A Task Completion Engine to Enhance Search Session Support for Air Traffic Work Tasks

Abstract

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