Using generalised stochastic Petri nets to model and analyse search behaviour patterns

Abstract

In recent years, discovering and understanding users' search behaviour attract attention in the research community. Different approaches have been proposed for: 1) learning and modelling how users search; 2) predicting future users' search behaviour patterns, most of them based on statistical analysis and application of data mining techniques on a query log data. In this paper, we focus on the application of the class of generalised stochastic Petri nets (GSPN) on already discovered users' search behaviour patterns, where consecutive actions for query reformulation during the course of a single user session are considered as transitions. An understanding of the motives underlying user actions can help designers to better accommodate to what appears to be chaos: make available those capabilities that best support the range of known behaviour patterns.