Drug Use in the Twittersphere: A Qualitative Contextual Analysis of Tweets About Prescription Drugs

Shutler, Lukas; Nelson, Lewis S.; Portelli, Ian; Blachford, Courtney; Perrone, Jeanmarie

doi:10.1080/10550887.2015.1074505

Cited by 62 publications

(67 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In response, this study advances prior studies that have examined the linkages between Twitter and NMUPD and introduces a new methodology leveraging recent developments in computer science in order to gain a "bigger" picture of national NMUPD trends. Previous studies have heavily relied upon content analysis and human coding/annotation using keyword searches, identifying subsets of Twitter NMUPD-related social circles, and analyzing a random sample of filtered tweets (Hanson et al, 2013a;Hanson, Cannon, Burton, & Giraud-Carrier, 2013b;Katsuki et al, 2015;Shutler, Nelson, Portelli, Blachford, & Perrone, 2015).…”

Section: Introductionmentioning

confidence: 99%

Exploring trends of nonmedical use of prescription drugs and polydrug abuse in the Twittersphere using unsupervised machine learning

Kalyanam

Katsuki

Lanckriet

et al. 2017

Addictive Behaviors

View full text Add to dashboard Cite

This study presents a methodology to filter Twitter content for NMUPD behavior, while also identifying underlying themes with minimal human intervention. Results from the study track accurately with the inclusion/exclusion criteria used to isolate NMUPD-related risk behaviors of interest and also provides insight on NMUPD behavior that has a high level of social media engagement. Results suggest that this could be a viable methodology for use in big data substance abuse surveillance, data collection, and analysis in comparison to other studies that rely upon content analysis and human coding schemes.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring trends of nonmedical use of prescription drugs and polydrug abuse in the Twittersphere using unsupervised machine learning

Kalyanam

Katsuki

Lanckriet

et al. 2017

Addictive Behaviors

View full text Add to dashboard Cite

show abstract

“…The content of tweets, although brief and limited to 140 characters (with some recent relaxation of this limit), can be used to extract information on user attitudes and behaviors related to drug use [15,16,18-22]. Prior research indicates that the ability to separate personal communications from other types of communications such as official/media or retail-related tweets might help reduce the “noise” in social media research and increase the quality of the data for epidemiological surveillance [23,24].…”

Section: Introductionmentioning

confidence: 99%

“…Several prior studies used manual coding to classify cannabis, alcohol, and other drug-related tweets by sentiment [15,18,20,21] and source [15,21]. However, such studies, because they relied on manual coding, were limited to the analyses of relatively small samples of tweets.…”

Section: Introductionmentioning

confidence: 99%

“When ‘Bad’ is ‘Good’”: Identifying Personal Communication and Sentiment in Drug-Related Tweets

Daniulaityte¹,

Chen²,

Lamy³

et al. 2016

JMIR Public Health Surveill

View full text Add to dashboard Cite

BackgroundTo harness the full potential of social media for epidemiological surveillance of drug abuse trends, the field needs a greater level of automation in processing and analyzing social media content.ObjectivesThe objective of the study is to describe the development of supervised machine-learning techniques for the eDrugTrends platform to automatically classify tweets by type/source of communication (personal, official/media, retail) and sentiment (positive, negative, neutral) expressed in cannabis- and synthetic cannabinoid–related tweets.MethodsTweets were collected using Twitter streaming Application Programming Interface and filtered through the eDrugTrends platform using keywords related to cannabis, marijuana edibles, marijuana concentrates, and synthetic cannabinoids. After creating coding rules and assessing intercoder reliability, a manually labeled data set (N=4000) was developed by coding several batches of randomly selected subsets of tweets extracted from the pool of 15,623,869 collected by eDrugTrends (May-November 2015). Out of 4000 tweets, 25% (1000/4000) were used to build source classifiers and 75% (3000/4000) were used for sentiment classifiers. Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machines (SVM) were used to train the classifiers. Source classification (n=1000) tested Approach 1 that used short URLs, and Approach 2 where URLs were expanded and included into the bag-of-words analysis. For sentiment classification, Approach 1 used all tweets, regardless of their source/type (n=3000), while Approach 2 applied sentiment classification to personal communication tweets only (2633/3000, 88%). Multiclass and binary classification tasks were examined, and machine-learning sentiment classifier performance was compared with Valence Aware Dictionary for sEntiment Reasoning (VADER), a lexicon and rule-based method. The performance of each classifier was assessed using 5-fold cross validation that calculated average F-scores. One-tailed t test was used to determine if differences in F-scores were statistically significant.ResultsIn multiclass source classification, the use of expanded URLs did not contribute to significant improvement in classifier performance (0.7972 vs 0.8102 for SVM, P=.19). In binary classification, the identification of all source categories improved significantly when unshortened URLs were used, with personal communication tweets benefiting the most (0.8736 vs 0.8200, P<.001). In multiclass sentiment classification Approach 1, SVM (0.6723) performed similarly to NB (0.6683) and LR (0.6703). In Approach 2, SVM (0.7062) did not differ from NB (0.6980, P=.13) or LR (F=0.6931, P=.05), but it was over 40% more accurate than VADER (F=0.5030, P<.001). In multiclass task, improvements in sentiment classification (Approach 2 vs Approach 1) did not reach statistical significance (eg, SVM: 0.7062 vs 0.6723, P=.052). In binary sentiment classification (positive vs negative), Approach 2 (focus on personal communication tweets only) improved classification results, ...

