Predicting Social Media Engagement from Emotional and Temporal Features
This work addresses social media analytics for platforms or marketers, but it is incremental as it applies existing methods to a new dataset.
The paper tackled predicting social media engagement (comments and likes) using emotional and temporal features, achieving high accuracy for likes (R^2 = 0.98) but lower for comments (R^2 = 0.41).
We present a machine learning approach for predicting social media engagement (comments and likes) from emotional and temporal features. The dataset contains 600 songs with annotations for valence, arousal, and related sentiment metrics. A multi target regression model based on HistGradientBoostingRegressor is trained on log transformed engagement ratios to address skewed targets. Performance is evaluated with both a custom order of magnitude accuracy and standard regression metrics, including the coefficient of determination (R^2). Results show that emotional and temporal metadata, together with existing view counts, predict future engagement effectively. The model attains R^2 = 0.98 for likes but only R^2 = 0.41 for comments. This gap indicates that likes are largely driven by readily captured affective and exposure signals, whereas comments depend on additional factors not represented in the current feature set.