Paper Type
full
Description
Opioid use disorder (OUD) refers to the physical and psychological reliance on opioids. OUD costs the US healthcare systems $504 billion annually and poses significant mortality risk for patients. Understanding and mitigating the barriers to OUD treatment is a high-priority area. Current OUD treatment studies rely on surveys with low response rate because of social stigma. In this paper, we explore social media as a new data source to study OUD treatments. We develop the SImilarity Network-based DEep Learning (SINDEL) to discover barriers to OUD treatment from the patient narratives and address the challenge of morphs. SINDEL reaches an F1 score of 76.79%. Thirteen types of OUD treatment barriers were identified and verified by domain experts. This study contributes to IS literature by proposing a novel deep-learning-based analytical approach with impactful implications for health practitioners.
Recommended Citation
Xie, Jiaheng; Zhang, Zhu; Liu, Xiao; and Zeng, Daniel, "Discovering Barriers to Opioid Addiction Treatment from Social Media: A Similarity Network-Based Deep Learning Approach" (2019). ICIS 2019 Proceedings. 2.
https://aisel.aisnet.org/icis2019/data_science/data_science/2
Discovering Barriers to Opioid Addiction Treatment from Social Media: A Similarity Network-Based Deep Learning Approach
Opioid use disorder (OUD) refers to the physical and psychological reliance on opioids. OUD costs the US healthcare systems $504 billion annually and poses significant mortality risk for patients. Understanding and mitigating the barriers to OUD treatment is a high-priority area. Current OUD treatment studies rely on surveys with low response rate because of social stigma. In this paper, we explore social media as a new data source to study OUD treatments. We develop the SImilarity Network-based DEep Learning (SINDEL) to discover barriers to OUD treatment from the patient narratives and address the challenge of morphs. SINDEL reaches an F1 score of 76.79%. Thirteen types of OUD treatment barriers were identified and verified by domain experts. This study contributes to IS literature by proposing a novel deep-learning-based analytical approach with impactful implications for health practitioners.