Intramural Research Program, National Institute on Drug Abuse, Baltimore, MD, USA.
Positive Psychology Center, University of Pennsylvania, Philadelphia, PA, USA.
Am J Drug Alcohol Abuse. 2022 Sep 3;48(5):573-585. doi: 10.1080/00952990.2022.2091450. Epub 2022 Jul 19.
Early indicators of who will remain in - or leave - treatment for substance use disorder (SUD) can drive targeted interventions to support long-term recovery. To conduct a comprehensive study of linguistic markers of SUD treatment outcomes, the current study integrated features produced by machine learning models known to have social-psychology relevance. We extracted and analyzed linguistic features from participants' Facebook posts ( = 206, 39.32% female; 55,415 postings) over the two years before they entered a SUD treatment program. Exploratory features produced by both Linguistic Inquiry and Word Count (LIWC) and Latent Dirichlet Allocation (LDA) topic modeling and the features from theoretical domains of religiosity, affect, and temporal orientation via established AI-based linguistic models were utilized. Patients who stayed in the SUD treatment for over 90 days used more words associated with religion, positive emotions, family, affiliations, and the present, and used more first-person singular pronouns (Cohen's values: [-0.39, -0.57]). Patients who discontinued their treatment before 90 days discussed more diverse topics, focused on the past, and used more articles (Cohen's values: [0.44, 0.57]). All s < .05 with Benjamini-Hochberg False Discovery Rate correction. We confirmed the literature on protective and risk social-psychological factors linking to SUD treatment in language analysis, showing that Facebook language before treatment entry could be used to identify the markers of SUD treatment outcomes. This reflects the importance of taking these linguistic features and markers into consideration when designing and recommending SUD treatment plans.
早期指标可以预测哪些人会继续接受或离开物质使用障碍（SUD）治疗，从而为支持长期康复提供有针对性的干预措施。为了全面研究 SUD 治疗结果的语言标志物，本研究整合了机器学习模型产生的特征，这些特征与社会心理学相关。我们从参与者在进入 SUD 治疗项目前两年的 Facebook 帖子中提取并分析了语言特征（=206，39.32%为女性；55415 条帖子）。使用了通过语言探究和词汇计数（LIWC）和潜在狄利克雷分配（LDA）主题建模产生的探索性特征，以及通过基于人工智能的语言模型从宗教、情感和时间取向等理论领域提取的特征。在 SUD 治疗中停留超过 90 天的患者使用了更多与宗教、积极情绪、家庭、关系和现在有关的词汇，并且使用了更多的第一人称单数代词（Cohen's 值：[-0.39，-0.57]）。在 90 天内停止治疗的患者讨论了更多不同的话题，关注过去，并使用了更多的冠词（Cohen's 值：[0.44，0.57]）。所有 s<0.05，经 Benjamini-Hochberg 错误发现率校正。我们在语言分析中证实了与 SUD 治疗相关的保护性和风险社会心理因素的文献，表明治疗前的 Facebook 语言可用于识别 SUD 治疗结果的标志物。这反映了在设计和推荐 SUD 治疗计划时考虑这些语言特征和标志物的重要性。
