An Iterative Refinement Approach for Social Media Headline Prediction

In this study, we propose a novel iterative refinement approach to predict the popularity score of the social media meta-data effectively. With the rapid growth of the social media on the Internet, how to adequately forecast the view count or popularity becomes more important. Conventionally, the en...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Hsu, Chih-Chung, Lee, Chia-Yen, Liao, Ting-Xuan, Lee, Jun-Yi, Hou, Tsai-Yne, Kuo, Ying-Chu, Lin, Jing-Wen, Hsueh, Ching-Yi, Zhan, Zhong-Xuan, Chien, Hsiang-Chin
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 24.09.2018
Subjects
Computer Science - Multimedia
Digital media
Extreme values
Performance prediction
Regression
Residues
Social networks
Online AccessGet full text

Cover

More Information
Summary:In this study, we propose a novel iterative refinement approach to predict the popularity score of the social media meta-data effectively. With the rapid growth of the social media on the Internet, how to adequately forecast the view count or popularity becomes more important. Conventionally, the ensemble approach such as random forest regression achieves high and stable performance on various prediction tasks. However, most of the regression methods may not precisely predict the extreme high or low values. To address this issue, we first predict the initial popularity score and retrieve their residues. In order to correctly compensate those extreme values, we adopt an ensemble regressor to compensate the residues to further improve the prediction performance. Comprehensive experiments are conducted to demonstrate the proposed iterative refinement approach outperforms the state-of-the-art regression approach.
ISSN:2331-8422
DOI:10.48550/arxiv.1809.08753