Linguistic measures of psychological distance track symptom levels and treatment outcomes in a large set of psychotherapy transcripts

Language use in depressed and non-depressed mothers and their adolescent offspring

BACKGROUND

Approximately 10% of mothers experience depression each year, which increases risk for depression in offspring. Currently no research has analysed the linguistic features of depressed mothers and their adolescent offspring during dyadic interactions. We examined the extent to which linguistic features of mothers' and adolescents' speech during dyadic interactional tasks could discriminate depressed from non-depressed mothers.

METHODS

Computer-assisted linguistic analysis (Linguistic Inquiry and Word Count; LIWC) was applied to transcripts of low-income mother-adolescent dyads (N = 151) performing a lab-based problem-solving interaction task. One-way multivariate analyses were conducted to determine linguistic features hypothesized to be related to maternal depressive status that significantly differed in frequency between depressed and non-depressed mothers and higher and lower risk offspring. Logistic regression analyses were performed to classify between dyads belonging to the two groups.

RESULTS

The results showed that linguistic features in mothers' and their adolescent offsprings' speech during problem-solving interactions discriminated between maternal depression status. Many, but not all effects, were consistent with those identified in previous research using primarily written text, highlighting the validity and reliability of language behaviour associated with depressive symptomatology across lab-based and natural environmental contexts.

LIMITATIONS

Our analyses do not enable to ascertain how mothers' language behaviour may have influenced their offspring's communication patterns. We also cannot say how or whether these findings generalize to other contexts or populations.

CONCLUSION

The findings extend the existing literature on linguistic features of depression by indicating that mothers' depression is associated with linguistic behaviour during mother-adolescent interaction.

Emotion regulation elicits cross-linguistically shared and language-specific forms of linguistic distancing

Cognitively reappraising a stressful experience-reinterpreting the situation to blunt its emotional impact-is effective for regulating negative emotions. English speakers have been shown to engage in linguistic distancing when reappraising, spontaneously using words that are more abstract or impersonal. Across two preregistered studies (N = 299), we investigated whether such shifts in language use generalize to Spanish, a language proposed to offer unique tools for expressing psychological distance. Bilingual speakers of Spanish and English and a comparison group of English monolinguals transcribed their thoughts in each of their languages while responding naturally to negative images or reappraising them. Reappraisal shifted markers of psychological distance common to both languages (e.g., reduced use of "I"/"yo"), as well as Spanish-specific markers (e.g., greater use of "estar": "to be" for temporary states). Whether these linguistic shifts reflected successful emotion regulation depended on language experience: in exploratory analyses, the common markers were more strongly linked to reduced negative affect for late than early Spanish learners, and one Spanish-specific marker ("estar") also predicted reduced negative affect for early learners. Our findings suggest that people distance their language in both cross-linguistically shared and language-specific ways when regulating their emotions.

Language sentiment predicts changes in depressive symptoms

The prevalence of depression is a major societal health concern, and there is an ongoing need to develop tools that predict who will become depressed. Past research suggests that depression changes the language we use, but it is unclear whether language is predictive of worsening symptoms. Here, we test whether the sentiment of brief written linguistic responses predicts changes in depression. Across two studies (N = 467), participants provided responses to neutral open-ended questions, narrating aspects of their lives relevant to depression (e.g., mood, motivation, sleep). Participants also completed the Patient Health Questionnaire (PHQ-9) to assess depressive symptoms and a risky decision-making task with periodic measurements of momentary happiness to quantify mood dynamics. The sentiment of written responses was evaluated by human raters (N = 470), Large Language Models (LLMs; ChatGPT 3.5 and 4.0), and the Linguistic Inquiry and Word Count (LIWC) tool. We found that language sentiment evaluated by human raters and LLMs, but not LIWC, predicted changes in depressive symptoms at a three-week follow-up. Using computational modeling, we found that language sentiment was associated with current mood, but language sentiment predicted symptom changes even after controlling for current mood. In summary, we demonstrate a scalable tool that combines brief written responses with sentiment analysis by AI tools that matches human performance in the prediction of future psychiatric symptoms.

Detecting adolescent depression through passive monitoring of linguistic markers in smartphone communication

BACKGROUND

Cross sectional studies have identified linguistic correlates of major depressive disorder (MDD) in smartphone communication. However, it is unclear whether monitoring these linguistic characteristics can detect when an individual is experiencing MDD, which would facilitate timely intervention.

METHODS

Approximately 1.2 million messages typed into smartphone social communication apps (e.g. texting, social media) were passively collected from 90 adolescents with a range of depression severity over a 12-month period. Sentiment (i.e. positive vs. negative valence of text), proportions of first-person singular pronouns (e.g. 'I'), and proportions of absolutist words (e.g. 'all') were computed for each message and converted to weekly aggregates temporally aligned with weekly MDD statuses obtained from retrospective interviews. Idiographic, multilevel logistic regression models tested whether within-person deviations in these linguistic features were associated with the probability of concurrently meeting threshold for MDD.

RESULTS

Using more first-person singular pronouns in smartphone communication relative to one's own average was associated with higher odds of meeting threshold for MDD in the concurrent week (OR = 1.29; p = .007). Sentiment (OR = 1.07; p = .54) and use of absolutist words (OR = 0.99; p = .90) were not related to weekly MDD.

CONCLUSIONS

Passively monitoring use of first-person singular pronouns in adolescents' smartphone communication may help detect MDD, providing novel opportunities for early intervention.

Linguistic markers of anxiety and depression in Somatic Symptom and Related Disorders: Observational study of a digital intervention

BACKGROUND

Somatic Symptom and Related Disorders (SSRD), including chronic pain, result in frequent primary care visits, depression and anxiety symptoms, and diminished quality of life. Treatment access remains limited due to structural barriers and functional impairment. Digital delivery offers to improve access and enables transcript analysis via Natural Language Processing (NLP) to inform treatment. Therefore, we investigated asynchronous message-delivered SSRD treatment, and used NLP methods to identify symptom reduction markers from emotional valence.

METHODS

173 individuals diagnosed with SSRD received interventions from licensed therapists via messaging 5 days/week for 8 weeks. Depression and anxiety symptoms were measured with the PHQ-9 and GAD-7 from baseline every three weeks. Symptoms trajectories were identified using unsupervised random forest clustering. Emotional valence expressed and use of emotional words were extracted from patients' de-identified transcripts, respectively using VADER and NCR Lexicon. Valence differences were examined using logistic regression.

RESULTS

Two subpopulations were identified showing symptoms Improvement (n = 72; 41.62 %) and non-response (n = 101; 58.38 %). Improvement patients expressed more positive valence in the first week of treatment (OR = 1.84, CI: 1.12-3.02; p = .015) and were less likely to express negative valence by the end of treatment (OR = 0.05; CI: 0.30-0.83; p = .008). Non-response patients used more negative valence words, including pain.

LIMITATIONS

Findings were derived from observational data obtained during an ecological intervention, without the inclusion of a control group.

CONCLUSIONS

NLP identified linguistic markers distinguishing changes in anxiety and depression symptoms over treatment. Digital interventions offer new forms of delivery and provide the opportunity to automatically collect data for linguistic analysis.

Notes from the Underground: Seeking the top personality correlates of self-referencing

OBJECTIVE

Self-focused language use has been frequently assumed to reflect narcissism; however, research indicates that the association between first-person singular pronouns (i.e., "I-talk") and grandiose narcissism is negligible.

METHOD

To extend this literature, we progressively identify vulnerable narcissism and rumination as positive correlates of I-talk in five studies (valid Ns = 211, 475, 1253, 289, 1113).

RESULTS

The first study revealed positive correlates of I-talk suggestive of vulnerable narcissism. The second study showed more directly that vulnerable narcissism was a positive correlate but that this association was attributable to shared variance with neuroticism. The third study, a preregistered effort, replicated and extended the results of the second study. The fourth and fifth studies focused on rumination in a preregistered manner.

CONCLUSIONS

All the studies point to a clear distinction: While grandiose narcissism is negligibly related to I-talk, vulnerable narcissism is positively related to I-talk; moreover, rumination is a robust predictor of I-talk. A research synthesis revealed the following constructs significantly capture I-talk: depression (r = 0.10), neuroticism (r = 0.15), rumination (r = 0.14), and vulnerable narcissism (r = 0.12). The association between I-talk and neuroticism was partially mediated by rumination, providing a testable candidate mechanism for neuroticism interventions.

