Full-Text Analysis of the Literature of an Entire Scientific Field

From Master Projects
Jump to: navigation, search


About Full-Text Analysis of the Literature of an Entire Scientific Field

  • This project has not yet been fulfilled.
  • This project fits in the following Bachelor programs: {{#arraymap:|, |xXx|bachelorproject within::xXx|,}}
  • This project fits in the following masterareas: {{#arraymap:AI and Communication, Computer Science and Communication, Human Ambience, Information Sciences, Information and Communication Technology, Knowledge Technology and Intelligent Internet Applications, Technical Artificial Intelligence|, |xXx|project within::xXx|,}}


Description

Problem: We only have a very incomplete understanding of how scientific work builds upon existing work, how innovation emerges, and how scientific publications build upon the existing literature. Existing studies mostly look at the citation network and/or titles and abstracts, but not at the full article texts (because they are normally not available).

Solution: The SCOAP3 dataset (http://scoap3.org/) provides us with a large portion of the publications as full texts in the given scientific field (particle physics), which we can use to study this field based on its publication output.

Method: We can apply existing methods of network analysis (citation network and/or co-authorship network) and natural language processing and look for patterns that show us how scientific work builds upon existing work, and which properties are important for the success of a paper.