Linguistic analysis of Latinx patients’ responses to a text messaging adjunct during cognitive behavioral therapy for depression

Hernandez-Ramos, Rosa; Altszyler, Edgar; Figueroa, Caroline A.; Avila-Garcia, Patricia; Aguilera, Adrián

doi:10.1016/j.brat.2021.104027

Cited by 8 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In line with this notion, reductions in the use of “I” and present‐tense verbs have been linked with symptom improvement during text‐based therapy, despite language not being a central focus of treatment (Nook et al, 2022 ). Additional language markers that predict symptom change during therapy for depression include positive emotion words, negative emotion words, and certainty (Hernandez‐Ramos et al, 2022 ), the latter of which may reflect cognitive distortions. Absolutist language (superlatives and intensifiers) has also been linked with suicidal thoughts, and greater pronoun use has been linked with suicidal behavior (Homan et al, 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Prospective associations of text‐message‐based sentiment with symptoms of depression, generalized anxiety, and social anxiety

Stamatis

Meyerhoff

Liu

et al. 2022

Depression and Anxiety

View full text Add to dashboard Cite

Objective Language patterns may elucidate mechanisms of mental health conditions. To inform underlying theory and risk models, we evaluated prospective associations between in vivo text messaging language and differential symptoms of depression, generalized anxiety, and social anxiety. Methods Over 16 weeks, we collected outgoing text messages from 335 adults. Using Linguistic Inquiry and Word Count (LIWC), NRC Emotion Lexicon, and previously established depression and stress dictionaries, we evaluated the degree to which language features predict symptoms of depression, generalized anxiety, or social anxiety the following week using hierarchical linear models. To isolate the specificity of language effects, we also controlled for the effects of the two other symptom types. Results We found significant relationships of language features, including personal pronouns, negative emotion, cognitive and biological processes, and informal language, with common mental health conditions, including depression, generalized anxiety, and social anxiety (ps < .05). There was substantial overlap between language features and the three mental health outcomes. However, after controlling for other symptoms in the models, depressive symptoms were uniquely negatively associated with language about anticipation, trust, social processes, and affiliation (βs: −.10 to −.09, ps < .05), whereas generalized anxiety symptoms were positively linked with these same language features (βs: .12–.13, ps < .001). Social anxiety symptoms were uniquely associated with anger, sexual language, and swearing (βs: .12–.13, ps < .05). Conclusion Language that confers both common (e.g., personal pronouns and negative emotion) and specific (e.g., affiliation, anticipation, trust, and anger) risk for affective disorders is perceptible in prior week text messages, holding promise for understanding cognitive‐behavioral mechanisms and tailoring digital interventions.

show abstract

Section: Introductionmentioning

confidence: 99%

Prospective associations of text‐message‐based sentiment with symptoms of depression, generalized anxiety, and social anxiety

Stamatis

Meyerhoff

Liu

et al. 2022

Depression and Anxiety

View full text Add to dashboard Cite

show abstract

“…Second, although our sample was racially/ethnically diverse, adolescents were primarily females from a western, educated, industrialized, rich, and democratic background (Henrich et al, 2010), posing generalizability issues. As an example, the LIWC dictionary of religion was found to relate to greater anhedonia in our sample, but predicted more positive mood in an older, low-income, Spanish-speaking sample of patients with depression (Hernandez-Ramos et al, 2022). The issue of generalizability is perhaps more severe for the data-driven LDA topics, which are more contextually embedded than closed-vocabulary dictionaries such as VADER and LIWC (Eichstaedt et al, 2021).…”

Section: Discussionmentioning

confidence: 67%

“…Specifically, LIWC was developed and validated with relatively formal writing, such as essays, science articles, and blogs (Tausczik & Pennebaker, 2010), and thus, may not be ideal for analyzing everyday language. In line with this, a study utilizing text-message responses to a standardized prompt ("Please respond with…a message about what you are doing or thinking") from a sample of Spanish-speaking older adults found that sentiment in this context did relate to mood intraindividually (Hernandez-Ramos et al, 2022). Therefore, there is a need to employ text analytic programs sensitive to the nuances of social communication.…”

mentioning

confidence: 94%

“…Again, findings have been inconsistent for first-person singular pronouns, with evidence for (McNeilly et al, 2023; Nook et al, 2022) and against (Stamatis et al, 2022; Sun et al, 2020) an association obtained. Interestingly, two studies showed that words related to social engagement were associated with greater positive mood across closed-vocabulary (e.g., dictionaries of family and friends; Hernandez-Ramos et al, 2022; Sun et al, 2020; cf., Stamatis et al, 2022) as well as open-vocabulary approaches (e.g., topics of gossip and making plans; Sun et al, 2020). Therefore, important insights can be gleaned from examining nonaffective linguistic features.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Capturing mood dynamics through adolescent smartphone social communication.

