Fake news: how can data science and deep learning be leveraged to detect it? Come on a journey with Mike Tamir, Head of Data Science at Uber ATG, who is building out a data science product that classifies text as news, editorial, satire, hate speech and fake news, among others. We'll also see what types of unique challenges Mike faced in his work at Takt, using data science to service the needs of Fortune 500 companies such as Starbucks.Links from the show

FROM THE INTERVIEW

FROM THE SEGMENTS

The Double-edged Sword of Impact Parts I & 2 (with Friederike Schüür, Cloudera Fast Forward Labs)

Media Manipulation and Disinformation Online from Data & Society
James Bridle's blog post 'Something is wrong on the internet'
The Cost of Fairness in Binary Classification (.pdf), a paper by Menon & Williamson (2018)
Multisided Fairness for Recommendation, a paper by Burke (2017)
All The Cool Kids, How Do They Fit In? Popularity and Demographic Biases in Recommender Evaluation and Effectiveness, a paper by Ekstrand et al. (2018)
The spread of true and false news online, a paper by Vosoughi et al. (2018)

Original music and sounds by The Sticks.

#13 Fake News Detection with Data Science

DataFramed