Using network science and text analytics to produce surveys in a scientific topic

作者：

Highlights：

• We developed a new method to generate automated taxonomies and visualizations of a scientific field.

• The technique extracts keywords from abstracts and the citation network of papers in a topic.

• Our approach uses network science interwoven with text analytics methods to build scientific maps.

• We analyzed the data encompassing two scientific topics: photonic crystals and complex networks, resulting in several insights about the two fields.

摘要

Highlights•We developed a new method to generate automated taxonomies and visualizations of a scientific field.•The technique extracts keywords from abstracts and the citation network of papers in a topic.•Our approach uses network science interwoven with text analytics methods to build scientific maps.•We analyzed the data encompassing two scientific topics: photonic crystals and complex networks, resulting in several insights about the two fields.

论文关键词：Entropy,Networks,Scientific map,Photonic crystals,Pattern recognition

论文评审过程：Received 7 November 2015, Revised 17 March 2016, Accepted 31 March 2016, Available online 22 April 2016, Version of Record 22 April 2016.

论文官网地址：https://doi.org/10.1016/j.joi.2016.03.008