Bursty Topic Detection in Cancer Field Based on Multi-features of Burst Words

Abstract Background:With the increase in the amounts and types of medical information resources and the interdisciplinarity of the related works,it has become increasingly challenging for researchers and information personnel to grasp the theme development.Considering the prominent position of cancer field among all the subject areas in scientific research, and in order to carry out a new bursty topic detection method, the author proposes a method based on the multi-features of burst words and demonstrates its operating process. Methods:The main stages in the process include concept mapping,topic words extraction,burst words extraction,burst topics identification.This paper continues to take the study of breast neoplasms treatment research as a field to test the new method for identifying burst topics in medical research. Result:With this method,we identified four burst topics in breast neoplasms treatment research, including Molecular Targeted Therapy of Triple Negative Breast Neoplasms,molecular pharmacology of Triple Negative Breast Neoplasms,Immunological Antineoplastic Agents therapeutic use of Breast Neoplasms and Surgery therapy of Breast Neoplasms. Conclusion:The test results are highly concordant with authoritative literature reviews in the field and are further confirmed by interviews with the field’s leading experts,thus verifying the reliability of the techniques and approaches proposed by the study.