Researchers created an algorithm that successfully predicted consumer purchases. The algorithm made use of data from the consumers’ daily activity on social media. Brands could use this to analyze potential customers. The researchers’ method combines powerful statistical modeling techniques with machine learning-based image recognition.
Tag / social network analysis
Facebook’s ad tools subsidize partisanship, research shows. And campaigns may not even know it. – The Washington Post
For the first time, researchers have demonstrated a skew in the delivery of political ads based on the content of those ads alone.
Scientists on Twitter: Preaching to the choir or singing from the rooftops? – SFU News – Simon Fraser University
Grassroots tech group takes startup approach to fight Brexit – The Washington Post
Grassroots group of UK tech volunteers battles Brexit by working like a startup
Source: Grassroots tech group takes startup approach to fight Brexit – The Washington Post
Το Τwitter «απειλεί» τους δημοσκόπους | Η Εφημερίδα των Συντακτών
Predicting Voter Behavior: Twitter vs Polls
Source: Το Τwitter «απειλεί» τους δημοσκόπους | Η Εφημερίδα των Συντακτών
RMIT uses Foursquare check-ins to predict drug busts – itnews
RMIT uses Foursquare check-ins to predict drug busts.
Source: Real-time social media location data used to predict crime – Software – iTnews
Social media data used to predict retail failure | University of Cambridge
Using information from ten different cities around the world, the researchers, led by the University of Cambridge, have developed a model that can predict with 80% accuracy whether a new business will fail within six months. The results will be presented at the ACM Conference on Pervasive and Ubiquitous Computing (Ubicomp), taking place this week in Singapore.
Source: Social media data used to predict retail failure | University of Cambridge