Dataset Information

A Machine Learning Approach for the Detection and Characterization of Illicit Drug Dealers on Instagram: Model Evaluation Study.

ABSTRACT: BACKGROUND:Social media use is now ubiquitous, but the growth in social media communications has also made it a convenient digital platform for drug dealers selling controlled substances, opioids, and other illicit drugs. Previous studies and news investigations have reported the use of popular social media platforms as conduits for opioid sales. This study uses deep learning to detect illicit drug dealing on the image and video sharing platform Instagram. OBJECTIVE:The aim of this study was to develop and evaluate a machine learning approach to detect Instagram posts related to illegal internet drug dealing. METHODS:In this paper, we describe an approach to detect drug dealers by using a deep learning model on Instagram. We collected Instagram posts using a Web scraper between July 2018 and October 2018 and then compared our deep learning model against 3 different machine learning models (eg, random forest, decision tree, and support vector machine) to assess the performance and accuracy of the model. For our deep learning model, we used the long short-term memory unit in the recurrent neural network to learn the pattern of the text of drug dealing posts. We also manually annotated all posts collected to evaluate our model performance and to characterize drug selling conversations. RESULTS:From the 12,857 posts we collected, we detected 1228 drug dealer posts comprising 267 unique users. We used cross-validation to evaluate the 4 models, with our deep learning model reaching 95% on F1 score and performing better than the other 3 models. We also found that by removing the hashtags in the text, the model had better performance. Detected posts contained hashtags related to several drugs, including the controlled substance Xanax (1078/1228, 87.78%), oxycodone/OxyContin (321/1228, 26.14%), and illicit drugs lysergic acid diethylamide (213/1228, 17.34%) and 3,4-methylenedioxy-methamphetamine (94/1228, 7.65%). We also observed the use of communication applications for suspected drug trading through user comments. CONCLUSIONS:Our approach using a combination of Web scraping and deep learning was able to detect illegal online drug sellers on Instagram, with high accuracy. Despite increased scrutiny by regulators and policymakers, the Instagram platform continues to host posts from drug dealers, in violation of federal law. Further action needs to be taken to ensure the safety of social media communities and help put an end to this illicit digital channel of sourcing.

SUBMITTER: Li J

PROVIDER: S-EPMC6598421 | biostudies-literature | 2019 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Machine Learning Approach for the Detection and Characterization of Illicit Drug Dealers on Instagram: Model Evaluation Study.

Li Jiawei J Xu Qing Q Shah Neal N Mackey Tim K TK

Journal of medical Internet research 20190615 6

<h4>Background</h4>Social media use is now ubiquitous, but the growth in social media communications has also made it a convenient digital platform for drug dealers selling controlled substances, opioids, and other illicit drugs. Previous studies and news investigations have reported the use of popular social media platforms as conduits for opioid sales. This study uses deep learning to detect illicit drug dealing on the image and video sharing platform Instagram.<h4>Objective</h4>The aim of thi ...[more]

PMID: 31199298

Similar Datasets

Project description:MotivationArtificial intelligence, trained via machine learning (e.g. neural nets, random forests) or computational statistical algorithms (e.g. support vector machines, ridge regression), holds much promise for the improvement of small-molecule drug discovery. However, small-molecule structure-activity data are high dimensional with low signal-to-noise ratios and proper validation of predictive methods is difficult. It is poorly understood which, if any, of the currently available machine learning algorithms will best predict new candidate drugs.ResultsThe quantile-activity bootstrap is proposed as a new model validation framework using quantile splits on the activity distribution function to construct training and testing sets. In addition, we propose two novel rank-based loss functions which penalize only the out-of-sample predicted ranks of high-activity molecules. The combination of these methods was used to assess the performance of neural nets, random forests, support vector machines (regression) and ridge regression applied to 25 diverse high-quality structure-activity datasets publicly available on ChEMBL. Model validation based on random partitioning of available data favours models that overfit and 'memorize' the training set, namely random forests and deep neural nets. Partitioning based on quantiles of the activity distribution correctly penalizes extrapolation of models onto structurally different molecules outside of the training data. Simpler, traditional statistical methods such as ridge regression can outperform state-of-the-art machine learning methods in this setting. In addition, our new rank-based loss functions give considerably different results from mean squared error highlighting the necessity to define model optimality with respect to the decision task at hand.Availability and implementationAll software and data are available as Jupyter notebooks found at https://github.com/owatson/QuantileBootstrap.Supplementary informationSupplementary data are available at Bioinformatics online.

