Experiments on Rating Conferences with CORE and DBLP.

Conferences are the lifeblood of research in computer science and they vary in reputation and perceived quality. One guidance for conferences is conference ratings which attempt to classify conferences by some quality measures. In this paper, we present a preliminary investigation on the possibility of systematic unbiased and automatic conference rating algorithms using random walks which give relatedness score for a conference relative to a reference conference (pivot). Our experiments show that just using a simple algorithm on the DBLP bibliographic database, it is possible to get ratings which correlate well with the CORE and CCF conference ratings.