Please use this identifier to cite or link to this item: doi:10.22028/D291-29212
Title: Demographic Inference and Representative Population Estimates from Multilingual Social Media Data
Author(s): Wang, Zijian
Hale, Scott
Adelani, David
Grabowicz, Przemyslaw
Hartman, Timo
Flöck, Fabian
Jurgens, David
Editor(s): Liu, Ling
Language: English
Title: The World Wide Web Conference
Pages: 2056-2067
Publisher/Platform: ACM
Year of Publication: 2019
Free key words: Demographics
Social Media
Latent Attribute Inference
Inclusion Probabilities
Deep Learning
DDC notations: 400 Language, linguistics
Publikation type: Conference Paper
Abstract: Social media provide access to behavioural data at an unprecedented scale and granularity. However, using these data to understand phenomena in a broader population is difficult due to their non-representativeness and the bias of statistical inference tools towards dominant languages and groups. While demographic attribute inference could be used to mitigate such bias, current techniques are almost entirely monolingual and fail to work in a global environment. We address these challenges by combining multilingual demographic inference with post-stratification to create a more representative population sample. To learn demographic attributes, we create a new multimodal deep neural architecture for joint classification of age, gender, and organization-status of social media users that operates in 32 languages. This method substantially outperforms current state of the art while also reducing algorithmic bias. To correct for sampling biases, we propose fully interpretable multilevel regression methods that estimate inclusion probabilities from inferred joint population counts and ground-truth population counts. In a large experiment over multilingual heterogeneous European regions, we show that our demographic inference and bias correction together allow for more accurate estimates of populations and make a significant step towards representative social sensing in downstream applications with multilingual social media.
DOI of the first publication: 10.1145/3308558.3313684
URL of the first publication:
Link to this record: urn:nbn:de:bsz:291--ds-292128
ISBN: 978-1-4503-6674-8
Date of registration: 8-Jul-2022
Faculty: P - Philosophische Fakultät
Department: P - Sprachwissenschaft und Sprachtechnologie
Professorship: P - Prof. Dr. Dietrich Klakow
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
File Description SizeFormat 
p2056-wang (1).pdf2,93 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons