Extracting Emerging Knowledge from Social Media

What is it about?

Knowledge in the world continuously evolves, and knowledge bases are largely incomplete for what concerns low-frequency data, i.e., data that refers to not-so-popular concepts, belonging to the so-called long tail. Actually, content on social media is an excellent source for discovering emerging knowledge. We propose a method for discovering emerging entities by extracting them from social content. Once instrumented by experts through very simple initialization, the method is capable of finding emerging entities; we use a purely syntactic method as a baseline, and we propose several semantic variants. The method uses seeds, i.e. prototypes of emerging entities provided by experts, for generating candidates; then, it associates candidates to feature vectors, built by using terms occurring in their social content, and then ranks the candidates by using their distance from the centroid of seeds. We validate our method by applying it to a set of diverse domain-specific application scenarios, spanning fashion, literature, and exhibitions.

Featured Image

Photo by bruce mars on Unsplash

Photo by bruce mars on Unsplash

Why is it important?

Social media is an enormous source of information, especially for evolving and innovative concepts and facts. We exploit this as a resource for discovering new knowledge.