UNDERSTANDING MEDICATION NONADHERENCE FROM SOCIAL MEDIA: A SENTIMENT-ENRICHED DEEP LEARNING APPROACH br | |
Xie, Jiaheng1; Liu, Xiao2; Zeng, Daniel Dajun3,4![]() | |
Source Publication | MIS QUARTERLY
![]() |
ISSN | 0276-7783 |
2022-03-01 | |
Volume | 46Issue:1Pages:341-372 |
Corresponding Author | Xie, Jiaheng(jxie@udel.edu) |
Abstract | Medication nonadherence (MNA) can lead to serious health ramifications and costs U.S. healthcare systems $290 billion annually. Understanding the reasons underlying patients' MNA is thus an urgent goal for researchers, practitioners, and the pharmaceuticalindustry in order to mitigate negative health and economic consequences. In recent years, patient engagement on social media sites has soared, making it a cost-efficient and rich information source that can complement prior survey studies and deepen the understanding of MNA. Yet these data remain untapped in existing MNA studies because of technical challenges such as long texts, decision-making based on negative sentiment, varied patient vocabulary, and the scarcity of relevant information. For this study, we developed a sentiment-enriched deep learning method (SEDEL) to address these challenges and extract reasons for MNA. We evaluated SEDEL using 53,180 reviews concerning180 drugs and achieved a precision of 89.25%, a recall of 88.48%, and an F1 score of 88.86%. SEDEL significantly outperformed state-of-the-art baseline models. We identified nine categories of MNA reasons, which were verified by domain experts. This study contributes to IS research by devising a novel deep-learning-based approach for reason mining and by providing direct implications for the health industry and for practitioners regarding the design of interventions |
Keyword | Sentiment-enriched deep learning reason mining social media analytics health risk analytics medication nonadherence |
DOI | 10.25300/MISQ/2022/15336 |
WOS Keyword | BIG DATA ; DESIGN SCIENCE ; ADHERENCE ; ANALYTICS ; WORD ; PERSPECTIVE ; EXTRACTION ; FRAMEWORK ; FEATURES ; SUPPORT |
Indexed By | SCI |
Language | 英语 |
Funding Project | National Key Research and Development Program of China[2020AAA0103405] ; National Natural Science Foundation of China[71621002] ; National Natural Science Foundation of China[62071467] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27030100] |
Funding Organization | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of the Chinese Academy of Sciences |
WOS Research Area | Computer Science ; Information Science & Library Science ; Business & Economics |
WOS Subject | Computer Science, Information Systems ; Information Science & Library Science ; Management |
WOS ID | WOS:000785872600009 |
Publisher | SOC INFORM MANAGE-MIS RES CENT |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.ia.ac.cn/handle/173211/48397 |
Collection | 复杂系统管理与控制国家重点实验室_互联网大数据与信息安全 |
Corresponding Author | Xie, Jiaheng |
Affiliation | 1.Univ Delaware, Dept Accounting & Management Informat Syst, Lerner Coll Business & Econ, Newark, DE 19716 USA 2.Arizona State Univ, Dept Informat Syst, WP Carey Sch Business, Tempe, AZ 85287 USA 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China |
Recommended Citation GB/T 7714 | Xie, Jiaheng,Liu, Xiao,Zeng, Daniel Dajun,et al. UNDERSTANDING MEDICATION NONADHERENCE FROM SOCIAL MEDIA: A SENTIMENT-ENRICHED DEEP LEARNING APPROACH br[J]. MIS QUARTERLY,2022,46(1):341-372. |
APA | Xie, Jiaheng,Liu, Xiao,Zeng, Daniel Dajun,&Fang, Xiao.(2022).UNDERSTANDING MEDICATION NONADHERENCE FROM SOCIAL MEDIA: A SENTIMENT-ENRICHED DEEP LEARNING APPROACH br.MIS QUARTERLY,46(1),341-372. |
MLA | Xie, Jiaheng,et al."UNDERSTANDING MEDICATION NONADHERENCE FROM SOCIAL MEDIA: A SENTIMENT-ENRICHED DEEP LEARNING APPROACH br".MIS QUARTERLY 46.1(2022):341-372. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment