top of page

Subscribe to get the latest updates from Receptiviti

Predicting Substance Use Disorder Treatment Outcomes Using Facebook Language Analysis

In a recent study, researchers aimed to identify early indicators of who will remain in or leave treatment for substance use disorder (SUD) by analyzing linguistic markers in patients' Facebook posts before they entered a SUD treatment program.

By utilizing machine learning models known to have social-psychology relevance, the researchers extracted and analyzed linguistic features from participants' Facebook posts (N = 206, 39.32% female; 55,415 postings) over the two years before treatment entry. The features from theoretical domains of religiosity, affect, and temporal orientation via established AI-based linguistic models were also used.

Results showed that patients who stayed in 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. Patients who discontinued their treatment before 90 days discussed more diverse topics, focused on the past, and used more articles. These findings confirm the literature on protective and risk social-psychological factors linking to SUD treatment in language analysis, highlighting the importance of taking these linguistic features and markers into consideration when designing and recommending SUD treatment plans.

Read the research: Linguistic predictors from Facebook postings of substance use disorder treatment retention versus discontinuation

Subscribe to the blog and get notified of new content:

Customer Stories

Customer Stories and Use Cases

Organizations of all sizes have integrated Receptiviti into their technologies and processes to uncover critical insights about the people who matter to their businesses.