Ruozhu Sheng

Mr. Ruozhu Sheng

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

30 July 2025 in Education Sciences
Verified
Journal Article
Open access
PDF file
RSRuozhu Sheng
Ruozhu Sheng
JLJinghong Li
Jinghong Li
SHShinobu Hasegawa
Shinobu Hasegawa
This study proposes a non-semantic multimodal approach to predict segment access frequency (SAF) in lecture archives. Such archives, widely used as supplementary resources in modern education, often consist of long, unedited recordings that are difficult to navigate and review efficiently. The predicted SAF, an indicator of student viewing behavior, serves as a practical proxy for student engagement. The increasing volume of recorded material renders manual editing and annotation impractical, making the automatic identification of high-SAF segments crucial for improving accessibility and supporting targeted content review. The approach focuses on lecture archives from a real-world blended learning context, characterized by resource constraints such as no specialized hardware and limited student numbers. The model integrates multimodal features from instructor’s actions (via OpenPose and optical flow), audio spectrograms, and slide page progression—a selection of features that makes the approach applicable regardless of lecture language. The model was evaluated on 665 labeled one-minute segments from one such course. Experiments show that the best-performing model achieves a Pearson correlation of 0.5143 in 7-fold cross-validation and 61.05% average accuracy in a downstream three-class classification task. These results demonstrate the system’s capacity to enhance lecture archives by automatically identifying key segments, which aids students in efficient, targeted review and provides instructors with valuable data for pedagogical feedback.

18 December 2025
Verified
Conference Paper
Closed access
JLJinghong Li
Jinghong Li
RSRuozhu Sheng
Ruozhu Sheng
DGDawn Gu
Dawn Gu
SHShinobu Hasegawa
Shinobu Hasegawa
The exponential growth of academic literature has created significant challenges in tracking knowledge evolution and understanding research trajectories. While generative AI has shown promise in constructing knowledge graphs and questionanswering systems from academic papers, current approaches struggle to capture the nuanced citation relationships that reveal how knowledge flows and evolves. This research introduces 'cite-clues' - semantic patterns that reveal cite-motivations and knowledge transfer mechanisms between survey papers and regular papers. We propose Survey Hint-net, a novel visualization framework that leverages these cite-clues to map knowledge evolution pathways in reasoning explanation. This framework enables researchers to navigate from foundational concepts to specific solutions and track the development of research topics over time.

21 April 2025 in arXiv
Verified
Preprint
Open access
PDF file
RSRuozhu Sheng
Ruozhu Sheng
JLJinghong Li
Jinghong Li
SHShinobu Hasegawa
Shinobu Hasegawa
This study proposes a multimodal neural network-based approach to predict segment access frequency in lecture archives. These archives, widely used as supplementary resources in modern education, often consist of long, unedited recordings that make it difficult to keep students engaged. Captured directly from face-to-face lectures without post-processing, they lack visual appeal. Meanwhile, the increasing volume of recorded material renders manual editing and annotation impractical. Automatically detecting high-engagement segments is thus crucial for improving accessibility and maintaining learning effectiveness. Our research focuses on real classroom lecture archives, characterized by unedited footage, no additional hardware (e.g., eye-tracking), and limited student numbers. We approximate student engagement using segment access frequency as a proxy. Our model integrates multimodal features from teachers' actions (via OpenPose and optical flow), audio spectrograms, and slide page progression. These features are deliberately chosen for their non-semantic nature, making the approach applicable regardless of lecture language. Experiments show that our best model achieves a Pearson correlation of 0.5143 in 7-fold cross-validation and 69.32 percent average accuracy in a downstream three-class classification task. The results, obtained with high computational efficiency and a small dataset, demonstrate the practical feasibility of our system in real-world educational contexts.