The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience
Researchers have developed a model capable of predicting which passages in a document will be highlighted by readers, even before those highlights accumulate. This model, trained on existing highlight data, outperforms a simple lead-based baseline by a small but statistically significant margin. The system shows particular promise for less popular content, where its predictive accuracy is more pronounced. AI
IMPACT This research could improve content summarization and recommendation systems by predicting user interest in specific passages.