Cited-works-lists in Humanities dissertations are typically the result of five years of work. However, despite the long-standing tradition of reference mining, no research has systematically untapped the bibliographic data of existing electronic thesis collections. One of the main reasons for this is the difficulty of creating a tagged gold standard for the around 300 pages long theses. In this short paper, we propose a page-based random forest (RF) prediction approach which uses a new corpus of Literary Studies Dissertations from Germany. Moreover, we will explain the handcrafted but computationally informed feature-selection process. The evaluation demonstrates that this method achieves an F1 score of 0.88 on this new dataset. In addition, it has the advantage of being derived from an interpretable model, where feature relevance for prediction is clear, and incorporates a simplified annotation process.

Title from PDF of title page. / Document formatted into pages; contains 215 pages. / Originally submitted in HTML and can be accessed at http://www.lib.usf.edu/ETD-db/theses/available/etd-04102002-122814/unrestricted/default.htm / Thesis (Ph.D.)--University of South Florida, 2002. / Includes bibliographical references. / Text (Electronic thesis) in PDF format. / ABSTRACT: Electronic theses and dissertations (ETDs) are an evolving genre of graduate student research that is gaining widespread acceptance among universities in the international community. ETDs are also beginning to diffuse slowly among American universities; however, a number of issues continue to work against more rapid adoption among intitutions in the United States. / ABSTRACT: This dissertation examines ETDs as an evolving electronic research genre by (1) historicizing the situated development of its predecessor, the traditional print dissertation, in nineteenth century German and American Universities; (2) reporting on the current state of the Networked Digital Library of Electronic Theses and Dissertations, an initiative of Virginia Polytechnic University; (3) analyzing ETDs as a technological innovation undergoing the diffusion process according to Emmet Roger's Diffusion of Innovation Theory; and (4) presenting the results of an ETD pilot project case study carried out at the University of South Florida. / System requirements: World Wide Web browser and PDF reader. / Mode of access: World Wide Web.