An Iterative Refinement Approach for Social Media Headline Prediction

in International Symposium (oral presentation paper), 國際研討會(全文口頭發表)
標題An Iterative Refinement Approach for Social Media Headline Prediction
AuthorsChih-Chung Hsu, 許志仲, Chia-Yen Lee 李佳燕, Ting-Xuan Liao 廖庭煖, Tsai-Yne Hou 侯采昀, Jun-Yi Lee 李俊毅, Ying-Chu Kuo 郭瑛茱, Jing-Wen Lin 林靜玟, Ching-Yi Hsueh 薛靜宜, Hsiang-Chin Chien 簡祥秦, & Zhong-Xuan Zhang 張忠軒
出版日期Oct 24 2018 12:0

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 the popularity score and retrieve their residues. Then, we adopt an ensemble regressor to compensate the residues further to improve the prediction performance. Comprehensive experiments are conducted to demonstrate the proposed iterative refinement approach outperforms the state-of-the-art regression approach.

校址:912 屏東縣內埔鄉學府路1號 總機:886-8-7703202 傳真:886-8-7740165 系統開發統維護單位:國立屏東科技大學 電算中心 版權所有