Exploring Time Aware Features in Microblog to Measure TV Ratings

Joon Yeon CHOEH; Hong Joo LEE; Eugene J. S. WON

doi:10.1587/transinf.2014EDL8036

Exploring Time Aware Features in Microblog to Measure TV Ratings

Joon Yeon CHOEH, Hong Joo LEE, Eugene J. S. WON

Full Text Views

0

Cite this

Summary :

In measuring TV ratings, some features can be significant at a certain time, whereas they can be meaningless in other time periods. Because the importance of features can change, a model capturing the time changing relevance is required in order to estimate TV ratings more accurately. Therefore, we focus on the time-awareness of features, particularly the time when the words of tweets are used. We develop a correlation-based, time-aware feature selection algorithm which finds the optimal time period of each feature, and the estimation method using e-SVR based on top-n-features that are ordered by correlation. We identify that the correlation values between features and TV ratings vary according to the time of postings - before and after the broadcast time. This implies that the relevance of features can change according to the time of the tweets. Experimental results indicate that the proposed method has better performance compared with the method based on count-based features. This result implies that understanding the time-dependency of features can be helpful in improving the accuracy of measuring TV ratings.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.10 pp.2810-2813

Publication Date: 2014/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2014EDL8036

Type of Manuscript: LETTER

Category: Office Information Systems, e-Business Modeling

Authors

Joon Yeon CHOEH
  Sejong University
Hong Joo LEE
  Catholic University of Korea
Eugene J. S. WON
  Dongduk Women's University

Keyword

time awareness, microblog, TV ratings

Cite this

Copy

Joon Yeon CHOEH, Hong Joo LEE, Eugene J. S. WON, "Exploring Time Aware Features in Microblog to Measure TV Ratings" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 10, pp. 2810-2813, October 2014, doi: 10.1587/transinf.2014EDL8036.
Abstract: In measuring TV ratings, some features can be significant at a certain time, whereas they can be meaningless in other time periods. Because the importance of features can change, a model capturing the time changing relevance is required in order to estimate TV ratings more accurately. Therefore, we focus on the time-awareness of features, particularly the time when the words of tweets are used. We develop a correlation-based, time-aware feature selection algorithm which finds the optimal time period of each feature, and the estimation method using e-SVR based on top-n-features that are ordered by correlation. We identify that the correlation values between features and TV ratings vary according to the time of postings - before and after the broadcast time. This implies that the relevance of features can change according to the time of the tweets. Experimental results indicate that the proposed method has better performance compared with the method based on count-based features. This result implies that understanding the time-dependency of features can be helpful in improving the accuracy of measuring TV ratings.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2014EDL8036/_p

Copy

@ARTICLE{e97-d_10_2810,
author={Joon Yeon CHOEH, Hong Joo LEE, Eugene J. S. WON, },
journal={IEICE TRANSACTIONS on Information},
title={Exploring Time Aware Features in Microblog to Measure TV Ratings},
year={2014},
volume={E97-D},
number={10},
pages={2810-2813},
abstract={In measuring TV ratings, some features can be significant at a certain time, whereas they can be meaningless in other time periods. Because the importance of features can change, a model capturing the time changing relevance is required in order to estimate TV ratings more accurately. Therefore, we focus on the time-awareness of features, particularly the time when the words of tweets are used. We develop a correlation-based, time-aware feature selection algorithm which finds the optimal time period of each feature, and the estimation method using e-SVR based on top-n-features that are ordered by correlation. We identify that the correlation values between features and TV ratings vary according to the time of postings - before and after the broadcast time. This implies that the relevance of features can change according to the time of the tweets. Experimental results indicate that the proposed method has better performance compared with the method based on count-based features. This result implies that understanding the time-dependency of features can be helpful in improving the accuracy of measuring TV ratings.},
keywords={},
doi={10.1587/transinf.2014EDL8036},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Exploring Time Aware Features in Microblog to Measure TV Ratings
T2 - IEICE TRANSACTIONS on Information
SP - 2810
EP - 2813
AU - Joon Yeon CHOEH
AU - Hong Joo LEE
AU - Eugene J. S. WON
PY - 2014
DO - 10.1587/transinf.2014EDL8036
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2014
AB - In measuring TV ratings, some features can be significant at a certain time, whereas they can be meaningless in other time periods. Because the importance of features can change, a model capturing the time changing relevance is required in order to estimate TV ratings more accurately. Therefore, we focus on the time-awareness of features, particularly the time when the words of tweets are used. We develop a correlation-based, time-aware feature selection algorithm which finds the optimal time period of each feature, and the estimation method using e-SVR based on top-n-features that are ordered by correlation. We identify that the correlation values between features and TV ratings vary according to the time of postings - before and after the broadcast time. This implies that the relevance of features can change according to the time of the tweets. Experimental results indicate that the proposed method has better performance compared with the method based on count-based features. This result implies that understanding the time-dependency of features can be helpful in improving the accuracy of measuring TV ratings.
ER -