Seek and You Shall Find: Design & Evaluation of a Context-Aware Interactive Search Companion

TL;DR

The paper targets the problem of poor search effectiveness and critical evaluation in high-stakes domains, driven by limited search literacy. It introduces a context-aware interactive search companion that integrates lightweight, predefined guidance into SERPs to promote clarifying intent, better query formulation, result exploration, and bias awareness. In a preregistered between-groups study with 170 participants on a medical task, overall accuracy did not improve, but the companion increased exploration and query reformulation, especially for harder tasks, indicating enhanced search literacy and reflective behavior. The work demonstrates the potential of micro-learning, low-friction guidance to empower users and informs future UI designs and personalization for assistive search systems, including integration with GenAI and browser-based deployments.

Abstract

Many users struggle with effective online search and critical evaluation, especially in high-stakes domains like health, while often overestimating their digital literacy. Thus, in this demo, we present an interactive search companion that seamlessly integrates expert search strategies into existing search engine result pages. Providing context-aware tips on clarifying information needs, improving query formulation, encouraging result exploration, and mitigating biases, our companion aims to foster reflective search behaviour while minimising cognitive burden. A user study demonstrates the companion's successful encouragement of more active and exploratory search, leading users to submit 75 % more queries and view roughly twice as many results, as well as performance gains in difficult tasks. This demo illustrates how lightweight, contextual guidance can enhance search literacy and empower users through micro-learning opportunities. While the vision involves real-time LLM adaptivity, this study utilises a controlled implementation to test the underlying intervention strategies.

Figures (1)

• Figure 1: Overview of all interactive search tips. For illustration purposes, these are presented in their expanded form to show all additional content if users click on 'Show More'. (Numbers in red are not part of the companion but used for referencing)