Embedding and predicting the event at early stage
- Publication Type:
- Journal Article
- Citation:
- World Wide Web, 2019, 22 (3), pp. 1055 - 1074
- Issue Date:
- 2019-05-15
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Liu2019_Article_EmbeddingAndPredictingTheEvent.pdf | Published Version | 996.73 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2018, Springer Science+Business Media, LLC, part of Springer Nature. Social media has become one of the most credible sources for delivering messages, breaking news, as well as events. Predicting the future dynamics of an event at a very early stage is significantly valuable, e.g, helping company anticipate marketing trends before the event becomes mature. However, this prediction is non-trivial because a) social events always stay with “noise” under the same topic and b) the information obtained at its early stage is too sparse and limited to support an accurate prediction. In order to overcome these two problems, in this paper, we design an event early embedding model (EEEM) that can 1) extract social events from noise, 2) find the previous similar events, and 3) predict future dynamics of a new event with very limited information. Specifically, a denoising approach is derived from the knowledge of signal analysis to eliminate social noise and extract events. Moreover, we propose a novel predicting scheme based on locally linear embedding algorithm to construct the volume of a new event from its k nearest neighbors. Compared to previous work only fitting the historical volume dynamics to make a prediction, our predictive model is based on both the volume information and content information of events. Extensive experiments conducted on a large-scale dataset of Twitter data demonstrate the capacity of our model on extract events and the promising performance of prediction by considering both volume information as well as content information. Compared with predicting with only the content or the volume feature, we find the best performance of considering they both with our proposed fusion method.
Please use this identifier to cite or link to this item: