A Potential Approach to Overcome Data Limitation in Scientific Publication Recommendation

Abstract

Data are essential for the experiments of relevant scientific publication recommendation methods but it is difficult to build ground truth data. A naturally promising solution is using publications that are referenced by researchers to build their ground truth data. Unfortunately, this approach has not been explored in the literature, so its applicability is still a gap in our knowledge. In this research, we systematically study this approach by theoretical and empirical analyses. In general, the results show that this approach is reasonable and has many advantages. However, the empirical analysis shows both positive and negative results. We conclude that, in some situations, this is a useful alternative approach toward overcoming data limitation. Based on this approach, we build and publish a dataset in computer science domain to help advancing other researches.