Citation plays an important role in understanding the knowledge sharing among scholars. Citation sentences embed useful contents that signify the influence of cited authors on shared ideas, and express own opinion of citing authors to others' articles. The purpose of the study is to provide a new lens to analyze the topical relationship embedded in the citation sentences in an integrated manner. To this end, we extract citation sentences from full-text articles in the field of Oncology. In addition, we adopt Author-Journal-Topic (AJT) model to take both authors and journals into consideration of topic analysis. For the study, we collect the 6,360 full-text articles from PubMed Central and select the top 15 journals on Oncology. By applying AJT model, we identify what the major topics are shared among researchers in Oncology and which authors and journal lead the idea exchange in sub-disciplines of Oncology.
|Number of pages||9|
|Journal||CEUR Workshop Proceedings|
|Publication status||Published - 2016|
|Event||Joint Workshop on Bibliometric-Enhanced Information Retrieval and Natural Language Processing for Digital Libraries, BIRNDL 2016 - Newark, United States|
Duration: 2016 Jun 23 → …
All Science Journal Classification (ASJC) codes
- Computer Science(all)