Encoding Lineage in Scholarly Articles

The development of new scientific concepts today is an out-come of the accumulated knowledge built over time. Every scientific domain requires understanding of the trends of the dependencies between its subdomains. Analyses of trends to capture such dependencies using conventional document modeling techniques is a challenging task due to two rea-sons: (1) conventional vector-space modeling based represen-tation of documents does not realize the history of the con-tent, and (2) neither feature-level nor document-level causal-ity is provided with any digital library metadata or citation network. In this paper, we propose an intuitive temporal rep-resentation of a scientific article that encodes inherent his-toric characteristics of the content. This intuitive representa-tion of each document is then leveraged to discover causal relationships between scientific articles. In addition, we pro-vide a mechanism to explore the lineage of each document in terms of other previously published documents, which illus-trates how the theme of the document under analysis evolved over time. Empirical studies reported in the paper show that the proposed technique identifies meaningful causal relation-ships and discovers meaningful lineage in the scientific litera-ture that could not be discovered through the citation network of the articles.