Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter

@article{Sarker2016SocialMM,
  title={Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter},
  author={A. Sarker and Karen O'Connor and Rachel E. Ginn and Matthew Scotch and Karen Smith and Dan Malone and Graciela Gonzalez},
  journal={Drug Safety},
  year={2016},
  volume={39},
  pages={231 - 240}
}
IntroductionPrescription medication overdose is the fastest growing drug-related problem in the USA. The growing nature of this problem necessitates the implementation of improved monitoring strategies for investigating the prevalence and patterns of abuse of specific medications.ObjectivesOur primary aims were to assess the possibility of utilizing social media as a resource for automatic monitoring of prescription medication abuse and to devise an automatic classification technique that can… 
Comment on: "Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter"
TLDR
Saber et al. propose to explore the data collected by Twitter to raise data about prescription medication abuse and provide a standardized method to automatically detect these data for future research.
Enabling Real-Time Drug Abuse Detection in Tweets
TLDR
The utility of Twitter in examining patterns of abuse, and the feasibility of building the drug abuse detection system that can process large volume data from social media sources in a near real-time are illustrated.
Mining social media for prescription medication abuse monitoring: a review and proposal for a data-centric framework
TLDR
A methodological review of social media–based PM abuse or misuse monitoring studies is presented, and a potential generalizable, data-centric processing pipeline for the curation of data from this resource is proposed.
Authors’ Reply to Jouanjus and Colleagues’ Comment on “Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter”
TLDR
Progress in performing drug safety surveillance from generic social media data will depend on the development of unsupervised systems that derive knowledge from large unlabeled data sets, and can complement existing supervised systems.
Promoting Reproducible Research for Characterizing Nonmedical Use of Medications Through Data Annotation: Description of a Twitter Corpus and Guidelines
TLDR
The manual annotation process revealed the variety of ways in which prescription medication misuse or abuse is discussed on Twitter, including expressions indicating coingestion, nonmedical use, nonstandard route of intake, and consumption above the prescribed doses.
Social Media Text Mining Framework for Drug Abuse: An Opioid Crisis Case Analysis
TLDR
The proposed framework for mining and analyzing social media content related to drug abuse in a manner that will mitigate challenges and limitations related to topic deduction and data quality is demonstrated and evaluated.
Drug Analysis Embedded Word
TLDR
This altered represent considers twitter's usefulness in analyzing abuse cases as a result diagram, and exhibits the feasibility of medicine abuse acknowledgement system structure that can strategize wide volume data from a neighboring coherent source of internet system administration.
Text Classification Models for the Automatic Detection of Nonmedical Prescription Medication Use from Social Media
TLDR
The development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter are described and the best-performing classification model is selected, suitable for automated continuous monitoring of nonmedical PM use from Twitter.
Text classification models for the automatic detection of nonmedical prescription medication use from social media
TLDR
BERT, BERT-like and fusion-based models outperform traditional machine learning and deep learning models, achieving substantial improvements over many years of past research on the topic of prescription medication misuse/abuse classification from social media.
Promoting Reproducible Research for Characterizing Nonmedical Use of Medications Through Data Annotation: Description of a Twitter Corpus and Guidelines (Preprint)
TLDR
The manual annotation process revealed the variety of ways in which prescription medication misuse or abuse is discussed on Twitter, including expressions indicating coingestion, nonmedical use, nonstandard route of intake, and consumption above the prescribed doses.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 60 REFERENCES
Leveraging Social Networks for Toxicovigilance
TLDR
An analysis of social media discussions about drug abuse patterns with computational linguistics, graph theory, and agent-based modeling permits the real-time monitoring and characterization of trends of drugs of abuse.
Utilizing social media data for pharmacovigilance: A review
Digital Drug Safety Surveillance: Monitoring Pharmaceutical Products in Twitter
TLDR
Patients reporting AEs on Twitter showed a range of sophistication when describing their experience, indicating their appropriate role in pharmacovigilance has not been established and additional work is needed to improve data acquisition and automation.
An Exploration of Social Circles and Prescription Drug Abuse Through Twitter
TLDR
Twitter users who discuss prescription drug abuse online are surrounded by others who also discuss it—potentially reinforcing a negative behavior and social norm.
Evaluating Social Media Networks in Medicines Safety Surveillance: Two Case Studies
TLDR
Publicly available data from the considered social media networks were sparse and largely untrackable for the purpose of providing early clues of safety concerns regarding the prespecified case studies.
PREDOSE: A semantic web platform for drug abuse epidemiology using social media
Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features
TLDR
A machine learning-based approach to extract mentions of adverse drug reactions (ADRs) from highly informal text in social media, suitable for social media mining, as it relies on large volumes of unlabeled data, thus diminishing the need for large, annotated training data sets.
Tweaking and Tweeting: Exploring Twitter for Nonmedical Use of a Psychostimulant Drug (Adderall) Among College Students
TLDR
Twitter posts confirm the use of Adderall as a study aid among college students and variations in volume around college exam periods, differences across sets of colleges and universities, and commonly mentioned side effects and co-ingested substances are identified.
Opportunities for exploring and reducing prescription drug abuse through social media
TLDR
Using social media to combat the opioid epidemic, although well intended, may be futile or even counterproductive, as promoting the use of social media among them to curb opioid abuse may paradoxically result in more drug abuse.
Drug Use in the Twittersphere: A Qualitative Contextual Analysis of Tweets About Prescription Drugs
TLDR
Twitter can be a resource to observe trends in perceptions about prescription opioid use and represent a positive connotation and promote psychoactive or analgesic use, or negative, or not characterizable.
...
1
2
3
4
5
...