Mining Scholarly Publications for Research Evaluation

Herrmannova, Drahomira (2018). Mining Scholarly Publications for Research Evaluation. PhD thesis The Open University.



Scientific research can lead to breakthroughs that revolutionise society by solving long-standing problems. However, investment of public funds into research requires the ability to clearly demonstrate beneficial returns, accountability, and good management. At the same time, with the amount of scholarly literature rapidly expanding, recognising key research that presents the most important contributions to science is becoming increasingly difficult and time-consuming. This creates a need for effective and appropriate research evaluation methods. However, the question of how to evaluate the quality of research outcomes is very difficult to answer and despite decades of research, there is still no standard solution to this problem.

Given this growing need for research evaluation, it is increasingly important to understand how research should be evaluated, and whether the existing methods meet this need. However, the current solutions, which are predominantly based on counting the number of interactions in the scholarly communication network, are insufficient for a number of reasons. In particular, they struggle in capturing many aspects of the academic culture and often significantly lag behind current developments.

This work focuses on the evaluation of research publications and aims at creating new methods which utilise publication content. It studies the concept of research publication quality, methods assessing the performance of new research publication evaluation methods, analyses and extends the existing methods, and, most importantly, presents a new class of metrics which are based on publication manuscripts. By bridging the fields of research evaluation and text- and data-mining, this work provides tools for analysing the outcomes of research, and for relieving information overload in scholarly publishing.

Viewing alternatives

Download history


Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions

Item Actions