Concordia researchers develop AI-based system to better detect toxic online content
Peer-Reviewed Publication
Updates every hour. Last Updated: 17-Jun-2026 00:16 ET (17-Jun-2026 04:16 GMT/UTC)
Based on the underlying paper, the key innovation is not simply better toxicity detection, but an adaptive cascade of AI models. Instead of sending every post through a large, computationally expensive detector, the system starts with faster, lightweight classifiers. If a piece of content is clearly benign or clearly toxic, a decision is made immediately. Only ambiguous cases are passed to increasingly powerful models. A reinforcement-learning algorithm decides which model to consult next, balancing speed, accuracy and computing cost. This approach dramatically increases throughput while slightly improving detection accuracy. (ScienceDirect)
For a 50–60 word EurekAlert summary:
Concordia researchers have developed an AI system that detects toxic online content faster and more accurately by combining multiple detection models in an adaptive sequence. Simple cases are screened by lightweight classifiers, while only difficult content is sent to more powerful AI tools. The approach improves accuracy while processing content up to nine times faster than conventional methods.
Depression may shape how much children pay attention to emotional expressions – sad or happy faces – and those changes appear to depend on whether the child has a family history of depression, according to a first-of-its-kind study from Binghamton University, State University of New York.
More than three-quarters of psychologists report their patients are discussing artificial intelligence in therapy, using the technology to seek additional support with their mental health, find a diagnosis or for friendship and intimate relationships, according to a survey by the American Psychological Association.
Unlike cigarettes or alcohol, cannabis products often come packaged as colorful gummies, chocolates, candies and snacks that can look remarkably similar to items found in a grocery store aisle. A new Washington State University study suggests some of those products may also attract the attention of underage consumers. More than 80% of the 454 teens and young adults surveyed said some cannabis gummy and candy products would appeal to people under 21, even though they complied with Washington state’s cannabis packaging regulations. While cannabis products are sold only in licensed stores that minors cannot legally enter, young people may still encounter the packaging through family members, friends, social media or other sources.