Empower - The Campaign for Northeastern University


Colloquium: Extraction of Evolving Knowledge from Social Media

TitleExtraction of Evolving Knowledge from Social MediaLocationWest Village H 366AbstractKnowledge in the world continuously evolves. Ontologies that aim at formalizing this knowledge are largely incomplete, especially regarding data belonging to the so-called long tail. On the other side, informal sources such has social media are typically very up to date with respect to facts, events and relations between real-world entities.We propose a method for discovering emerging knowledge by extracting it from social content. Once initialized by domain experts, the method is capable of finding relevant entities by means of a mixed syntactic-semantic method. 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 ranks the candidates by using their distance from the centroid of seeds, returning the top candidates. Our method can run iteratively, using the results as new seeds. The talk will describe the different extraction techniques, the advantages obtained by combining them, and the results of the experiments performed with the different methods.About the SpeakerMarco Brambilla is associate professor at Politecnico di Milano. His research interests include data science, domain specific modeling languages and design patterns, crowdsourcing, social media monitoring, and big data analysis. He has been visiting researcher at CISCO, San Josè, and University of California, San Diego. He has been visiting professor at Dauphine University, Paris.He is co-founder of the startups Fluxedo, focusing on social media analysis and Social engagement, and WebRatio, devoted to software modeling tools for Web, Mobile and Business Process based software applications. He is author of various international books and research articles in journals and conferences, with over 200 papers. He was awarded various best paper prizes and gave keynotes and speeches at many conferences and organizations. He runs research projects on data science and industrial projects on data-driven innovation and big data. He is the main author of the OMG standard IFML.Related Papers Extracting Emerging Knowledge from Social Media. WWW 2017 Iterative Knowledge Extraction from Social Networks. WWW Comp. 2018

Monday, January 28 at 12:30pm



Google Calendar iCal Outlook

Recent Activity