Invited Speaker---Dr. Gautam Srivastava


Dept. of Computer Science, Brandon University, Canada

Biography: Dr. Gautam Srivastava was awarded a B.Sc. from Briar Cliff University in Sioux City, Iowa, U.S.A. in 2004, followed by M.Sc. and Ph.D. from the University of Victoria in Victoria, British Columbia, Canada, in the years 2006 and 2011, respectively. He then worked for 3 years at the University of Victoria in the Department of Computer Science (Faculty of Engineering), where he was regarded as one of the top Undergraduate professors in Computer Science Course Instruction at the University. From there in 2014 he started a tenure-track position at Brandon University in Brandon, Manitoba, Canada, where he currently is an Assistant Professor. Dr. G (as he is popularly known) is active in research in the fields of Data Mining and Big Data. During his 6-year academic career, he has published a total of 15 papers in high-impact conferences and journals. He has also given invited guest lectures at many Taiwan universities in Big Data. He currently has active research projects with other academics in Taiwan, Singapore, Canada and U.S.A. He is constantly looking for collaboration opportunities with foreign professors and students.

Speech Title: Measuring Twitter User Influence Through a Discrete Event
Abstract: NASA is viewed as a prime piece of the frontier of human knowledge by several generations, and is relied upon to educate the public on astronomical matters. With the Great American Eclipse of 2017, NASA’s production was crucial to the general public’s awareness and understanding of the event. With the explosion of data mining avenues and techniques, being able to study and quantify such major events has become of utmost importance for many of the involved. Our goal with this research is to understand how the public perceived the social media coverage that NASA had provided. We accomplish this through sentiment analysis and the spotting of trends within Twitter data. Furthermore, we follow a framework of study that allows simple and cost-effective analysis of discrete events of arbitrary nature in the future.