Background.The behaviors and emotions associated with and reasons for nonmedical prescription drug use(NMPDU)are notwell-captured through traditional instruments such as surveys and insurance claims.Publicly available...Background.The behaviors and emotions associated with and reasons for nonmedical prescription drug use(NMPDU)are notwell-captured through traditional instruments such as surveys and insurance claims.Publicly available NMPDU-related postson social media can potentially be leveraged to study these aspects unobtrusively and at scale.Methods.We applied a machinelearning classifier to detect self-reports of NMPDU on Twitter and extracted all public posts of the associated users.Weanalyzed approximately 137 million posts from 87,718 Twitter users in terms of expressed emotions,sentiments,concerns,andpossible reasons for NMPDU via natural language processing.Results.Users in the NMPDU group express more negativeemotions and less positive emotions,more concerns about family,the past,and body,and less concerns related to work,leisure,home,money,religion,health,and achievement compared to a control group(i.e.,users who never reported NMPDU).NMPDU posts tend to be highly polarized,indicating potential emotional triggers.Gender-specific analyses show that femaleusers in the NMPDU group express more content related to positive emotions,anticipation,sadness,joy,concerns aboutfamily,friends,home,health,and the past,and less about anger than males.The findings are consistent across distinctprescription drug categories(opioids,benzodiazepines,stimulants,and polysubstance).Conclusion.Our analyses of large-scaledata show that substantial differences exist between the texts of the posts from users who self-report NMPDU on Twitter andthose who do not,and between males and females who report NMPDU.Our findings can enrich our understanding ofNMPDU and the population involved.展开更多
基金the NIDA of the NIH under the award number R01DA046619.
文摘Background.The behaviors and emotions associated with and reasons for nonmedical prescription drug use(NMPDU)are notwell-captured through traditional instruments such as surveys and insurance claims.Publicly available NMPDU-related postson social media can potentially be leveraged to study these aspects unobtrusively and at scale.Methods.We applied a machinelearning classifier to detect self-reports of NMPDU on Twitter and extracted all public posts of the associated users.Weanalyzed approximately 137 million posts from 87,718 Twitter users in terms of expressed emotions,sentiments,concerns,andpossible reasons for NMPDU via natural language processing.Results.Users in the NMPDU group express more negativeemotions and less positive emotions,more concerns about family,the past,and body,and less concerns related to work,leisure,home,money,religion,health,and achievement compared to a control group(i.e.,users who never reported NMPDU).NMPDU posts tend to be highly polarized,indicating potential emotional triggers.Gender-specific analyses show that femaleusers in the NMPDU group express more content related to positive emotions,anticipation,sadness,joy,concerns aboutfamily,friends,home,health,and the past,and less about anger than males.The findings are consistent across distinctprescription drug categories(opioids,benzodiazepines,stimulants,and polysubstance).Conclusion.Our analyses of large-scaledata show that substantial differences exist between the texts of the posts from users who self-report NMPDU on Twitter andthose who do not,and between males and females who report NMPDU.Our findings can enrich our understanding ofNMPDU and the population involved.
