Mining e-cigarette adverse events in social media using Bi-LSTM recurrent neural network with word embedding representation.
Jiaheng XieXiao LiuDaniel Dajun ZengPublished in: J. Am. Medical Informatics Assoc. (2018)
Keyphrases
- recurrent neural networks
- social media
- long short term memory
- neural network
- recurrent networks
- feed forward
- complex valued
- social media data
- artificial neural networks
- reservoir computing
- hidden layer
- echo state networks
- feedforward neural networks
- knowledge discovery
- neural model
- event sequences
- real world events
- big data
- temporal information
- temporal relationships
- n gram
- temporal events
- word counts
- data mining techniques
- genetic algorithm
- control system
- nonlinear dynamic systems
- business intelligence
- sequential patterns
- event detection