Condorcet Fusion for Blog Opinion Retrieval

Blogs have been popular social networking platforms in recent years. Blog opinion retrieval is one of the key issues that needs to be solved. In this paper, we investigate if the Condorcet fusion and the weighted Condorcet fusion can be used for effectiveness improvement of blog opinion retrieval. The experiments carried out with the data set from the TREC 2008 Blog track show that the Condorcet fusion is effective and the weighted Condorcet fusion, with its weights trained by linear discriminant analysis, is very effective. Both of them outperform the best component result by a clear margin.