Facial expressions might not be reliable indicators of emotion, research indicates. In fact, it might be more accurate to say we should never trust a person's face, new research suggests.
Food waste is a big problem in the United States. According to the US Department of Agriculture, food waste is estimated at between 30-40 percent of the food supply. New research in the INFORMS journal Manufacturing & Service Operations Management finds that increasing the number of grocery stores in certain areas can drastically decrease waste.
Smartphone apps used as 'early warning systems' for skin cancer are poorly regulated and frequently cannot be relied upon to produce accurate results, according to new analysis by experts at the University of Birmingham.
A recent study undertaken by researchers from Germany contradicts the assumption that the use of social networks and search engines has had a negative impact on the diversity of news that people access.
Product reviews and ratings have a strong impact on consumer consideration. In restaurant reviews, new research upcoming in the INFORMS journal Information Systems Research shows that location bias, based on the popularity difference between the reviewer's hometown and the distance to their destination, can affect a reviewers online rating by as much as 11%.
Bias in artificial intelligence is well established. Researchers are now proposing that developers incorporate the concept of 'feminist design thinking' into their process as a way of improving equity -- particularly in the development of software used in hiring.
This is the result of a study led by Valerio Lorini, a PhD student on the ICT programme, led by Carlos Castillo, coordinator of the Web Science and Social Computing group, with Javier Rando, a student at UPF doing the bachelor's degree in Mathematical Engineering in Data Science, focusing on flooding as a case study. Their work will be presented at ISCRAM 2020, from 24 to 27 May in Virginia (USA).
Research from Michigan State University reveals the importance of pinpointing a hacker's motive to predict, identify and prevent cyberattacks.
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.
New research in the INFORMS journal Information Systems Research finds that the purchasing decision of customers considering buying e-books is significantly influenced through easy access to a combination of e-book previews and reviews, resulting in a staggering 31% increase in a consumer's likelihood to purchase an e-book. When exposed to either previews only or online reviews only, purchase likelihood is between 7 and 17%.