Li,

Trivedi,

Helgren

et al. 2023

Journal of Psychopathology and Clinical Science

View full text Add to dashboard Cite

Most adolescents with depression remain undiagnosed and untreated—missed opportunities that are costly from both personal and public health perspectives. A promising approach to detecting adolescent depression in real-time and at a large scale is through their social communication on the smartphone (e.g., text messages, social media posts). Past research has shown that language from online social communication reliably indicates interindividual differences in depression. To move toward detecting the emergence of depression symptoms intraindividually, the present study tested whether sentiment (i.e., words connoting positive and negative affect) from smartphone social communication prospectively predicted daily mood fluctuations in 83 adolescents (Mage = 16.49, 73.5% female) with a wide range of depression severity. Participants completed daily mood ratings across a 90-day period, during which 354,278 messages were passively collected from social communication apps. Greater positive sentiment (i.e., more positive weighted composite valence score and a greater proportion of words expressing positive sentiment) predicted more positive next-day mood, controlling for previous-day mood. Moreover, greater proportions of positive and negative sentiment were, respectively, associated with lower anhedonia and greater dysphoria symptoms measured at baseline. Exploratory analyses of nonaffective linguistic features showed that greater use of social engagement words (e.g., friends and affiliation) and emojis (primarily consisting of hearts) predicted more positive changes in mood. Collectively, findings suggest that language from smartphone social communication can detect mood fluctuations in adolescents, laying the foundation for language-based tools to identify periods of heightened depression risk.

show abstract

“…For example, ecological momentary assessments (EMAs) provide a real-time data collection strategy delivered in the user’s natural environment. Among low-income Spanish-speaking adults, EMAs and language content analysis of brief SMS text message responses allowed for a deeper understanding of participant responses to depression treatment [ 37 ].…”

Section: Discussionmentioning

confidence: 99%

Feasibility, Usability and Acceptability of a mHealth Intervention to Reduce Cardiovascular Risk in Rural Hispanic Adults: Descriptive Study

Rowland¹,

Ramos²,

Trinidad³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

Background Mobile health (mHealth) technology using apps or devices to self-manage health behaviors is an effective strategy to improve lifestyle-related health problems such as hypertension, obesity, and diabetes. However, few studies have tested an mHealth intervention with Hispanic/Latino adults, and no studies were found testing mHealth with rural Hispanic/Latino adults, the fastest-growing population in rural areas. Objective The purpose of this study was to evaluate the feasibility, usability, and acceptability of an mHealth cardiovascular risk self-management intervention with rural Hispanic/Latino adults. Methods A descriptive study using quantitative and qualitative methods was used to evaluate the feasibility, usability, and acceptability of delivering a 12-week mHealth self-management intervention to reduce cardiovascular risk with rural Hispanic/Latino adults who were randomized to 1 of 2 groups. Both groups were asked to use MyFitnessPal to self-monitor daily steps, weight, and calories. The intervention group received support to download, initiate, and troubleshoot technology challenges with MyFitnessPal (Under Armour) and a smart scale, while the enhanced usual care group received only a general recommendation to use MyFitnessPal to support healthy behaviors. The usability of MyFitnessPal and the smart scale was measured using an adapted Health Information Technology Usability EvaluationScale (Health-ITUES). Adherence data in the intervention group (daily steps, weight, and calories) were downloaded from MyFitnessPal. Acceptability was evaluated using semistructured interviews in a subsample (n=5) of intervention group participants. Results A sample of 70 eligible participants (enhanced usual care group n=34; intervention group n=36) were enrolled between May and December 2019. The overall attrition was 28% at 12 weeks and 54% at 24 weeks. mHealth usability in the intervention group increased at each time point (6, 12, and 24 weeks). Adherence to self-monitoring using mHealth in the intervention group after week 1 was 55% for steps, 39% for calories, and 35% for weights; at the end of the 12-week intervention, the adherence to self-monitoring was 31% for steps, 11% for weight, and 8% for calories. Spikes in adherence coincided with scheduled in-person study visits. Structured interviews identified common technology challenges including scale and steps not syncing with the app and the need for additional technology support for those with limited mHealth experience. Conclusions Recruitment of rural Hispanic/Latino adults into the mHealth study was feasible using provider and participant referrals. The use of MyFitnessPal, the smart scale, and SMS text messages to self-monitor daily steps, weights, and calories was acceptable and feasible if technology support was provided. Future research should evaluate and support participants’ baseline technology skill level, provide training if needed, and use a phone call or SMS text message follow-ups as a strategy to minimize attrition. A wearable device, separate from the smartphone app, is recommended for activity tracking.

show abstract

Linguistic analysis of Latinx patients’ responses to a text messaging adjunct during cognitive behavioral therapy for depression

Cited by 8 publications

References 50 publications

Prospective associations of text‐message‐based sentiment with symptoms of depression, generalized anxiety, and social anxiety

Prospective associations of text‐message‐based sentiment with symptoms of depression, generalized anxiety, and social anxiety

Capturing mood dynamics through adolescent smartphone social communication.

Feasibility, Usability and Acceptability of a mHealth Intervention to Reduce Cardiovascular Risk in Rural Hispanic Adults: Descriptive Study

Contact Info

Product

Resources

About