The Emotional Content of Children's Writing: A Data-Driven Approach

Emotion is closely associated with language, but we know very little about how children express emotion in their own writing. We used a large-scale, cross-sectional, and data-driven approach to investigate emotional expression via writing in children of different ages, and whether it varies for boys and girls. We first used a lexicon-based bag-of-words approach to identify emotional content in a large corpus of stories (N>100,000) written by 7- to 13-year-old children. Generalized Additive Models were then used to model changes in sentiment across age and gender. Two other machine learning approaches (BERT and TextBlob) validated and extended these analyses, converging on the finding that positive sentiments in children's writing decrease with age. These findings echo reports from previous studies showing a decrease in mood and an increased use of negative emotion words with age. We also found that stories by girls contained more positive sentiments than stories by boys. Our study shows the utility of large-scale data-driven approaches to reveal the content and nature of children's writing. Future experimental work should build on these observations to understand the likely complex relationships between written language and emotion, and how these change over development.

Linguistic Variables and Gender Differences Within a Messenger-Based Psychosocial Chat Counseling Service for Children and Adolescents: Cross-Sectional Study

BACKGROUND

Text messaging is widely used by young people for communicating and seeking mental health support through chat-based helplines. However, written communication lacks nonverbal cues, and language usage is an important source of information about a person's mental health state and is known to be a marker for psychopathology.

OBJECTIVE

The aim of the study was to investigate language usage, and its gender differences and associations with the presence of psychiatric symptoms within a chat counseling service for adolescents and young adults.

METHODS

For this study, the anonymized chat content of a German messenger-based psychosocial chat counseling service for children and adolescents ("krisenchat") between May 2020 and July 2021 was analyzed. In total, 661,131 messages from 6962 users were evaluated using Linguistic Inquiry and Word Count, considering the following linguistic variables: first-person singular and plural pronouns, negations, positive and negative emotion words, insight words, and causation words. Descriptive analyses were performed, and gender differences of those variables were evaluated. Finally, a binary logistic regression analysis examined the predictive value of linguistic variables on the presence of psychiatric symptoms.

RESULTS

Across all analyzed chats, first-person singular pronouns were used most frequently (965,542/8,328,309, 11.6%), followed by positive emotion words (408,087/8,328,309, 4.9%), insight words (341,460/8,328,309, 4.1%), negations (316,475/8,328,309, 3.8%), negative emotion words (266,505/8,328,309, 3.2%), causation words (241,520/8,328,309, 2.9%), and first-person plural pronouns (499,698/8,328,309, 0.6%). Female users and users identifying as diverse used significantly more first-person singular pronouns and insight words than male users (both P<.001). Negations were significantly more used by female users than male users or users identifying as diverse (P=.007). Similar findings were noted for negative emotion words (P=.01). The regression model of predicting psychiatric symptoms by linguistic variables was significant and indicated that increased use of first-person singular pronouns (odds ratio [OR] 1.05), negations (OR 1.11), and negative emotion words (OR 1.15) was positively associated with the presence of psychiatric symptoms, whereas increased use of first-person plural pronouns (OR 0.39) and causation words (OR 0.90) was negatively associated with the presence of psychiatric symptoms. Suicidality, self-harm, and depression showed the most significant correlations with linguistic variables.

CONCLUSIONS

This study highlights the importance of examining linguistic features in chat counseling contexts. By integrating psycholinguistic findings into counseling practice, counselors may better understand users' psychological processes and provide more targeted support. For instance, certain linguistic features, such as high use of first-person singular pronouns, negations, or negative emotion words, may indicate the presence of psychiatric symptoms, particularly among female users and users identifying as diverse. Further research is needed to provide an in-depth look into language processes within chat counseling services.

