Date: 3rd Dec 2015
Talk Time: 12:00 – 13:00 Hrs
Venue: Seminar Hall, KICS, UET, Lahore
Speaker: Dr. Prof. Andreas Dengel
Among the vast information available on the web, social media streams capture what people currently pay attention to and how they feel about certain topics. Awareness of such trending topics plays a crucial role in multimedia systems such as trend aware recommendation and automatic vocabulary selection for video concept detection systems. Correctly utilizing trending topics requires a better understanding of their various characteristics in different social media streams. To this end, I present the first comprehensive study across three major online and social media streams, Twitter, Google, and Wikipedia, covering thousands of trending topics during an observation period of an entire year. Our results indicate that depending on one's requirements one does not necessarily have to turn to Twitter for information about current events and that some media streams strongly emphasize content of specific categories. As our second key contribution we further present a novel approach for the challenging task of forecasting the life cycle of trending topics in the very moment they emerge. Our fully automated approach is based on a nearest neighbor forecasting technique exploiting our assumption that semantically similar topics exhibit similar behavior. We demonstrate on a large-scale dataset of Wikipedia page view statistics that forecasts by the proposed approach are about 9-48k views closer to the actual viewing statistics compared to baseline methods and achieve a mean average percentage error of 45-19% for time periods of up to 14 days.
Professor Andreas Dengel is a member of the Management Board as well as Scientific Director at the German Research Center for Artificial Intelligence (DFKI GmbH) in Kaiserslautern where he is leading the Knowledge Management research department. In 1993 he was appointed Professor at the Computer Science Department of the University of Kaiserslautern where he holds the chair “Knowledge-Based Systems”. Since 2009 he is also Professor (Kyakuin) at the Department of Computer Science and Intelligent Systems, Graduate School of Engineering, at Osaka Prefecture University.
From 1980 to 1986, Prof. Dengel studied Computer Science and Economics at the University of Kaiserslautern. He subsequently worked at the Siemens research lab in Munich and at the University of Stuttgart where he completed his doctoral thesis in 1989. In 1991 he worked as a guest researcher at Xerox Parc in Palo Alto.
Since 2006 he has been a member of the IT-Summit Working Group on “service and consumer-oriented information technology”, consulting the German government on questions of future IT-strategies. in 2009 he appointed an expert for the German Council of Science and Humanities of the German Government. In 2008 he co-founded the Institute for Document Analysis and Knowledge Science "IDAKS" at the Osaka Prefecture University in Japan.
Andreas is an advisory board member of the Center of Excellence on Semantic Technologies at MIMOS, Kuala Lumpur, Malaysia, the NEC Computers and Communication Innovation Research Labs (CCIL), and Intl. Conference on Document Analysis and Recognition (ICDAR). He is a board member of the Science Alliance Kaiserslautern, a Principle Investigator of theCMCM Research Center at the University of Kaiserslautern as well as of the Diemersteiner Circle.
Formerly, he was the German representative in the ICT Prize Executive Jury of the European Council of Applied Science (Euro-CASE), a lecturer of the Joint Executive MBA course at the Johannes Gutenberg University at Mainz, the University of Texas at Austin, and the Dongbei University of Finance and Economics at Dalian, China. From 1997 to 2001 Prof. Dengel was a member of the METTREC Planning Committee (Metadata/Text/Retrieval Conference Committee) of the National Institutitute for Standards and Technology (NIST) in the United States. Besides many keynotes at international conferences, Andreas gave numerous invited technical talks at highly renowned universities and research labs including MIT, Stanford University, PARC, UC Berkeley, UC Davis, CMU, ATR, Microsoft Research und Google Research. Andreas was program/technical chair of ICPR,ICDAR, DAS, KM und KI. conferences.
Prof. Dengel is Member of the Editorial Board for international journals like IJDAR, Intelligent Decision Technologies or Future Internet. Moreover, he is founder or initiator of several successful start-up companies, e.g. Insiders Technologies where he also acted as a CEO between 1999 and 2001. In 2005 he received a “Pioneer Spirit Award” for one of his start-up concepts. He is co-editor of various international computer science journals and has written or edited 10 books and is author of more than 160 peer-reviewed scientific publications. He supervised more than 120 PhD and master theses.
In 2004, Andreas Dengel has been elected a Fellow of the International association for Pattern Recognition (IAPR) and has been honored for his work several times. Most prominent prizes are the ICDAR “Young Investigator Award”, the Nakano Award, the Technical Communication Award of the Alcatel SEL Foundation, the Multi-Media Award of the State Rheinland-Pfalz as well as a Document Analysis Systems Achievement Award. His main scientific emphasis is in the areas of Knowledge Management, Artificial Intelligence, and Document Understanding. Prof. Dengel is founder or initiator of several successful start-up companies.