Sharing Behavior in Online Social Media: An Empirical Analysis with Deep Learning
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.
KeywordsSocial media Information diffusion Deep learning Topic modeling Community analysis
- 1.Banerjee, A., Chandrasekhar, A.G., Duflo, E., Jackson, M.O.: The diffusion of microfinance. Science 341(6144) (2013)Google Scholar
- 4.Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: ACM International Conference on Multimedia, pp. 675–678 (2014)Google Scholar
- 5.Lee, D., Hosanagar, K., Nair, H.: The effect of social media marketing content on consumer engagement: evidence from facebook. In: SSRN, p. 2290802 (2014)Google Scholar
- 9.Shi, Z., Lee, G.M., Whinston, A.B.: Towards a better measure of business proximity: topic modeling for industry intelligence. MIS Q. forthcomingGoogle Scholar
- 10.Shi, Z., Rui, H., Whinston, A.B.: Content sharing in a social broadcasting environment: evidence from twitter. MIS Q. 38(1), 123–142 (2014)Google Scholar