Predicting impactful events with Graph Machine Learning using Large Language Models.
By Gal Gantar, Mark David Longar, Adrian Mladenić Grobelnik, Nejc Rus as part of the Stanford CS224W course project.
In a world of information overload, we are bombarded with a seemingly endless stream of interconnected news events, articles, and concepts, each competing for our attention. This large quantity of information, constantly flooding our daily lives through various channels like social media, online news platforms, and traditional media, presents a unique set of challenges. Not only does it make it difficult to keep up with the latest developments, but it also poses the risk of missing critical information amid the noise. In such a landscape, being able to effectively filter out the most important information has become crucial. It’s not just about staying informed; it’s about understanding the significance and relevance of the news we consume.
Our goal is to predict which breaking news events are going to be impactful. If successful, such a tool would be useful for journalists, policymakers, and informed citizens to focus their attention and resources on the stories that matter most. It can lead to a more informed and proactive response to emerging issues.
Medium article available at: https://medium.com/@adrian.mladenic.grobelnik/predicting-impactful-events-with-graph-ml-ccd0feefa869