A task completion engine to enhance search session support for air traffic work tasks

Tools

Moshfeghi, Yashar and Rothfeld, Raoul and Azzopardi, Leif and Triantafillou, Peter; Jose, Joemon M. and Hauff, Claudia and Altıngovde, Ismail Sengor and Song, Dawei and Albakour, Dyaa and Watt, Stuart and Tait, John, eds. (2017) A task completion engine to enhance search session support for air traffic work tasks. In: European Conference on Information Retrieval. Lecture Notes in Computer Science, 10193 . Springer International Publishing AG, GBR, pp. 278-290. ISBN 9783319566078 (https://doi.org/10.1007/978-3-319-56608-5_22)

[thumbnail of Moshfeghi-etal-ECIR-2017-A-task-completion-engine-to-enhance-search-session-support-for-air-traffic-work-tasks]
Preview
 Text. Filename: Moshfeghi_etal_ECIR_2017_A_task_completion_engine_to_enhance_search_session_support_for_air_traffic_work_tasks.pdf
Accepted Author Manuscript
Download (756kB)| Preview

Abstract

Providing support for users during their search sessions has been hailed as a major challenge in interactive information retrieval (IIR). Providing such support requires considering the context of the search and facilitating the work task at hand. In this paper, we consider the work tasks associated with air traffic analysts, who perform numerous searches using a multifaceted search interface in order to acquire business intelligence regarding particular events and situations. In particular, we develop a novel task completion engine and seamlessly incorporated it within a current air traffic search system to facilitate the comparison of information objects found. In a study with 24 participants, we found that they completed the complex work task faster using the comparison feature, but for simple work tasks, participants were slower. However, participants reported (statistically) significantly higher satisfaction and had (statistically) significantly higher accuracy using the search system equipped with task completion engine. These findings help to steer systems to provide a better support to users in their search process.

CORE (COnnecting REpositories)