Learning to explore spatio-temporal impacts for event evaluation on social media

  • Authors:
  • Chung-Hong Lee;Hsin-Chang Yang;Wei-Shiang Wen;Cheng-Hsun Weng

  • Affiliations:
  • Dept of Electrical Engineering, National Kaohsiung University of Applied Sciences, Kaohsiung, Taiwan;Dept of Information Management, National University of Kaohsiung, Kaohsiung, Taiwan;Dept of Electrical Engineering, National Kaohsiung University of Applied Sciences, Kaohsiung, Taiwan;Dept of Electrical Engineering, National Kaohsiung University of Applied Sciences, Kaohsiung, Taiwan

  • Venue:
  • ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Due to the explosive growth of social-media applications, enabling event-awareness by social mining has become extremely important. The contents of microblogs preserve valuable information associated with past disastrous events and stories. To learn the experiences from past microblogs for tackling emerging real-world events, in this work we utilize the social-media messages to characterize events through their contents and spatio-temporal features for relatedness analysis. Several essential features of each detected event dataset have been extracted for event formulation by performing content analysis, spatial analysis, and temporal analysis. This allows our approach compare the new event vector with existing event vectors stored in the event-data repository for evaluation of event relatednesss, by means of validating spatio-temporal feature factors involved in the event evolution. Through the developed algorithms for computing event relatedness, in our system the ranking of related events can be computed, allowing for predicting possible evolution and impacts of the event. The developed system platform is able to immediately evaluate the significantly emergent events, in order to achieve real-time knowledge discovery of disastrous events.