Query transformations and their role in Web searching by the general public

Introduction - This paper reports preliminary research in a primarily experimental study of how the general public search for information on the Web. The focus is on the query transformation patterns that characterise searching.

Method - In this work, we have used transaction logs from the Excite search engine to develop methods for analysing query transformations that should aid the analysis of our ongoing experimental work. Our methods involve the use of similarity techniques to link queries with the most similar previous query in a train. The resulting query transformations are represented as a list of codes representing a whole search.

Analysis - It is shown how query transformation sequences can be represented as graphical networks and some basic statistical results are shown. A correlation analysis is performed to examine the co-occurrence of Boolean and quotation mark changes with the syntactic changes.

Results - A frequency analysis of the occurrence of query transformation codes is presented. The connectivity of graphs obtained from the query transformation is investigated and found to follow an exponential scaling law. The correlation analysis reveals a number of patterns that provide some interesting insights into Web searching by the general public.

Conclusion - We have developed analytical methods based on query similarity that can be applied to our current experimental work with volunteer subjects. The results of these will form part of a database with the aim of developing an improved understanding of how the public search the Web.