Exploring Topic-language Preferences in Multilingual Swahili Information Retrieval in Tanzania

Habitual switching of languages is a common behaviour among polyglots when searching for information on the Web. Studies in information retrieval (IR) and multilingual information retrieval (MLIR) suggest that part of the reason for such regular switching of languages is the topic of search. Unlike survey-based studies, this study uses query and click-through logs. It exploits the querying and results selection behaviour of Swahili MLIR system users to explore how topic of search (query) is associated with language preferences—topic-language preferences. This article is based on a carefully controlled study using Swahili-speaking Web users in Tanzania who interacted with a guided multilingual search engine. From the statistical analysis of queries and click-through logs, it was revealed that language preferences may be associated with the topics of search. The results also suggest that language preferences are not static; they vary along the course of Web search from query to results selection. In most of the topics, users either had significantly no language preference or preferred to query in Kiswahili and changed their preference to either English or no preference for language when selecting/clicking on the results. The findings of this study might provide researchers with more insights in developing better MLIR systems that support certain types of users and in certain scenarios.