Leveraging full-text article exploration for citation analysis

Abstract Scientific articles often include in-text citations quoting from external sources. When the cited source is an article, citation context can be analyzed by exploring article full-text. To quickly access key information, researchers are interested in identifying sections of that most pertinent to text surrounding citing article. This paper first performs a data-driven analysis correlation between textual content and snippet where placed. The results show title abstract likely highly similar snippet. However, subsequent snippets as well. Hence, there need understand extent which exploration full-text would beneficial gain insights into snippet, considering also fact could restricted. this end, we then propose classification approach automatically predicting whether contain significant amount new beyond title. proposed support leveraging for analysis. experiments conducted on real scientific promising results: classifier has 90% chance correctly distinguish only cases.