Using Google™ facets as implicit feedback for query expansion in database searching

Abstract

The purpose of this study is to examine the Google facets, namely the suggestions found occasionally under the section "Searches related to" on the Google results page. The study focuses on whether they constitute good candidate terms for implementing expansion of queries submitted to databases. The thought behind this is to benefit from the Google recommendations and see if they relate in a satisfactory proportion with the initial user queries so that the first can provide reliable information on the context of the second, especially in cases where no results are returned for the initial query. During our study we have recorded the conditions under which Google creates facets, their informational characteristics as well as various problems concerning the available features of the Greek version of Google. After submitting our collection of 750 zero-hit queries to Google, we retrieved facets for 302 of them, which correspond to 95 of the initial users' queries. Finally, we found that 12.67% of otherwise zero-hit queries would return results with the use of Google facets.