Auditing the Information Quality of News-Related Queries on the Alexa Voice Assistant

要旨

Smart speakers are becoming increasingly ubiquitous in society and are now used for satisfying a variety of information needs, from asking about the weather or traffic to accessing the latest breaking news information. Their growing use for news and information consumption presents new questions related to the quality, source diversity, and comprehensiveness of the news-related information they convey. These questions have significant implications for voice assistant technologies acting as algorithmic information intermediaries, but systematic information quality audits have not yet been undertaken. To address this gap, we develop a methodological approach for evaluating information quality in voice assistants for news-related queries. We demonstrate the approach on the Amazon Alexa voice assistant, first characterising Alexa's performance in terms of response relevance, accuracy, and timeliness, and then further elaborating analyses of information quality based on query phrasing, news category, and information provenance. We discuss the implications of our findings for the design of future smart speaker devices and for the consumption of news information via such algorithmic intermediaries more broadly.

著者
Henry Kudzanai. Dambanemuya
Northwestern University, Evanston, Illinois, United States
Nicholas Diakopoulos
論文URL

https://doi.org/10.1145/3449157

動画

会議: CSCW2021

The 24th ACM Conference on Computer-Supported Cooperative Work and Social Computing

セッション: Algorithmic Auditing and Responsible AI

Papers Room D
8 件の発表
2021-10-25 21:00:00
2021-10-25 22:30:00