Abstract | ||
---|---|---|
Drug abuse continues to accelerate toward becoming the most severe public health problem in the United States. The ability to detect drug abuse risk behavior at a population scale, such as among the population of Twitter users, can help us to monitor the trend of drug-abuse incidents. Unfortunately, traditional methods do not effectively detect drug abuse risk behavior, given tweets. This is because: (1) Tweets usually are noisy and sparse; and (2) The availability of labeled data is limited. To address these challenging problems, we proposed a deep self-taught learning system to detect and monitor drug abuse risk behaviors in the Twitter sphere, by leveraging a large amount of unlabeled data. Our models automatically augment annotated data: (i) To improve the classification performance, and (ii) To capture the evolving picture of drug abuse on online social media. Our extensive experiment has been conducted on 3 million drug abuse-related tweets with geo-location information. Results show that our approach is highly effective in detecting drug abuse risk behaviors. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-030-04648-4_28 | CSoNet |
Field | DocType | Citations |
Public health,Population,Internet privacy,Social media,Psychology,Substance abuse,Artificial intelligence,Deep learning,Labeled data | Conference | 0 |
PageRank | References | Authors |
0.34 | 10 | 9 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Hu | 1 | 193 | 14.98 |
NhatHai Phan | 2 | 98 | 10.76 |
James Geller | 3 | 221 | 38.48 |
Huy T. Vo | 4 | 1035 | 61.10 |
Manasi Bhole | 5 | 0 | 0.34 |
Xueqi Huang | 6 | 0 | 0.34 |
Sophie Di Lorio | 7 | 0 | 0.34 |
T. N. Dinh | 8 | 660 | 40.17 |
Soon Ae Chun | 9 | 893 | 100.67 |