Skip to main content
Computational Social Networks
Fig. 1 | Computational Social Networks

Fig. 1

From: An insight analysis and detection of drug-abuse risk behavior on Twitter with self-taught deep learning

Fig. 1

Drug-abuse detection system. There are 4 steps as follows: (1) Tweets will be collected through Twitter APIs. (2) Pre-processed tweets will be labeled by humans, AI techniques, and crowd-sourcing techniques. (3) Labeled tweets will be used to augment the training data of our AI models and data analysis tasks to identify tweets with drug-abuse risk behaviors, through a self-taught algorithm. In addition, (4) trained systems will be used in different drug-abuse monitoring services and interactive user interfaces

Back to article page