Differential temporal utility of passively sensed smartphone features for depression and anxiety symptom prediction: a longitudinal cohort study

While studies show links between smartphone data and affective symptoms, we lack clarity on the temporal scale, specificity (e.g., to depression vs. anxiety), and person-specific (vs. group-level) nature of these associations. We conducted a large-scale (n = 1013) smartphone-based passive sensing study to identify within- and between-person digital markers of depression and anxiety symptoms over time. Participants (74.6% female; M age = 40.9) downloaded the LifeSense app, which facilitated continuous passive data collection (e.g., GPS, app and device use, communication) across 16 weeks. Hierarchical linear regression models tested the within- and between-person associations of 2-week windows of passively sensed data with depression (PHQ-8) or generalized anxiety (GAD-7). We used a shifting window to understand the time scale at which sensed features relate to mental health symptoms, predicting symptoms 2 weeks in the future (distal prediction), 1 week in the future (medial prediction), and 0 weeks in the future (proximal prediction). Spending more time at home relative to one's average was an early signal of PHQ-8 severity (distal β = 0.219, p = 0.012) and continued to relate to PHQ-8 at medial (β = 0.198, p = 0.022) and proximal (β = 0.183, p = 0.045) windows. In contrast, circadian movement was proximally related to (β = -0.131, p = 0.035) but did not predict (distal β = 0.034, p = 0.577; medial β = -0.089, p = 0.138) PHQ-8. Distinct communication features (i.e., call/text or app-based messaging) related to PHQ-8 and GAD-7. Findings have implications for identifying novel treatment targets, personalizing digital mental health interventions, and enhancing traditional patient-provider interactions. Certain features (e.g., circadian movement) may represent correlates but not true prospective indicators of affective symptoms. Conversely, other features like home duration may be such early signals of intra-individual symptom change, indicating the potential utility of prophylactic intervention (e.g., behavioral activation) in response to person-specific increases in these signals.

Mental Health Counseling From Conversational Content With Transformer-Based Machine Learning

Importance

Use of asynchronous text-based counseling is rapidly growing as an easy-to-access approach to behavioral health care. Similar to in-person treatment, it is challenging to reliably assess as measures of process and content do not scale.

Objective

To use machine learning to evaluate clinical content and client-reported outcomes in a large sample of text-based counseling episodes of care.

Design, Setting, and Participants

In this quality improvement study, participants received text-based counseling between 2014 and 2019; data analysis was conducted from September 22, 2022, to November 28, 2023. The deidentified content of messages was retained as a part of ongoing quality assurance. Treatment was asynchronous text-based counseling via an online and mobile therapy app (Talkspace). Therapists were licensed to provide mental health treatment and were either independent contractors or employees of the product company. Participants were self-referred via online sign-up and received services via their insurance or self-pay and were assigned a diagnosis from their health care professional.

Exposure

All clients received counseling services from a licensed mental health clinician.

Main Outcomes and Measures

The primary outcomes were client engagement in counseling (number of weeks), treatment satisfaction, and changes in client symptoms, measured via the 8-item version of Patient Health Questionnaire (PHQ-8). A previously trained, transformer-based, deep learning model automatically categorized messages into types of therapist interventions and summaries of clinical content.

Results

The total sample included 166 644 clients treated by 4973 therapists (20 600 274 messages). Participating clients were predominantly female (75.23%), aged 26 to 35 years (55.4%), single (37.88%), earned a bachelor's degree (59.13%), and were White (61.8%). There was substantial variability in intervention use and treatment content across therapists. A series of mixed-effects regressions indicated that collectively, interventions and clinical content were associated with key outcomes: engagement (multiple R = 0.43), satisfaction (multiple R = 0.46), and change in PHQ-8 score (multiple R = 0.13).

Conclusions and Relevance

This quality improvement study found associations between therapist interventions, clinical content, and client-reported outcomes. Consistent with traditional forms of counseling, higher amounts of supportive counseling were associated with improved outcomes. These findings suggest that machine learning-based evaluations of content may increase the scale and specificity of psychotherapy research.

A core component of psychological therapy causes adaptive changes in computational learning mechanisms

BACKGROUND

Cognitive distancing is an emotion regulation strategy commonly used in psychological treatment of various mental health disorders, but its therapeutic mechanisms are unknown.

METHODS

935 participants completed an online reinforcement learning task involving choices between pairs of symbols with differing reward contingencies. Half (49.1%) of the sample was randomised to a cognitive self-distancing intervention and were trained to regulate or 'take a step back' from their emotional response to feedback throughout. Established computational (Q-learning) models were then fit to individuals' choices to derive reinforcement learning parameters capturing clarity of choice values (inverse temperature) and their sensitivity to positive and negative feedback (learning rates).

