Invited Speakers
Keynote speakers
Entity Based User Interfaces for Resourceful Information Exploration
Text based retrieval in a query and response paradigm has been criticised for its limited ability to support exploratory search. The talk proposes a new approach characterised by entity modelling of information, conversational and synergic human-computer interaction, combining search and recommendation, and mapping relationships and representations of intent, queries and results. To demonstrate these features the talk discusses recent systems we developed including an interactive model of intent represented by keywords used to direct exploratory search, a system utilising entity based parallel search streams, and an interactive map visualisation for multi-aspect information retrieval. The talk will summarise the principles embodied in the presented system towards a framework that considers principle of how to employ entities in information exploration.
Improving interactive information discovery
Many prior works in recommender systems and information retrieval focussed on improving the accuracy of rating predictions and search results. However, topics related to interfaces and user interaction received less attention. In our work, we considered computational ways for improving the interaction of users with the recommendation lists or Web search results, aiming to devise a method that simplifies and shortens information discovery for users. We present one practical application of a generalised linear search (combination of the established linear and generalised search approaches) evaluated both with offline datasets and in an online user study. We also discuss how similar interactive information discovery approaches can be applied to scenarios beyond recommender systems and Web search.