Project description:BackgroundLogistic regression-based signal detection algorithms have benefits over disproportionality analysis due to their ability to handle potential confounders and masking factors. Feature exploration and developing alternative machine learning algorithms can further strengthen signal detection.ObjectivesOur objective was to compare the signal detection performance of logistic regression, gradient-boosted trees, random forest and support vector machine models utilizing Food and Drug Administration adverse event reporting system data.DesignCross-sectional study.MethodsThe quarterly data extract files from 1 October 2017 through 31 December 2020 were downloaded. Due to an imbalanced outcome, two training sets were used: one stratified on the outcome variable and another using Synthetic Minority Oversampling Technique (SMOTE). A crude model and a model with tuned hyperparameters were developed for each algorithm. Model performance was compared against a reference set using accuracy, precision, F1 score, recall, the receiver operating characteristic area under the curve (ROCAUC), and the precision-recall curve area under the curve (PRCAUC).ResultsModels trained on the balanced training set had higher accuracy, F1 score and recall compared to models trained on the SMOTE training set. When using the balanced training set, logistic regression, gradient-boosted trees, random forest and support vector machine models obtained similar performance evaluation metrics. The gradient-boosted trees hyperparameter tuned model had the highest ROCAUC (0.646) and the random forest crude model had the highest PRCAUC (0.839) when using the balanced training set.ConclusionAll models trained on the balanced training set performed similarly. Logistic regression models had higher accuracy, precision and recall. Logistic regression, random forest and gradient-boosted trees hyperparameter tuned models had a PRCAUC ⩾ 0.8. All models had an ROCAUC ⩾ 0.5. Including both disproportionality analysis results and additional case report information in models resulted in higher performance evaluation metrics than disproportionality analysis alone.

Project description:BackgroundDrug repositioning, also known as drug repurposing, defines new indications for existing drugs and can be used as an alternative to drug development. In recent years, the accumulation of large volumes of information related to drugs and diseases has led to the development of various computational approaches for drug repositioning. Although herbal medicines have had a great impact on current drug discovery, there are still a large number of herbal compounds that have no definite indications.ResultsIn the present study, we constructed a computational model to predict the unknown pharmacological effects of herbal compounds using machine learning techniques. Based on the assumption that similar diseases can be treated with similar drugs, we used four categories of drug-drug similarity (e.g., chemical structure, side-effects, gene ontology, and targets) and three categories of disease-disease similarity (e.g., phenotypes, human phenotype ontology, and gene ontology). Then, associations between drug and disease were predicted using the employed similarity features. The prediction models were constructed using classification algorithms, including logistic regression, random forest and support vector machine algorithms. Upon cross-validation, the random forest approach showed the best performance (AUC = 0.948) and also performed well in an external validation assessment using an unseen independent dataset (AUC = 0.828). Finally, the constructed model was applied to predict potential indications for existing drugs and herbal compounds. As a result, new indications for 20 existing drugs and 31 herbal compounds were predicted and validated using clinical trial data.ConclusionsThe predicted results were validated manually confirming the performance and underlying mechanisms - for example, irinotecan as a treatment for neuroblastoma. From the prediction, herbal compounds were considered to be drug candidates for related diseases which is important to be further developed. The proposed prediction model can contribute to drug discovery by suggesting drug candidates from herbal compounds which have potentials but few were studied.

Dataset Information

A Machine Learning Approach for the Detection and Characterization of Illicit Drug Dealers on Instagram: Model Evaluation Study.

Publications

A Machine Learning Approach for the Detection and Characterization of Illicit Drug Dealers on Instagram: Model Evaluation Study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets