Integrative model for discovering linked topics in science and technology
作者：
Highlights：
• The science and technology semantic linkage integration model improves the identification of linked topics in science and technology (LTSTs).
• Simple fusion and link prediction form a twofold model to identify topics and implicit semantics.
• Term co-occurrence networks of basic and applied research are fused.
• The fusion expands topic networks and enhances their semantic associations.
• LTST chains identified by connected LTST terms provide micro granularity.
摘要
•The science and technology semantic linkage integration model improves the identification of linked topics in science and technology (LTSTs).•Simple fusion and link prediction form a twofold model to identify topics and implicit semantics.•Term co-occurrence networks of basic and applied research are fused.•The fusion expands topic networks and enhances their semantic associations.•LTST chains identified by connected LTST terms provide micro granularity.
论文关键词：Linked topics in science and technology,Scientific innovation,Science and technology linkage,Link prediction,Topic recognition
论文评审过程：Received 26 May 2021, Revised 11 February 2022, Accepted 16 February 2022, Available online 2 March 2022, Version of Record 2 March 2022.
论文官网地址：https://doi.org/10.1016/j.joi.2022.101265
