Sharing Behavior in Online Social Media: An Empirical Analysis with Deep Learning

Donghyuk Shin, Shu He, Gene Moo Lee, Andrew B. Whinston

Abstract: We conduct a large-scale empirical study on the sharing behavior in social media to measure the effect of message features and initial messengers on information diffusion. Our analysis focuses on messages created by companies and utilizes both textual and visual semantic content by employing state-of-the-art machine learning methods: topic modeling and deep learning. We find that messages with multiple conspicuous images and messengers with similar content are crucial in the diffusion process. Our approach for semantic content analysis, particularly for visual content, bridges advanced machine learning techniques for effective marketing and social media strategies.

External IDs:dblp:conf/web/ShinHLW15