Multilingual News–An Investigation of Consumption, Querying, and Search Result Selection Behaviors

ABSTRACT

With the global expansion of the Internet and the World Wide Web, users are becoming increasingly diverse, particularly in terms of languages. In fact, there are now many users online who are polyglots, i.e. users who are proficient in more than one language. However, even such multilingual users often continue to suffer from unbalanced and fragmented news information, as traditional news access systems seldom allow users to simultaneously search for and/or compare news in different languages, even though prior research results have shown that multilingual users make significant use of each of their languages when generally searching for information online.

The research presented in this paper provides the first investigation of multilingual news consumption, as well as a detailed analysis of multilingual querying and search result selection behaviors. In particular, through a set of 2 phases of crowdsourced user studies, this paper presents the first human-centered studies in multilingual news access, aiming to drive the development of personalized multilingual news access systems that better support each individual user.

Acknowledgments

We want to thank our user study participants who generously shared their time and experience for this research project. We have no competing interests. The datasets used and analyzed during the current study are available from the corresponding author on reasonable request.

Notes

1. www.internetlivestats.com/internet-users/.

2. https://factfinder.census.gov.

3. Eurostat Foreign language learning statistics: ec.europa.eu/eurostat/statistics-explained/index.php/Foreign_language_learning_statistics.

4. w3techs.com/technologies/overview/content_language/all.

5. http://www.internetlivestats.com/internet-users-by-country/.

6. CLEF (Conference and Labs of the Evaluation Forum): www.clef-initiative.eu/.

7. http://www.figure-eight.com (originally known as CrowdFlower).

8. http://www.internetworldstats.com/stats7.htm.

9. While the accuracy of self-rated proficiency may potentially differ from person to person, this measure is often used in multilingual studies (e.g. [Chu et al., 2015][Hale & Eleta, 2017][Steichen & Freund, 2015).

10. http://trends.google.com/trends/trendingsearches/realtime?geo=US&category=all.

11. https://index.baidu.com.

12. http://azure.microsoft.com/en-us/services/cognitive-services/bing-web-search-api/.

Additional information

Notes on contributors

Chenjun Ling

Chenjun Ling Ph.D. candidate in the Computer Science and Engineering at Santa Clara University. Her research interests include Information Retrieval, HCI, and Data Science.

Ben Steichen

Ben Steichen is an Assistant Professor in the Computer Science Department at California State Polytechnic University, Pomona. Dr. Steichen’s research focuses on Human-Centered Computing and Personalized Information Access, which involves techniques and concepts from the fields of HCI, Information Retrieval & Visualization, and Web & Data Science.

Silvia Figueira

Silvia Figueira is a Professor of Computer Science and Engineering at Santa Clara University and the director of the SCU Frugal Innovation Hub. Her research is in the area of performance evaluation and prediction, recently with a focus on energy efficiency.