What problem does it solve? Identifying emerging research fronts and hot topics from large bibliographic datasets is time-consuming when done manually. This Skill automates keyword burst detection on cleaned Web of Science (WoS) plain text files, revealing which terms surged in specific time periods and how research trends evolved. ## Core Features & Use Cases - Burst Detection: Applies a simplified Kleinberg two-state automaton algorithm to find keywords with significant frequency surges, reporting burst strength, start/end years, and duration. - Trend & Phase Analysis: Groups burst keywords into research phases (early exploration, growth, frontier) and highlights emerging keywords from recent years. - Network Pruning Reference: Integrates CiteSpace pruning methods (Pathfinder, MST, Pruning Sliced Networks) and network metrics such as degree, betweenness, and closeness centrality. - Use Case: After cleaning a WoS dataset of 3,000+ papers, run this Skill to produce a ranked CSV of burst keywords, an ASCII timeline visualization, and a Top 50 high-frequency keyword list for a literature review. ## Quick Start Run keyword burst detection on my cleaned WoS plain text file and export the burst keyword results with strength scores and time ranges to a CSV file.
