Employ Multimodal Machine Learning for Content quality analysis

TL;DR

This paper introduces a multimodal machine learning approach that combines image and text features using a Siamese network to improve content quality analysis accuracy on media sites.

Contribution

It proposes a novel multimodal quality recognition method utilizing separate feature extractors and a Siamese network, advancing beyond single-modal approaches.

Findings

Higher accuracy in quality score prediction compared to existing methods

Effective integration of image and text features

Demonstrated improvement in content quality assessment

Abstract

The task of identifying high-quality content becomes increasingly important, and it can improve overall reading time and CTR(click-through rate estimates). Generalizes quality analysis only focused on single Modal,such as image or text,but in today's mainstream media sites a lot of information is presented in graphic form.In this paper we propose a MultiModal quality recognition approach for the quality score. First we use two feature extractors,one for image and another for the text. After that we use an Siamese Network with the rank loss as the optimization objective.Compare with other approach,our approach get a more accuracy result.