The application of weighted co‐occurring keywords time gram in academic research temporal sequence discovery

Abstract

Abstract The discovery and visualization of temporal sequence of personalized academic research can enhance the ability for discovering the latent trend of interests to information seekers. In this paper, we propose a definition of weighted co‐occurring keywords time gram and use it as a basic unit to analyze the temporal information in existed keywords collection. We further propose a method to get the temporal sequence and temporal network based on these time grams. An application of the proposed method in discovering academic research temporal sequence is discussed, which includes techniques for acquiring extended keywords, assigning weight to each keyword and co‐occurring weight to each keyword pair. A visualization tool is designed for browsing the temporal networks identified. Finally, we report an experiment in the area of library and information studies. The experiment results show the effectiveness of the proposed method in helping users analyzing and portraying the evolution pattern and developing trend of corresponding academic research.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.