Dual-view cross attention enhanced semi-supervised learning method for discourse cognitive engagement classification in online course discussions
Abstract: Highlights•We build cognitive and semantic dual-view enhanced feature representation.•We propose dual-view semi-supervised cognitive engagement classification method.•Our semi-supervised learning method works well in the few-sample labeling context.•Our method outperforms state-of-the-art methods on three real-world datasets.
External IDs:doi:10.1016/j.eswa.2025.127339
Loading