Researchers at Concordia’s Gina Cody School of Engineering and Computer Science have developed a new approach to identifying fake news. And they say it will be able to find hidden patterns that reveal whether a particular item is likely fake or not.

The model, called SmoothDetector, integrates a probabilistic algorithm with a deep neural network. It’s designed to capture the uncertainties and key patterns in the shared latent representations of texts and images in a multimodal setting. The model uses annotated text and image data from the United States–based social media platform X and the China-based Weibo to learn. The researchers are currently looking into ways to eventually incorporate functionalities to detect fake audio and video content as well, leveraging every medium to counter misinformation.

Locals at Lake Siljan in northern Sweden have told of persistent winter ice holes that often occur in the same place year after year. Now, researchers from Chalmers University of Technology, in Sweden, have examined the area with a completely new measurement method and discovered unexpectedly strong methane emissions from several places on the lakes in the area – which is the cause of the holes in the ice.

This type of long-term and concentrated methane emission has never been observed by a lake, and the researchers will now investigate whether the emissions are unique to Siljan – or a phenomenon that can occur in lakes all over the world.

The project holds the potential to create numerous jobs and positions the region at the forefront of new energy production.