Twitter researchers offer clues for why Trump won
The more Donald Trump tweeted, the faster his following grew, even after he sparked controversies. This is among the many findings from an exhaustive 14-month study of each candidate’s tweets during the 2016 election by researchers Jiebo Luo and Yu Wang.
Three health analytics projects receive pilot funding
The University’s Goergen Institute for Data Science has awarded grants to three projects aimed at using big data to improve treatment of patients who are in intensive care or who suffer from epilepsy or mental disorders.
10 years later, ‘inconsequential’ tweets a boon for researchers
Twitter founder Jack Dorsey chose the name because “twitter” described “a short inconsequential burst of information.” And yet, the social network is anything but inconsequential in terms of data science research and its applications. Twitter, which went public on this date in 2006, is fertile ground for Rochester researchers interested in tracking everything from disease outbreaks to the dynamics of political campaigns and consumer preferences.
Paying attention to words, not just images, leads to better captions
A team of University and Adobe researchers is outperforming other approaches to creating computer-generated image captions in an international competition. The key to their winning approach? Thinking about words – what they mean and how they fit in a sentence structure – just as much as thinking about the image itself.
Data mining Instagram feeds can point to teenage drinking patterns
By extracting information from Instagram images and hashtags, computer science researchers have shown they can expose patterns of underage drinking more cheaply and faster than conventional surveys.
New app would monitor mental health through “selfie” videos, social media
In a paper to be presented this week at the American Association for Artificial Intelligence conference in Austin, Texas, computer science professor Jiebo Luo and his colleagues describe a computer program that can analyze “selfie” videos recorded by a webcam as the person engages with social media.