A framework for multi-faceted content analysis of social media chatter regarding non-medical use of prescription medications

Abstract

Background: Substance use, including the non-medical use of prescription medications, is a global health problem resulting in hundreds of thousands of overdose deaths and other health problems. Social media has emerged as a potent source of information for studying substance use-related behaviours and their consequences. Mining large-scale social media data on the topic requires the development of natural language processing (NLP) and machine learning frameworks customized for this problem. Our objective in this research is to develop a framework for conducting a content analysis of Twitter chatter about the non-medical use of a set of prescription medications.

Methods: We collected Twitter data for four medications-fentanyl and morphine (opioids), alprazolam (benzodiazepine), and Adderall^® (stimulant), and identified posts that indicated non-medical use using an automatic machine learning classifier. In our NLP framework, we applied supervised named entity recognition (NER) to identify other substances mentioned, symptoms, and adverse events. We applied unsupervised topic modelling to identify latent topics associated with the chatter for each medication.

Results: The quantitative analysis demonstrated the performance of the proposed NER approach in identifying substance-related entities from data with a high degree of accuracy compared to the baseline methods. The performance evaluation of the topic modelling was also notable. The qualitative analysis revealed knowledge about the use, non-medical use, and side effects of these medications in individuals and communities.

Conclusions: NLP-based analyses of Twitter chatter associated with prescription medications belonging to different categories provide multi-faceted insights about their use and consequences. Our developed framework can be applied to chatter about other substances. Further research can validate the predictive value of this information on the prevention, assessment, and management of these disorders.

Keywords: Machine learning; Natural language processing; Social media; Substance use.

Fig. 1

Overview of proposed NLP framework for extracting non-medical prescription medication use-related information from Twitter chatter

Fig. 2

The main components of the proposed NLP framework (a) Named Entity Recognition architecture with embedding layer, BiLSTM layer and CRF layer, (b) Topic modelling component

Fig. 3

The coherence scores for the topics generated by BERTopic for four drugs: Fentanyl, Morphine, Alprazolam, and Adderall^®. The coherence scores range between 0–1, with values closer to 1 indicating high coherence among the topics

Fig. 4

Most frequent substances mentioned in tweets along with (a) fentanyl, (b) morphine, (c) alprazolam, and (d) Adderall^®

Fig. 5

Percentage distribution of adverse drug events (ADE) due to substance non-medical use. The scores are normalized, x-axis presents the frequency distribution and y-axis presents the ADE

Fig. 6

Top-10 Substance Use Topics from May 2021 to October 2021. Each line or marker represents a specific topic, with the x-axis showing the date and the y-axis indicating the value (importance or frequency) of each topic