Platforms are increasingly using transparency, whether it be in the form of political advertising disclosures or a record of page name changes, to combat disinformation campaigns. In the case of state-controlled media outlets on YouTube, Facebook, and Twitter this has taken the form of labeling their connection to a state. We show that these labels have the ability to mitigate the effects of viewing election misinformation from the Russian media channel RT. However, this is only the case when the platform prominently places the label so as not to be missed by users.
Satire is a form of humorous critique, but it is sometimes misinterpreted by readers as legitimate news, which can lead to harmful consequences. We observe that the images used in satirical news articles often contain absurd or ridiculous content and that image manipulation is used to create fictional scenarios. While previous work have studied text-based methods, in this work we propose a multi-modal approach based on state-of-the-art visiolinguistic model ViLBERT. To this end, researchers created a new dataset consisting of images and headlines of regular and satirical news for the task of satire detection. The researchers also fine-tune ViLBERT on the dataset and train a convolutional neural network that uses an image forensics technique. Evaluation on the dataset shows that our proposed multi-modal approach outperforms image-only, text-only, and simple fusion baselines.
Social media are a promising new data source for real-world behavioral monitoring. Despite clear advantages, analyses of social media data face some challenges. In this paper, we seek to elucidate some of these challenges and draw relevant lessons from more traditional survey techniques. Beyond standard machine learning approaches, we make the case that studies that conduct statistical analyses of social media data should carefully consider elements of study design, providing behavioral examples throughout. Specifically, we focus on issues surrounding the validity of statistical conclusions that may be drawn from social media data. We discuss common pitfalls and techniques to avoid these pitfalls, so researchers may mitigate potential problems of design.
Home page - events - title
Monday, October 19, 2020 - 10:00am
This virtual conference explored the questions about fact checking the presidential campaign, considered how communities of color are impacted by digital disinformation, talked about potential post election violence and examined how discourse about COVID-19 is reshaping American politics.
Thursday, August 13, 2020 - 1:00pm
What are the implications of online vaccine communication for political discourse?
Thursday, August 6, 2020 - 9:00am
The Institute for Data, Democracy & Politics hosted it's third and final International Forum on the Harms of Social Media Disinformation on August 6th. The forums have spann
For all the flak that President Trump has taken over the federal government's response, or lack thereof, to the coronavirus pandemic, the government's vaccine development project, Operation Warp Speed, looks like a winner. According to Pfizer, its vaccine prevented COVID in 95 percent of participants in its clinical trials, which are now complete. Moderna's vaccine, which got $1 billion in U.S. government support, prevents 94 percent of cases, the company said.
Maria Ressa says what she’s living through is Kafkaesque. The crusading Filipina journalist received a John Aubuchon Press Freedom Award on Wednesday from the National Press Club in Washington, D.C., the latest international recognition of her years-long fight to defend independent media in the Philippines against the authoritarian President Rodrigo Duterte, who denounces her website Rappler as “fake news.”
Hate speech does not operate in a vacuum, and its rise reflects changing political contexts. If we’re serious about fighting hate speech and its violent and destabilizing consequences, we need to identify its earliest manifestations. Babak Bahador offers a hate-speech intensity scale, a strategy that allows us to move beyond the binary approach that dominates current hate speech research. This concept can be operationalized to better identify and understand the evolutions of hate speech before it leads to real-world harms.