Aggregating Multiple Opinion Evidence in Proximity-Based Opinion Retrieval

Blog post opinion retrieval is the problem of ranking blog posts according to the likelihood that the post is relevant to the query and that the author was expressing an opinion about the topic (of the query). A recent study has proposed a method for finding the opinion density at query term positions in a document which uses the proximity of query term and opinion term as an indicator of their relatedness. The maximum opinion density between different query positions was used as an opinion score of the whole document. In this paper we investigate the effect of exploiting multiple opinion evidence of a document. We propose using the ordered weighted averaging (OWA) operator in order to combine the opinion score of different query positions for a final score of a document, in the proximity-based opinion retrieval system.