Measuring scientific influence using quality citations

Abstract

Every research manuscript is appreciated in the form of citations Citations are expected to carry the essence of the underlying base research article by rhetorical means However this is not true in reality Citation manipulations are equally possible which shall be identified using research semantics This work discusses machine learning based approaches for analyzing research citations with the aim of finding quality research citations On analyzing the semantics of the research manuscript and the respective citations this work proposes various metrics for citation quality analysis including deep cite raw expressive power expressive power and normalized expressive power This thesis also proposes techniques for measuring the citation context of a research manuscript from respective citations and projects the rhetorical quality as a measure of article s expressive power by employing deep learning techniques The articles impact is also analyzed and the proposed metrics are normalized to establish the actual quality of the research manuscript from the perspective of its citations Quite often researchers do not find time to narrate the step by step experiences of their research and eventually ends up writing the article thesis by referring to already published articles The rephrasing approach they use makes the text plagiarism detection tougher newline