Bibliography | Seibold, Constantin: Improving author co-citation analysis in scientific literature by using citation function classification. University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Bachelor Thesis (2016). 57 pages, english.
|
CR-Schema | H.3.3 (Information Search and Retrieval) I.2.7 (Natural Language Processing) I.5.3 (Pattern Recognition Clustering)
|
Abstract | The concept of co-citation analysis is a possible approach for the interpretation of the relations between scientific papers or authors. Most of the previous work regarding author co-citation analysis, however, does not take the citation context into account. In this thesis, I propose a method for letting citation functions, which are functions that represent the intention of an author assigned to the corresponding references, directly influence the author co-citation analysis procedure. This approach is based on a faceted citation classification scheme, which allows comparisons between references. This should allow an easier representation of author groups, as authors, which are working together, usually share the same view on science and, therefore, are likely to be cited similarly. As there is no real gold standard for author groups, the evaluation of this approach tests the textual coherence of clusters created by this procedure based on the authors' oeuvres and compares the nationality of authors within clusters. The results indicate a correlation between author groups and similar citation functions.
|
Full text and other links | PDF (1348316 Bytes)
|
Department(s) | University of Stuttgart, Institute for Natural Language Processing
|
Superviser(s) | Padó, Prof. Sebastian, Klinger, Dr. Roman |
Entry date | September 25, 2018 |
---|