This is the second edition of the Workshop on Exploratory Search and Interactive Data Analytics (ESIDA). This series of workshops emerged as a response to the growing interest in developing new methods and systems that allow users to interactively explore large volumes of data, such as documents, multimedia or specialised collections, such as biomedical datasets. There are various approaches to supporting users in this interactive environment ranging from the development of new algorithms through visualisation methods to analysing users' search patterns. The overarching goal of ESIDA is to bring together researchers working in areas that span across multiple facets of exploratory search and data analytics to discuss and outline research challenges for this novel area.
4 ICIC-CONICET BACKGROUND While retrieval techniques operating on text or semantic annotations have become an industry standard, traditional search by keyword query becomes cumbersome for other forms of data (e.g. images, video, music) and even for textual data in the case of ambiguous queries (e.g. bank referring to side of a river or a financial institution). Also, in complex scenarios, or when the path from data to decision is not clear, exploratory search is necessary to understand and seek information interactively. Therefore, by actively engaging the user in the information retrieval loop, the user can explore a given dataset more easily as well as gradually direct their search to a more specific area of the search space. ©2018. Copyright for the individual papers remains with the authors. Copying permitted for private and academic purposes.
ESIDA’18, March 11, 2018, Tokyo, Japan
Despite an increasing interest in exploratory search and
interactive data analytics [
What is the scope of exploratory search [
The first keynote, by Giulio Jacucci (University of Helsinki, Finland), was titled “Entity Based User Interfaces for Resourceful Information Exploration”. The talk proposed 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 discussed recent systems developed by the speaker’s team 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 summarised the principles embodied in the presented system towards a framework that considers principle of how to employ entities in information exploration.
The second keynote, by Shlomo Berkovsky (CSIRO, Australia), was titled “Improving interactive information discovery”. The talk presented 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. One practical application of a generalised linear search (combination of the established linear and generalised search approaches) was presented, evaluated both with offline datasets and in an online user study. It was discussed how similar interactive information discovery approaches can be applied to scenarios beyond recommender systems and Web search.
Sense making of document collections was the subject of
two papers. Hierarchically organized social media
discussions were visualized as scatter plots via dimensionality
reduction [