RESULTS

Cognitive distancing improved task performance, including when participants were later tested on novel combinations of symbols without feedback. Group differences in computational model-derived parameters revealed that cognitive distancing resulted in clearer representations of option values (estimated 0.17 higher inverse temperatures). Simultaneously, distancing caused increased sensitivity to negative feedback (estimated 19% higher loss learning rates). Exploratory analyses suggested this resulted from an evolving shift in strategy by distanced participants: initially, choices were more determined by expected value differences between symbols, but as the task progressed, they became more sensitive to negative feedback, with evidence for a difference strongest by the end of training.

CONCLUSIONS

Adaptive effects on the computations that underlie learning from reward and loss may explain the therapeutic benefits of cognitive distancing. Over time and with practice, cognitive distancing may improve symptoms of mental health disorders by promoting more effective engagement with negative information.

Capturing mood dynamics through adolescent smartphone social communication

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. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Adolescent Social Communication Through Smartphones: Linguistic Features of Internalizing Symptoms and Daily Mood

The increasing use of smartphone technology by adolescents has led to unprecedented opportunities to identify early indicators of shifting mental health. This intensive longitudinal study examined the extent to which differences in mental health and daily mood are associated with digital social communication in adolescence. In a sample of 30 adolescents (ages 11-15 years), we analyzed 22,152 messages from social media, email, and texting across one month. Lower daily mood was associated with linguistic features reflecting self-focus and reduced temporal distance. Adolescents with lower daily mood tended to send fewer positive emotion words on a daily basis, and more total words on low mood days. Adolescents with lower daily mood and higher depression symptoms tended to use more future focus words. Dynamic linguistic features of digital social communication that relate to changes in mental states may represent a novel target for passive detection of risk and early intervention in adolescence.

Depression and anxiety have distinct and overlapping language patterns: Results from a clinical interview

Depression has been associated with heightened first-person singular pronoun use (I-usage; e.g., "I," "my") and negative emotion words. However, past research has relied on nonclinical samples and nonspecific depression measures, raising the question of whether these features are unique to depression vis-à-vis frequently co-occurring conditions, especially anxiety. Using structured questions about recent life changes or difficulties, we interviewed a sample of individuals with varying levels of depression and anxiety (N = 486), including individuals in a major depressive episode (n = 228) and/or diagnosed with generalized anxiety disorder (n = 273). Interviews were transcribed to provide a natural language sample. Analyses isolated language features associated with gold standard, clinician-rated measures of depression and anxiety. Many language features associated with depression were in fact shared between depression and anxiety. Language markers with relative specificity to depression included I-usage, sadness, and decreased positive emotion, while negations (e.g., "not," "no"), negative emotion, and several emotional language markers (e.g., anxiety, stress, depression) were relatively specific to anxiety. Several of these results were replicated using a self-report measure designed to disentangle components of depression and anxiety. We next built machine learning models to detect severity of common and specific depression and anxiety using only interview language. Individuals' speech characteristics during this brief interview predicted their depression and anxiety severity, beyond other clinical and demographic variables. Depression and anxiety have partially distinct patterns of expression in spoken language. Monitoring of depression and anxiety severity via language can augment traditional assessment modalities and aid in early detection. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Natural language processing for mental health interventions: a systematic review and research framework

