Learning hidden variable models for blog retrieval
Mengqiu Wang · 2010
We describe probabilistic models that leverage individual blog post evidence to improve blog seed retrieval performances. Our model offers a intuitive and principled method to combine multiple posts in scoring a whole blog site by treating individual posts as hidden variables. When applied to the seed retrieval task, our model yields state-of-the-art results on the TREC 2007 Blog Distillation Task dataset.