Analysis of Faces in a Decade of US Cable TV News

Cable (TV) news reaches millions of US households each day. News stakeholders such as communications researchers, journalists, and media monitoring organizations are interested in the visual content of cable news, especially who is on-screen. Manual analysis, however, is labor intensive and limits the size of prior studies. We conduct a large-scale, quantitative analysis of the faces in a decade of cable news video from the top three US cable news networks (CNN, FOX, and MSNBC), totaling 244,038 hours between January 2010 and July 2019. Our work uses technologies such as automatic face and gender recognition to measure the "screen time" of faces and to enable visual analysis and exploration at scale. Our analysis method gives insight into a broad set of socially relevant topics. For instance, male-presenting faces receive much more screen time than female-presenting faces (2.4x in 2010, 1.9x in 2019). To make our dataset and annotations accessible, we release a public interface at https://tvnews.stanford.edu that allows the general public to write queries and to perform their own analyses.

[1]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[2]  Erez Lieberman Aiden,et al.  Quantitative Analysis of Culture Using Millions of Digitized Books , 2010, Science.

[3]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Jeff Donahue,et al.  Visual Search at Pinterest , 2015, KDD.

[5]  Trevor Paglen,et al.  Correction to: Excavating AI: the politics of images in machine learning training sets , 2021, AI & SOCIETY.

[6]  Timnit Gebru,et al.  Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification , 2018, FAT.

[7]  Yusuke Matsui,et al.  Evaluating Face Tracking for Political Analysis in Japanese News Over a Long Period of Time , 2019, WI.

[8]  Maria Elizabeth Grabe,et al.  Taking Television Seriously: A Sound and Image Bite Analysis of Presidential Campaign Coverage, 1992–2004 , 2007 .

[9]  Duy-Dinh Le,et al.  Visual Analytics of Political Networks From Face-Tracking of News Video , 2016, IEEE Transactions on Multimedia.

[10]  F. Mott,et al.  The Utility of the HOME-SF Scale for Child Development Research in a Large National Longitudinal Survey: The National Longitudinal Survey of Youth 1979 Cohort , 2004 .

[11]  Ewan Klein,et al.  Natural Language Processing with Python , 2009 .

[12]  Inioluwa Deborah Raji,et al.  Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing , 2020, AIES.

[13]  Morgan Klaus Scheuerman,et al.  Gender Recognition or Gender Reductionism?: The Social Implications of Embedded Gender Recognition Systems , 2018, CHI.

[14]  Other Contributors Are Indicated Where They Contribute.  British Broadcasting Corporation (BBC) , 2017 .

[15]  Amazon Rekognition , 2019, Machine Learning in the AWS Cloud.

[16]  Maria del Novo.  The Global Media Monitoring Project , 1970 .

[17]  Linda D. Hallman,et al.  The Status of Women , 1949, Social Service Review.

[18]  D. Hallin.  Sound Bite News: Television Coverage of Elections, 1968–1988 , 1992 .

[19]  Florence March,et al.  2016 , 2016, Affair of the Heart.