Simplified Relative Citation Ratio for Static Paper Ranking: UFMG/LATIN at WSDM Cup 2016
This work addresses static paper ranking for academic search, but it is incremental as it simplifies an existing metric.
The authors tackled the problem of static paper ranking by proposing S-RCR, a simplified version of the Relative Citation Ratio based on co-citation networks, which improved efficiency while maintaining reasonable effectiveness and was used to rank over 120 million papers, achieving 3rd place in the first phase of the WSDM Cup 2016.
Static rankings of papers play a key role in the academic search setting. Many features are commonly used in the literature to produce such rankings, some examples are citation-based metrics, distinct applications of PageRank, among others. More recently, learning to rank techniques have been successfully applied to combine sets of features producing effective results. In this work, we propose the metric S-RCR, which is a simplified version of a metric called Relative Citation Ratio --- both based on the idea of a co-citation network. When compared to the classical version, our simplification S-RCR leads to improved efficiency with a reasonable effectiveness. We use S-RCR to rank over 120 million papers in the Microsoft Academic Graph dataset. By using this single feature, which has no parameters and does not need to be tuned, our team was able to reach the 3rd position in the first phase of the WSDM Cup 2016.