Frequency of sentential contexts vs. frequency of query terms in opinion retrieval

Document Type

Conference Proceeding

Publication Title

WEBIST 2011 - Proceedings of the 7th International Conference on Web Information Systems and Technologies


Many opinion retrieval techniques use frequency of query terms as a measurement for detecting documents that contain opinion. However, using frequency of query terms leads to bias in context-dependent opinion retrieval such that all documents containing query terms are retrieved, regardless of contextual relevance to the intent of the human seeking the opinion. This can be described as non-contextual relevance problem in opinion retrieval systems such as Google Blogs Search and Technorati Blog Directory. Sentence-level contextual understanding and grammatical dependencies need be considered to ensure documents retrieved contain large proportion of textual contents that have the same underlying meaning with the given query instead of using frequency of individual query terms. Thus, we present specific challenges with state-of-the-art opinion retrieval techniques that rely on frequency of query terms and we propose a grammar-based technique for efficient context-dependent opinion retrieval. We believe our proposed technique can solve the non-contextual relevance problem common to opinion retrieval systems, and can be used for context-dependent retrieval such as expert search systems, faceted-opinion retrieval, opinion trend analytic, and personalized web search.

First Page


Last Page


Publication Date


This document is currently not available here.