The purpose of this research is to develop a Viewpoint Refinement in Automatic Summarization (VPRAS) system for research articles. The system will reflect viewpoints of survey to support surveys stage for researchers and students. We collect academic articles using web scraping technology and construct training data by combining sections and sentences through analysis of the article's PDF structure. We use machine learning techniques to classify sentences in Japanese articles into viewpoints. In addition to supervised learning, we introduce reinforcement learning and Dynamic Programming (DP) to extract important sentences for each viewpoint. Finally, we implemented an agent to automatically extract summary sentences based on a reward function.
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.
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.