Predicting Meme Success with Linguistic Features in a Multilayer Backpropagation Network

The challenge of predicting meme success has gained attention from researchers, largely due to the increased availability of social media data. Many models focus on structural features of online social networks as predictors of meme success. The current work takes a different approach, predicting meme success from linguistic features. We propose predictive power is gained by grounding memes in theories of working memory, emotion, memory, and psycholinguistics. The linguistic content of several memes were analyzed with linguistic analysis tools. These features were then trained with a multilayer supervised backpropagation network. A set of new memes was used to test the generalization of the network. Results indicated the network was able to generalize the linguistic features in order to predict success at greater than chance levels (80% accuracy). Linguistic features appear to be enough to predict meme transmission success without any information about social network structure.