An Iterative Refinement Approach for Social Media Headline Prediction

TL;DR

This paper introduces an iterative refinement method for social media headline popularity prediction, improving accuracy especially for extreme values by combining initial predictions with residue compensation using ensemble regressors.

Contribution

It presents a novel iterative refinement approach that enhances prediction accuracy for social media popularity scores, especially for extreme values, outperforming existing regression methods.

Findings

Outperforms state-of-the-art regression approaches

Effectively predicts extreme high or low popularity scores

Demonstrates improved accuracy through iterative residue compensation

Abstract

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.