Unsupervised Learning For Effective User Engagement on Social Media

TL;DR

This paper evaluates unsupervised feature learning methods, PCA and sparse Autoencoder, for predicting social media user engagement, showing significant improvements over baseline methods in different models.

Contribution

It demonstrates the effectiveness of unsupervised learning techniques, specifically PCA and sparse Autoencoder, in enhancing prediction accuracy of user engagement metrics.

Findings

Sparse Autoencoder improves Linear Regression RMSE by 42%.

PCA improves Regression Tree RMSE by 15%.

Unsupervised techniques outperform baseline methods.

Abstract

In this paper, we investigate the effectiveness of unsupervised feature learning techniques in predicting user engagement on social media. Specifically, we compare two methods to predict the number of feedbacks (i.e., comments) that a blog post is likely to receive. We compare Principal Component Analysis (PCA) and sparse Autoencoder to a baseline method where the data are only centered and scaled, on each of two models: Linear Regression and Regression Tree. We find that unsupervised learning techniques significantly improve the prediction accuracy on both models. For the Linear Regression model, sparse Autoencoder achieves the best result, with an improvement in the root mean squared error (RMSE) on the test set of 42% over the baseline method. For the Regression Tree model, PCA achieves the best result, with an improvement in RMSE of 15% over the baseline.