Abstract
We proposed an approach for temporal event detection using deep learning and multi-embedding on a set of text data from social media. First, a convolutional neural network augmented with multiple word-embedding architectures is used as a text classifier for the pre-processing of the input textual data. Second, an event detection model using a recurrent neural network is employed to learn time series data features by extracting temporal information. Recently, convolutional neural networks have been used in natural language processing problems and have obtained excellent results as performing on available embedding vector. In this article, word-embedding features at the embedding layer are combined and fed to convolutional neural network. The proposed method shows no size limitation, supplementation of more embeddings than standard multichannel based approaches, and obtained similar performance (accuracy score) on some benchmark data sets, especially in an imbalanced data set. For event detection, a long short-term memory network is used as a predictor that learns higher level temporal features so as to predict future values. An error distribution estimation model is built to calculate the anomaly score of observation. Events are detected using a window-based method on the anomaly scores.
Highlights
Social network services (SNSs) such as Twitter and Facebook have been widely used in recent years, and they have become a potential data source for data mining as social sensor
Since social media has emerged as a dominant channel for gathering and spreading information during the occurrence of some event, social networks have become a useful means of communicating information
We introduced an event detection approach composed of Convolutional neural network (CNN) and long short-term memory (LSTM) models
Summary
Social network services (SNSs) such as Twitter and Facebook have been widely used in recent years, and they have become a potential data source for data mining as social sensor. We propose an approach that automatically identifies informative messages on social sensors by taking advantage of neural network techniques It learns text features from embedding vectors. In the scope of event detection, there are many traditional methods for this task, but feature-based methods require complicated feature engineering.[19,20,22,27] In this article, we introduce a way to take advantage of both CNN on word embedding and variable sizes of multiple embeddings under the classifier in order to identify informative messages. A window-based method is used to detect events with the anomaly score This approach performs well on many context applications, where balanced data are not always available and real-time disaster event detection is required.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call