Neuropsychiatric disorders pose a high societal cost, but their treatment is hindered by lack of objective outcomes and fidelity metrics. AI technologies and specifically Natural Language Processing (NLP) have emerged as tools to study mental health interventions (MHI) at the level of their constituent conversations. However, NLP's potential to address clinical and research challenges remains unclear. We therefore conducted a pre-registered systematic review of NLP-MHI studies using PRISMA guidelines (osf.io/s52jh) to evaluate their models, clinical applications, and to identify biases and gaps. Candidate studies (n = 19,756), including peer-reviewed AI conference manuscripts, were collected up to January 2023 through PubMed, PsycINFO, Scopus, Google Scholar, and ArXiv. A total of 102 articles were included to investigate their computational characteristics (NLP algorithms, audio features, machine learning pipelines, outcome metrics), clinical characteristics (clinical ground truths, study samples, clinical focus), and limitations. Results indicate a rapid growth of NLP MHI studies since 2019, characterized by increased sample sizes and use of large language models. Digital health platforms were the largest providers of MHI data. Ground truth for supervised learning models was based on clinician ratings (n = 31), patient self-report (n = 29) and annotations by raters (n = 26). Text-based features contributed more to model accuracy than audio markers. Patients' clinical presentation (n = 34), response to intervention (n = 11), intervention monitoring (n = 20), providers' characteristics (n = 12), relational dynamics (n = 14), and data preparation (n = 4) were commonly investigated clinical categories. Limitations of reviewed studies included lack of linguistic diversity, limited reproducibility, and population bias. A research framework is developed and validated (NLPxMHI) to assist computational and clinical researchers in addressing the remaining gaps in applying NLP to MHI, with the goal of improving clinical utility, data access, and fairness.

Expressive writing treatments to reduce PTSD symptom severity and negative alcohol-related outcomes among trauma-exposed sexual minority women and transgender/nonbinary people: Study protocol for a mixed-method pilot trial

Background

Sexual minority women (SMW) and transgender and/or nonbinary (TNB) individuals report an elevated prevalence of posttraumatic stress disorder (PTSD) symptoms and negative alcohol-related outcomes compared to heterosexual women and cisgender people. SMW and TNB individuals also face barriers to utilizing treatment, which can result in delayed or missed appointments. Accessible, feasible, and effective treatment approaches, such as web-based expressive writing (EW) treatments, are needed to address PTSD and negative alcohol-related outcomes in these populations.

Method

We describe the design of a mixed-method pilot randomized controlled trial which will compare an EW treatment adapted for SMW and TNB people (stigma-adapted EW) and trauma (i.e., non-adapted) EW with an active (neutral-event) control to determine acceptability and feasibility of a future fully powered randomized controlled trial. The sample will include 150 trauma-exposed SMW and TNB individuals from across the United States who will be randomly assigned to stigma-adapted EW (n = 50), trauma EW (n = 50), or control (n = 50). Participants will be assessed before treatment, one-week after the first writing session, and three-months after the first writing session. This paper identifies steps for evaluating the acceptability and feasibility of the proposed study and determining changes in outcomes resulting from adapted and non-adapted EW treatments to inform refinements. This paper also highlights our strategy for testing theory-driven mediators and moderators of treatment outcomes.

Conclusions

This mixed-method pilot trial will inform the first fully powered, self-administered, brief web-based treatment to reduce PTSD symptom severity and negative alcohol-related outcomes among trauma-exposed SMW and TNB individuals.

The Promise of Affective Language for Identifying and Intervening on Psychopathology

We are in dire need of innovative tools for reducing the global burden of psychopathology. Emerging evidence suggests that analyzing language (i.e., the words people use) can grant insight into an individual's emotional experiences, their ability to regulate their emotions, and even their current experiences of psychopathology. As such, linguistic analyses of people's everyday word use may be a diagnostic marker of emotional well-being, and manipulating the words people use could foster adaptive emotion regulation and mental health. Given the ubiquity of language in everyday life, such language-based tools for measuring and intervening in emotion and mental health can advance how we identify and treat mental illnesses at a large scale. In this paper, I outline the promise of this approach and identify key problems we must solve if we are to make it a reality. In particular, I summarize evidence connecting language, emotion, and mental health for three key constructs: sentiment (i.e., the valence of one's language), linguistic distancing (i.e., using language to separate oneself from distressing stimuli), and emotion differentiation (i.e., using words to specifically identify one's emotions). I also identify open questions in need of attention for each of these constructs and this area of research as a whole. Overall, I believe the future is bright for the application of psycholinguistic approaches to mental health detection and intervention.

Analyzing text message linguistic features: Do people with depression communicate differently with their close and non-close contacts?

BACKGROUND

Relatively little is known about how communication changes as a function of depression severity and interpersonal closeness. We examined the linguistic features of outgoing text messages among individuals with depression and their close- and non-close contacts.

