A structured representation of researcher interests for filtering of research journals and proceedings papers

Abstract

SUMMARYThere is increasing demand for a filtering system for scientific papers that can be utilized by researchers in business organizations. In conventional paper filtering systems, relevant papers are selected without sufficiently representing the researcher's interest structure, and thus the accuracy of filtering is not satisfactory. The purpose of this paper is to solve this problem and to propose a method of providing a structured representation of the researcher's interests by clustering papers of interest to the researcher. The similarity of newly appearing papers to the structured representation is calculated and the result of filtering is presented with rankings, resulting in both accuracy and convenience of use. With three researchers as the participants, an experimental evaluation of the filtering was performed by an N-fold cross-validation test, using 2 years of papers from proceedings journals in information science. An accuracy of 44% to 69% was achieved, 9.6% to 17.9% higher than the results of a filtering system without clustering used as the baseline.

Paper filtering method using features of coauthor research group, subject category, and terminology

“…In the future, we plan to work toward a practical implementation of the filtering system by further accuracy improvement, using enhancement based on profile structurization [5] and other effective methods, and toward a more intuitive representation of the filtering results to users by refining the user interface.…”

“…If the score is high, the document is considered relevant and is submitted to the user. This approach is presented in a number of studies, whose subjects include recommending new Web sites to the user based on information about sites of interest provided by the user [1][2][3][4], and paper profiling aiming at higher accuracy by structuring the user's profile [5]. In these studies, the setting of filtering conditions by the user is limited to preregistration of several relevant documents, and therefore Requirement A is basically met.…”

Tsinghua University launches School of Public Health

“…By extracting citation fields, we can establish collaboration networks among researchers and conduct various studies [5,6], such as research community detection [7], research trends prediction [8], and topics analysis [9]. While we may obtain citation information from bibliographic databases and multiple user-generated resources, this information is vexed by several problems: the limited coverage of disciplines and researchers, inconsistent citation styles, incomplete sentence syntax, and insufficient training data.…”