Predicting the outcome of elections is a topic that has been extensively studied in political polls, which have generally provided reliable predictions by means of statistical models. In recent years, online social media platforms have become a potential alternative to traditional polls, since they provide large amounts of post and user data, also referring to … Continue reading Understanding Polarized Political Events through Social Media Analysis
Social media platforms let users share their opinions through textual or multimedia content. In many settings, this becomes a valuable source of knowledge that can be exploited for specific business objectives. Brands and companies often ask to monitor social media as sources for understanding the stance, opinion, and sentiment of their customers, audience and … Continue reading Data Cleaning for Knowledge Extraction and Understanding on Social Media
Our motivation starts from the fact that knowledge in the world continuously evolves, and thus ontologies and knowledge bases are largely incomplete. We explored iterative methods, using the results as new seeds. In this paper we address the following research questions:
How does the reconstructed domain knowledge evolve if the candidates of one extraction are recursively used as seeds?
How does the reconstructed domain knowledge spread geographically?
Can the method be used to inspect the past, present, and future of knowledge?
Can the method be used to find emerging knowledge?
I collected here the list of my write-ups of the first three keynote speeches of the conference: Human in the Loop Machine Learning (Carla E. Brodley, Northeastern Univ.) Enhancing Human Perception via Text Mining and IR (Cheng Zhai, Univ. Illinois) Graph Representation Learning (Jure Leskovec, Stanford and Pinterest)