Finding Similar Queries to Satisfy Searches Based on Query Traces

Abstract

Many agree that the relevancy of current search engine results needs significant improvement. On the other hand, it is also true that finding the appropriate query for the best search engine result is not a trivial task. Often, users try different queries until they are satisfied with the results. This paper presents a method for building a system for automatically suggesting similar queries when results for a query are not satisfactory. Assuming that every search query can be expressed differently and that other users with similar information needs could have already expressed it better, the system makes use of collaborative knowledge from different search engine users to recommend new ways of expressing the same information need. The approach is based on the notion of quasi-similarity between queries since full similarity with an unsatisfactory query would lead to disappointment. We present a model for search engine queries and a variety of quasi-similarity measures to retrieve relevant queries.