A Study on User-Controllable Social Exploratory Search

Abstract

Information-seeking tasks with learning or investigative purposes are usually referred to as exploratory search. Exploratory search unfolds as a dynamic process where the user, amidst navigation, trial-and-error and on-the-fly selections, gathers and organizes information (resources). A range of innovative interfaces with increased user control have been developed to support exploratory search process. In this work we present our attempt to increase the power of exploratory search interfaces by using ideas of social search, i.e., leveraging information left by past users of information systems. Social search technologies are highly popular nowadays, especially for improving ranking. However, current approaches to social ranking do not allow users to decide to what extent social information should be taken into account for result ranking. This paper presents an interface that integrates social search functionality into an exploratory search system in a user-controlled way that is consistent with the nature of exploratory search. The interface incorporates control features that allow the user to (i) express information needs by selecting keywords and (ii) to express preferences for incorporating social wisdom based on tag matching and user similarity. The interface promotes search transparency through color-coded stacked bars and rich tooltips. In an online study investigating system accuracy and subjective aspects with a structural model we found that, when users actively interacted with all its control features, the hybrid system outperformed a baseline content-based-only tool and users were more satisfied.

Understanding the effects of control and transparency in searching as learning

“…Our results align to related research on UX with RS and search systems, which reported similar effects of personal characteristics: experienced users understand advanced features better and are able to perceive more control over the system [17,38,69]. Specifically in information-seeking area investigated the effects of search experience and expertise (which are not necessarily the same [6]) reporting better task outcomes [6,32], lower task completion time [62] and more effective strategies [44,50].…”

“…For example, Knijnenburg et al [38] hypothesized that perceived inspectability in interactive recommender systems influences the amount o perceived control. The UX model in di Sciascio et al [17] considers that perceived control in social-enhanced search systems contributes to increase the perception of transparency (Perc. Control → Perc.…”

“…However, this set of studies focused on some aspect of performance, whereas our focus was to assess the effect of self-assessed expertise on different dimensions of the user experience. Our approach is similar to di Sciascio et al [17], except that we used a proper scale construct (formed by 3 items instead of a single-item indicator).…”

“…Displaying social information helps to enrich the search process, for example by augmenting results with social cues [24,49,65] or visualizing social links [20]. Also, the social-enhanced version of uRank applies control mechanisms and fine-grained explanations for multiple sources of relevance [16,17]. Allowing users to decide how content-based and social methods influence the final document ranking has a positive effect on transparency, user experience and system performance.…”

“…Perceived learning is not a concept visited in exploratory search. Lastly, UX is largely evaluated for RS [38,39] and lately social exploratory search [16,17], but not for the case of searching as learning.…”