Supporting the Modern Polyglot

Abstract

The unrelenting rise in online user diversification has generated tremendous new challenges for search system providers. Among these, the need to address multiple user language abilities and preferences is paramount. The majority of research on multilingual search has so far focused on improving retrieval and translation techniques in cross-language information retrieval. However, less research has focused on the human-computer interaction aspects of multilingual search, particularly in terms of multilingual result display interfaces. To address this research gap, this paper presents a comparison of 5 different search interface designs for multilingual search. We analyze and evaluate these interfaces through a crowd-based experiment involving 885 participants. Our results show that the common approach of interleaving multilingual results is in fact the least preferred, whereas single-page displays with clear language separation are most preferred. In addition, we show that user proficiency and search content type play an important role in user preferences, and that different interfaces elicit different user behaviors.