Supporting Exploratory Search with a Visual User-Driven Approach

Abstract

Whenever users engage in gathering and organizing new information, searching and browsing activities emerge at the core of the exploration process. As the process unfolds and new knowledge is acquired, interest drifts occur inevitably and need to be accounted for. Despite the advances in retrieval and recommender algorithms, real-world interfaces have remained largely unchanged: results are delivered in a relevance-ranked list. However, it quickly becomes cumbersome to reorganize resources along new interests, as any new search brings new results. We introduce an interactive user-driven tool that aims at supporting users in understanding, refining, and reorganizing documents on the fly as information needs evolve. Decisions regarding visual and interactive design aspects are tightly grounded on a conceptual model for exploratory search. In other words, the different views in the user interface address stages of awareness, exploration, and explanation unfolding along the discovery process, supported by a set of text-mining methods. A formal evaluation showed that gathering items relevant to a particular topic of interest with our tool incurs in a lower cognitive load compared to a traditional ranked list. A second study reports on usage patterns and usability of the various interaction techniques within a free, unsupervised setting.

Understanding the effects of control and transparency in searching as learning

“…uRank enables users to discover and refine their search interests by way of interactions with extracted keywords and provides a visual ranking metaphor to explain document relevance with respect to evolving information needs. User studies report lower cognitive workload, as well as similar relevance assessments for subjects working with uRank and a baseline SERP condition [18,19].…”

“…The benchmark system employed in this work builds upon the uRank system [18,19], which promotes a user-driven approach influenced by work on control and transparency in interactive RS. uRank enables users to discover and refine their search interests by way of interactions with extracted keywords and provides a visual ranking metaphor to explain document relevance with respect to evolving information needs.…”

“…For this study we replicated functionalities of uRank [18,19], a user-driven exploratory search tool [18], which promotes control and transparency in the UI. Control refers to the possibility for the user to influence the decisions of the system, whereas transparency is the ability of the system to explain to the user how it works.…”

“…User selected keywords (and their weights) are the inputs of a content-based (CB) model that re-ranks results in real-time. (For further details refer to [19]). A previous version of the tool [18] made it possible to visualize and select co-occurring terms in a two-step mechanism (combination of clicks and drag-and-drop).…”

“Mirror, mirror on my search...”: Data-Driven Reflection and Experimentation with Search Behaviour

“…Both the design of our widget for reflective search (description below) and research question as stated above, are based on this understanding. The widget for reflective search that we have developed is embedded into a newly developed search platform [24] that offers multiple search interfaces, such as the typical text search, a graph visualisations of search lists, an interactively ranked visualisation of search results based on keywords according to di Sciascio et al [22], a tag cloud visualisation based on keywords' frequency, and a bar chart visualisation presenting properties of the retrieved documents. While using this custom search platform constrained the available content for searching, it enabled us to track user interaction with the widget in a fine-granular manner.…”