We present a new method for identifying the latent categorization of items
based on their rankings. Complimenting a recent work that uses a Dirichlet
prior on preference vectors and variational inference, we show that this
problem can be effectively dealt with using existing community detection
algorithms, with the communities corresponding to item categories. In
particular we convert the bipartite ranking data to a unipartite graph of item
affinities, and apply community detection algorithms. In this context we modify
an existing algorithm - namely the label propagation algorithm to a variant
that uses the distance between the nodes for weighting the label propagation -
to identify the categories. We propose and analyze a synthetic ordinal ranking
model and show its relation to the recently much studied stochastic block
model. We test our algorithms on synthetic data and compare performance with
several popular community detection algorithms. We also test the method on real
data sets of movie categorization from the Movie Lens database. In all of the
cases our algorithm is able to identify the categories for a suitable choice of
tuning parameter.

本文提出一种新的基于排名的潜在分类识别方法，通过对偏好向量的 Dirichlet 先验和变分推断，以及利用现有的社区检测算法将双部排名数据转化为单部物品相似度图，并分析一种合成序数排名模型及其与随机块模型之间的关系，然后通过将标签传播算法修改为使用节点之间距离进行标签传播的变体来识别类别，并使用几种流行的社区检测算法进行性能比较。