Exploratory search systems (ESSs), such as Discovery Hub or 3cixty are search engines that help users to explore a topic of interest. These ESSs differ from classic search engines such as Google, Bing or Yahoo!, which rather support lookup searches. A shortcoming of current evaluation methods is that they cannot be used to determine if an exploratory search system can effectively help the user in performing exploratory search (ES) tasks. One of the reasons is that these methods are not based on a suitable model of exploratory search process, or are too close to lookup process models. The main objective of this thesis is to propose for the designers of ESSs (i.e. computer scientists) user-centered evaluation methods of exploratory search systems based on an "approximate" model of ES process. We propose here: 1) a model of ES we designed from the analysis of ES definitions and existing models of information seeking; 2) the two model-based methods we designed, including: a) an inspe ction method with heuristics (evaluation without users and from the first sketches of the ESS); b) a user testing method with users. The evaluation of the model and the methods have demonstrated their usefulness. We also present two tools facilitating the use of the heuristics of ES: 1) an online evaluation checklist; 2) A Google Chrome plugin "CheXplore".
Evaluating exploratory search engines: designing a set of user-centered methods based on a modeling of the exploratory search process
© EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Thesis and is available at :
PERMALINK : https://www.eurecom.fr/publication/5737