Trend sensing via Twitter

Yavuz Selim Yilmaz, Muhammed Fatih Bulut, Cuneyt Gurcan Akcora, Murat Ali Bayir, Murat Demirbas

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Due to its ever increasing popularity, Twitter has become a pervasive information outlet. In this paper, we present a passive sensing framework for identifying trends via Twitter. In our framework, we use a multi-dimensional corpus for finegranularity sensing of trends, and employ both vector-space and set-space methods for achieving accuracy.We present two applications of our framework. The first one is sensing trends in public opinion by using an emotion-category corpus. The second application is sensing trends in location-types in a city by using a location-category corpus. Our experiments show that the proposed methods are able to determine changes in trends effectively in both application scenarios.

Original languageEnglish
Pages (from-to)16-26
Number of pages11
JournalInternational Journal of Ad Hoc and Ubiquitous Computing
Volume14
Issue number1
DOIs
Publication statusPublished - 18 Sep 2013

Fingerprint

Vector spaces
Experiments

Keywords

  • City-wide sensing
  • Opinion mining
  • Trend sensing
  • Twitter

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Cite this

Yilmaz, Y. S., Bulut, M. F., Akcora, C. G., Bayir, M. A., & Demirbas, M. (2013). Trend sensing via Twitter. International Journal of Ad Hoc and Ubiquitous Computing, 14(1), 16-26. https://doi.org/10.1504/IJAHUC.2013.056271

Trend sensing via Twitter. / Yilmaz, Yavuz Selim; Bulut, Muhammed Fatih; Akcora, Cuneyt Gurcan; Bayir, Murat Ali; Demirbas, Murat.

In: International Journal of Ad Hoc and Ubiquitous Computing, Vol. 14, No. 1, 18.09.2013, p. 16-26.

Research output: Contribution to journalArticle

Yilmaz, YS, Bulut, MF, Akcora, CG, Bayir, MA & Demirbas, M 2013, 'Trend sensing via Twitter', International Journal of Ad Hoc and Ubiquitous Computing, vol. 14, no. 1, pp. 16-26. https://doi.org/10.1504/IJAHUC.2013.056271
Yilmaz YS, Bulut MF, Akcora CG, Bayir MA, Demirbas M. Trend sensing via Twitter. International Journal of Ad Hoc and Ubiquitous Computing. 2013 Sep 18;14(1):16-26. https://doi.org/10.1504/IJAHUC.2013.056271
Yilmaz, Yavuz Selim ; Bulut, Muhammed Fatih ; Akcora, Cuneyt Gurcan ; Bayir, Murat Ali ; Demirbas, Murat. / Trend sensing via Twitter. In: International Journal of Ad Hoc and Ubiquitous Computing. 2013 ; Vol. 14, No. 1. pp. 16-26.
@article{a2a6a5b08fbb421d85539c83938324d8,
title = "Trend sensing via Twitter",
abstract = "Due to its ever increasing popularity, Twitter has become a pervasive information outlet. In this paper, we present a passive sensing framework for identifying trends via Twitter. In our framework, we use a multi-dimensional corpus for finegranularity sensing of trends, and employ both vector-space and set-space methods for achieving accuracy.We present two applications of our framework. The first one is sensing trends in public opinion by using an emotion-category corpus. The second application is sensing trends in location-types in a city by using a location-category corpus. Our experiments show that the proposed methods are able to determine changes in trends effectively in both application scenarios.",
keywords = "City-wide sensing, Opinion mining, Trend sensing, Twitter",
author = "Yilmaz, {Yavuz Selim} and Bulut, {Muhammed Fatih} and Akcora, {Cuneyt Gurcan} and Bayir, {Murat Ali} and Murat Demirbas",
year = "2013",
month = "9",
day = "18",
doi = "10.1504/IJAHUC.2013.056271",
language = "English",
volume = "14",
pages = "16--26",
journal = "International Journal of Ad Hoc and Ubiquitous Computing",
issn = "1743-8225",
publisher = "Inderscience Enterprises Ltd",
number = "1",

}

TY - JOUR

T1 - Trend sensing via Twitter

AU - Yilmaz, Yavuz Selim

AU - Bulut, Muhammed Fatih

AU - Akcora, Cuneyt Gurcan

AU - Bayir, Murat Ali

AU - Demirbas, Murat

PY - 2013/9/18

Y1 - 2013/9/18

N2 - Due to its ever increasing popularity, Twitter has become a pervasive information outlet. In this paper, we present a passive sensing framework for identifying trends via Twitter. In our framework, we use a multi-dimensional corpus for finegranularity sensing of trends, and employ both vector-space and set-space methods for achieving accuracy.We present two applications of our framework. The first one is sensing trends in public opinion by using an emotion-category corpus. The second application is sensing trends in location-types in a city by using a location-category corpus. Our experiments show that the proposed methods are able to determine changes in trends effectively in both application scenarios.

AB - Due to its ever increasing popularity, Twitter has become a pervasive information outlet. In this paper, we present a passive sensing framework for identifying trends via Twitter. In our framework, we use a multi-dimensional corpus for finegranularity sensing of trends, and employ both vector-space and set-space methods for achieving accuracy.We present two applications of our framework. The first one is sensing trends in public opinion by using an emotion-category corpus. The second application is sensing trends in location-types in a city by using a location-category corpus. Our experiments show that the proposed methods are able to determine changes in trends effectively in both application scenarios.

KW - City-wide sensing

KW - Opinion mining

KW - Trend sensing

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84883859395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883859395&partnerID=8YFLogxK

U2 - 10.1504/IJAHUC.2013.056271

DO - 10.1504/IJAHUC.2013.056271

M3 - Article

AN - SCOPUS:84883859395

VL - 14

SP - 16

EP - 26

JO - International Journal of Ad Hoc and Ubiquitous Computing

JF - International Journal of Ad Hoc and Ubiquitous Computing

SN - 1743-8225

IS - 1

ER -