms of topic and geolocation, the interesting events and the associated hashtags. To this end, a generative latent variable model is assumed, and a generalized expectation-maximization (EM) algorithm is derived to learn the model parameters. The proposed method is computationally efficient, and lends itself to big datasets. Lastly, experimental results on a Twitter dataset from August 2014 show the efficacy of the proposed method.

Authors:
 [1];  [1]
  1. Univ. of Michigan, Ann Arbor, MI (United States). Department of Electrical Engineering and Computer Science
Publication Date:
Research Org.:
Univ. of Michigan, Ann Arbor, MI (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1454761
Grant/Contract Number:  
NA0002534
Resource Type:
Accepted Manuscript
Journal Name:
Journal of Signal Processing Systems
Additional Journal Information:
Journal Volume: 90; Journal Issue: 2; Journal ID: ISSN 1939-8018
Publisher:
Springer
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Event detection; Twitter hashtag networks; Multimodal data fusion; Generative latent variable model; Variational EM algorithm

Citation Formats

Yilmaz, Yasin, and Hero, Alfred O. Multimodal Event Detection in Twitter Hashtag Networks. United States: N. p., 2016. Web. doi:10.1007/s11265-016-1151-4.
Yilmaz, Yasin, & Hero, Alfred O. Multimodal Event Detection in Twitter Hashtag Networks. United States. doi:10.1007/s11265-016-1151-4.
Yilmaz, Yasin, and Hero, Alfred O. Fri . "Multimodal Event Detection in Twitter Hashtag Networks". United States. doi:10.1007/s11265-016-1151-4. https://www.osti.gov/servlets/purl/1454761.
@article{osti_1454761,
title = {Multimodal Event Detection in Twitter Hashtag Networks},
author = {Yilmaz, Yasin and Hero, Alfred O.},
abstractNote = {In this study, event detection in a multimodal Twitter dataset is considered. We treat the hashtags in the dataset as instances with two modes: text and geolocation features. The text feature consists of a bag-of-words representation. The geolocation feature consists of geotags (i.e., geographical coordinates) of the tweets. Fusing the multimodal data we aim to detect, in terms of topic and geolocation, the interesting events and the associated hashtags. To this end, a generative latent variable model is assumed, and a generalized expectation-maximization (EM) algorithm is derived to learn the model parameters. The proposed method is computationally efficient, and lends itself to big datasets. Lastly, experimental results on a Twitter dataset from August 2014 show the efficacy of the proposed method.},
doi = {10.1007/s11265-016-1151-4},
journal = {Journal of Signal Processing Systems},
number = 2,
volume = 90,
place = {United States},
year = {2016},
month = {7}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: