Tae Soo Park, Ok-Ran Jeong, Journal of Internet Computing and Services, Vol. 17, No. 6, pp. 153-0, Dec. 2016
10.7472/jksii.2016.17.6.153, Full Text:  HTML
Keywords: Event Detection, Social Network, Social Media Contents

Abstract

As the number of social network users increases, the information on event such as social issues and disasters receiving attention in each region is promptly posted by the bucket through social media site in real time, and its social ripple effect becomes huge. This study proposes a detection method of events that draw attention from users in specific region at specific time by using twitter data with regional information. In order to collect Twitter data, we use Twitter Streaming API. After collecting data, We implemented event detection system by analyze the frequency of a keyword which contained in a twit in a particular time and clustering the keywords that describes same event by exploiting keywords' co-occurrence graph. Finally, we evaluates the validity of our method through experiments.

Statistics
Cite this article