A novel theoretical model to detect hot events from online social media

被引：0
作者：
Han, Xiaohui [1 ]
Ma, Jun [1 ]
Xue, Ran [1 ]
机构：
[1] School of Computer Science and Technology, Shandong University
来源：
International Journal of Digital Content Technology and its Applications | 2012年 / 6卷 / 19期
关键词：
Aging Theory; Event Detection; Image; LDA;
D O I：
10.4156/jdcta.vol6.issue19.6
中图分类号：
学科分类号：
摘要：
The rapid development of social media brings new opportunities and challenges to find hot events from the data in these social media. Since online image communities like Flickr usually provide images as well as titles, tags and comments annotated by users, it is possible to utilize both the textual and visual information in image communities to enhance event detection. In this paper we propose an LDA (Latent Dirichlet Allocation) based data representation and then provide an algorithm to detect hot events, which considers the geographical closeness constraint in the event detection process and uses Aging Theory to model the life cycle of an event. We rank the detected events according to their energy values in a specific time span and chose the highly ranked events as the hot events. Experiments on Flickr data collection reveal that the performance of our algorithm is better than previous known ones in terms of precision, recall and F1 value. In addition, the hot events detected by our model seem more reasonable according to the P@10 score.
引用
收藏
页码：42 / 50
页数：8
相关论文
共 18 条
  • [1] Tang J., Chinese Event Identification and Tracking Using Two Phase Clustering Algorithm, Journal of Convergence Information Technology, 6, 3, pp. 283-289, (2011)
  • [2] Zhong Z., Li C., Guan Y., Liu Z., A Method of Query Expansion Based on Event Ontology, Journal of Convergence Information Technology (JCIT), 7, 9, pp. 364-371, (2012)
  • [3] Halpin H., Robu V., Shepherd H., The Complex Dynamics of Collaborative Tagging, Proceedings of the 16th International Conference on World Wide Web, pp. 211-220, (2007)
  • [4] Firan C.S., Georgescu M., Nejdl W., Paiu R., Bringing Order to Your Photos: Event-Driven Classification of Flickr Images Based on Social knowledge, Proceedings of the 19th ACM International Conference on Information and Knowledge Management, pp. 189-198, (2010)
  • [5] Becker H., Mornaaman G.L., Learning Similarity Metrics for Event Identification in Social Media, Proceedings of 3rd ACM international conference on Web Search and Data Mining, pp. 291-300, (2010)
  • [6] Chen L., Roy A., Event Detection from Flickr Data through Wavelet-based Spatial Analysis, Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 523-532, (2009)
  • [7] Jin X., Gallagher A., Cao L., Luo J., Han J., The Wisdom of Social Multimedia: Using Flickr for Prediction and Forecast, Proceedings of the International Conference on Multimedia, pp. 1235-1244, (2010)
  • [8] Gabriel Fung P.C., Xu Yu J., Yu P.S., Liu H., Parameter Free Bursty Events Detection in Text Streams, Proceedings of the 31st VLDB Conference, pp. 181-192, (2005)
  • [9] Chieu H.L., Keok Lee Y., Query Based Event Extraction along a Timeline, Proceedings of the 27th Annual International ACM SIGIR Conference, pp. 425-432, (2004)
  • [10] He Q., Chang K., Lim E.-P., Analyzing Feature Trajectories for Event Detection, Proceedings of the 30th Annual International ACM SIGIR Conference, pp. 207-214, (2007)
12