show abstract

“…Data mining or ‘social listening’ case studies have established a base of applied examples of how generally unstructured online electronic sources can be used to derive drug safety information from news and social media, commonly including Twitter, Facebook, Google+, patient forums, news reports, blogs, and others. Notable among these are studies evaluating online discussions of benfluorex [17], antibiotics [18], human papilloma virus (HPV) vaccine and infertility [19], oral antineoplastic drugs [20], duloxetine [21], anti-Parkinsonian agents [22], and opioid analgesics [23]; a study by Coloma et al [19] used assertion analysis to demonstrate a positive association between rosiglitazone and cardiovascular events in posts acquired from Twitter. Data mining of web search logs has also been considered for pharmacovigilance and drug safety surveillance [24, 25].…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Facebook and Twitter Monitoring to Detect Safety Signals for Medical Products: An Analysis of Recent FDA Safety Alerts

et al. 2017

View full text Add to dashboard Cite

IntroductionThe rapid expansion of the Internet and computing power in recent years has opened up the possibility of using social media for pharmacovigilance. While this general concept has been proposed by many, central questions remain as to whether social media can provide earlier warnings for rare and serious events than traditional signal detection from spontaneous report data.ObjectiveOur objective was to examine whether specific product–adverse event pairs were reported via social media before being reported to the US FDA Adverse Event Reporting System (FAERS).MethodsA retrospective analysis of public Facebook and Twitter data was conducted for 10 recent FDA postmarketing safety signals at the drug–event pair level with six negative controls. Social media data corresponding to two years prior to signal detection of each product–event pair were compiled. Automated classifiers were used to identify each ‘post with resemblance to an adverse event’ (Proto-AE), among English language posts. A custom dictionary was used to translate Internet vernacular into Medical Dictionary for Regulatory Activities (MedDRA®) Preferred Terms. Drug safety physicians conducted a manual review to determine causality using World Health Organization-Uppsala Monitoring Centre (WHO-UMC) assessment criteria. Cases were also compared with those reported in FAERS.FindingsA total of 935,246 posts were harvested from Facebook and Twitter, from March 2009 through October 2014. The automated classifier identified 98,252 Proto-AEs. Of these, 13 posts were selected for causality assessment of product–event pairs. Clinical assessment revealed that posts had sufficient information to warrant further investigation for two possible product–event associations: dronedarone–vasculitis and Banana Boat Sunscreen--skin burns. No product–event associations were found among the negative controls. In one of the positive cases, the first report occurred in social media prior to signal detection from FAERS, whereas the other case occurred first in FAERS.ConclusionsAn efficient semi-automated approach to social media monitoring may provide earlier insights into certain adverse events. More work is needed to elaborate additional uses for social media data in pharmacovigilance and to determine how they can be applied by regulatory agencies.Electronic supplementary materialThe online version of this article (doi:10.1007/s40264-016-0491-0) contains supplementary material, which is available to authorized users.

show abstract

Drug Use in the Twittersphere: A Qualitative Contextual Analysis of Tweets About Prescription Drugs

Cited by 62 publications

References 9 publications

Exploring trends of nonmedical use of prescription drugs and polydrug abuse in the Twittersphere using unsupervised machine learning

Exploring trends of nonmedical use of prescription drugs and polydrug abuse in the Twittersphere using unsupervised machine learning

“When ‘Bad’ is ‘Good’”: Identifying Personal Communication and Sentiment in Drug-Related Tweets

Evaluation of Facebook and Twitter Monitoring to Detect Safety Signals for Medical Products: An Analysis of Recent FDA Safety Alerts

Contact Info

Product

Resources

About