METHODS

419 participants were included in this 16-week-long observational study. Participants regularly completed the PHQ-8 and rated subjective closeness to their contacts. Text messages were processed to count frequencies of word usage in the LIWC 2015 libraries. A linear mixed modeling approach was used to estimate linguistic feature scores of outgoing text messages.

RESULTS

Regardless of closeness, people with higher PHQ-8 scores tended to use more differentiation words. When texting with close contacts, individuals with higher PHQ-8 scores used more first-person singular, filler, sexual, anger, and negative emotion words. When texting with non-close contacts these participants used more conjunctions, tentative, and sadness-related words and fewer first-person plural words.

CONCLUSION

Word classes used in text messages, when combined with symptom severity and subjective social closeness data, may be indicative of underlying interpersonal processes. These data may hold promise as potential treatment targets to address interpersonal drivers of depression.

A natural language processing approach reveals first-person pronoun usage and non-fluency as markers of therapeutic alliance in psychotherapy

It remains elusive what language markers derived from psychotherapy sessions are indicative of therapeutic alliance, limiting our capacity to assess and provide feedback on the trusting quality of the patient-clinician relationship. To address this critical knowledge gap, we leveraged feature extraction methods from natural language processing (NLP), a subfield of artificial intelligence, to quantify pronoun and non-fluency language markers that are relevant for communicative and emotional aspects of therapeutic relationships. From twenty-eight transcripts of non-manualized psychotherapy sessions recorded in outpatient clinics, we identified therapists' first-person pronoun usage frequency and patients' speech transition marking relaxed interaction style as potential metrics of alliance. Behavioral data from patients who played an economic game that measures social exchange (i.e. trust game) suggested that therapists' first-person pronoun usage may influence alliance ratings through their diminished trusting behavior toward therapists. Together, this work supports that communicative language features in patient-therapist dialogues could be markers of alliance.

Spinning Your Wheels: Psychological Overinvolvement and Actigraphy-Assessed Sleep Efficiency Following Marital Separation

BACKGROUND

This study investigated the ways in which adults reflect on their psychological experiences amid a recent marital separation and how these patterns of thought, manifest in language, are associated with self-reported negative affect and actigraphy-assessed sleep disturbance.

METHODS

In a sample of 138 recently separated adults assessed three times over five months, we examined within- and between-person associations among psychological overinvolvement (operationalized using verbal immediacy derived as a function of the language participants used to discuss their relationship history and divorce experience), continued attachment to an ex-partner, negative affect, and sleep efficiency.

RESULTS

The association between psychological overinvolvement and negative affect operated at the within-person level, whereas the associations between psychological overinvolvement and sleep disturbance, as well as negative affect and sleep disturbance, operated at the between-person level.

CONCLUSIONS

These findings shed light on the intraindividual processes that may explain why some people are more susceptible to poor outcomes after separation/divorce than others. Our findings suggest that individuals who express their divorce-related thoughts and feelings in a psychologically overinvolved manner may be at greatest risk for sleep disturbances after marital separation/divorce.

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

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.

Linguistic distancing predicts response to a digital single-session intervention for adolescent depression

Examining the linguistic characteristics of youths' writing may be a promising method for detecting youth who are struggling. In this study, we examined linguistic patterns of adolescent responses to writing prompts in a large, well-powered trial of an evidence-based, digital single-session intervention teaching malleability beliefs about personal traits and symptoms ("growth mindset"). Participants who completed the intervention as part of a larger randomized control trial were included in this preregistered study (n = 638, https://osf.io/zqmxt). Participants' responses were processed using Linguistic Inquiry and Word Count. We tested correlations between linguistic variables (i.e., linguistic distancing, positive affect, negative affect, insight, certainty), baseline outcome variables, post-intervention outcome variables, and 3-month post-intervention outcome variables. We also used Least Absolute Shrinkage and Selection Operator (LASSO) regression models to identify key predictors of treatment outcomes. As hypothesized, greater use of linguistic distancing was associated with lower levels of baseline hopelessness and higher levels of perceived agency. Additionally, per LASSO models including all linguistic variables, greater use of linguistic distancing predicted larger reductions in depressive symptoms from baseline to three-month follow-up. Linguistic distancing appeared to account for 27% of the variance in depression trajectories when also accounting for baseline depression. CLINICAL REGISTRATION NO: NCT04634903.