Linguistic analysis of patients with mood and anxiety disorders during cognitive behavioral therapy

Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model

BACKGROUND

Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics in speech recordings collected from clinical samples.

METHODS

The data included 3919 English free-response speech recordings collected via smartphones from 265 participants with a depression history. We transcribed speech recordings via automatic speech recognition (Whisper tool, OpenAI) and identified principal topics from transcriptions using a deep learning topic model (BERTopic). To identify depression risk topics and understand the context, we compared participants' depression severity and behavioral (extracted from wearable devices) and linguistic (extracted from transcribed texts) characteristics across identified topics.

RESULTS

From the 29 topics identified, we identified 6 risk topics for depression: 'No Expectations', 'Sleep', 'Mental Therapy', 'Haircut', 'Studying', and 'Coursework'. Participants mentioning depression risk topics exhibited higher sleep variability, later sleep onset, and fewer daily steps and used fewer words, more negative language, and fewer leisure-related words in their speech recordings.

LIMITATIONS

Our findings were derived from a depressed cohort with a specific speech task, potentially limiting the generalizability to non-clinical populations or other speech tasks. Additionally, some topics had small sample sizes, necessitating further validation in larger datasets.

CONCLUSION

This study demonstrates that specific speech topics can indicate depression severity. The employed data-driven workflow provides a practical approach for analyzing large-scale speech data collected from real-world settings.

Linguistic analysis of health anxiety during the COVID-19 pandemic

Health anxiety, which is defined as fear of having or contracting serious physical illness, is particularly salient in light of the COVID-19 pandemic. We conducted a mixed methods study in which 578 narrative samples were analyzed using Linguistic Inquiry and Word Count (LIWC) software to determine linguistic markers from six LIWC categories relevant to cognitive-behavioral features of health anxiety. Broad linguistic predictors were analyzed through three backward elimination regression models in order to inform subcategory predictors of each area of health anxiety. Thus, both broad and specific linguistic predictors of general health anxiety, virus-relevant body vigilance, and fears of viral contamination were examined. Greater use of affective category words in written narratives predicted general health anxiety, as well as body vigilance and viral contamination fears. These findings represent the first direct demonstration of linguistic analysis of health anxiety and provide nuanced information about the nature and etiology of health anxiety.

Identifying self-disclosed anxiety on Twitter: A natural language processing approach

BACKGROUND

Text analyses of social media posts are a promising source of mental health information. This study used natural language processing to explore distinct language patterns on Twitter related to self-reported anxiety diagnosis.

METHODS

A total of 233.000 tweets made by 605 users (300 reporting anxiety diagnosis and 305 not) over six months were comparatively analysed, considering user behavior, Linguistic Inquiry Word Count (LIWC), and sentiment analysis. Twitter users with a self-disclosed diagnosis of anxiety were classified as 'anxious' to facilitate group comparisons.

RESULTS

Supervised machine learning models showed a high prediction accuracy (Naïve Bayes 81.1 %, Random Forests 79.8 %, and LASSO-regression 79.4 %) in identifying Twitter users' self-disclosed diagnosis of anxiety. Additionally, a Latent Profile Analysis (LPA) identified four profiles characterized by high sentiment (31 % anxious participants), low sentiment (68 % anxious), self-immersed (80 % anxious), and normative behavior (38 % anxious).

CONCLUSION

The digital footprint of self-disclosed anxiety on Twitter posts presented a high frequency of words conveying either negative sentiment, a low frequency of positive sentiment, a reduced frequency of posting, and lengthier texts. These distinct patterns enabled highly accurate prediction of anxiety diagnosis. On this basis, appropriately resourced, awareness raising, online mental health campaigns are advocated.

Emotion-dependent language featuring depression

BACKGROUND AND OBJECTIVES

Understanding language features of depression contributes to the detection of the disorder. Considering that depression is characterized by dysfunctions in emotion and individuals with depression often show emotion-dependent cognition, the present study investigated the speech features and word use of emotion-dependent narrations in patients with depression.

METHODS

Forty depression patients and forty controls were required to narrate self-relevant memories under five basic human emotions (i.e., sad, angry, fearful, neutral, and happy). Recorded speech and transcribed texts were analyzed.

RESULTS

Patients with depression, as compared to non-depressed individuals, talked slower and less. They also performed differently in using negative emotion, work, family, sex, biology, health, and assent words regardless of emotion manipulation. Moreover, the use of words such as first person singular pronoun, past tense, causation, achievement, family, death, psychology, impersonal pronoun, quantifier and preposition words displayed emotion-dependent differences between groups. With the involvement of emotion, linguistic indicators associated with depressive symptoms were identified and explained 71.6% variances of depression severity.

LIMITATIONS

Word use was analyzed based on the dictionary which does not cover all the words spoken in the memory task, resulting in text data loss. Besides, a relatively small number of depression patients were included in the present study and therefore the results need confirmation in future research using big emotion-dependent data of speech and texts.

CONCLUSIONS

Our findings suggest that consideration of different emotional contexts is an effective means to improve the accuracy of depression detection via the analysis of word use and speech features.

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.

The effect of cognitive-behavioral group therapy on reducing depression and anxiety in patients with mood disorders: experimental research

Mood disorders are one of the most common psychiatric disorders that manifest as a low mood in depressed people or a high mood in manic people. The cognitive-behavioral therapy group is one of the most effective forms of intervention available for patients with mood disorders. This research aimed to evaluate the effect of cognitive-behavioral group therapy in reducing depression and anxiety in patients with mood disorders.

CASE PRESENTATION

The study was a semi-experimental study with a pretest-post-test design with a control group. The research subjects were 60 patients hospitalized in the psychiatric department of Razi Hospital in Tehran, who were randomly divided into two experimental (N:30) and control (N:30) groups. Both groups took medicine as usual. Before the therapeutic intervention, both groups were evaluated with Beck's depression questionnaire and the Zung anxiety scale. In addition to drug therapy, the experimental group participated in ten sessions of the cognitive-behavioral therapy group, and in the control group, no psychological intervention was performed except for drug therapy. At the end of the nonpharmacological treatment intervention, both groups were evaluated again with the aforementioned tests. The obtained data were analyzed using independent and dependent t-tests.

CLINICAL DISCUSSION

The research findings showed that the cognitive-behavioral therapy group was significantly (P<0.05) effective in reducing the depression of hospitalized patients with mood disorders, but this method did not have much effect in reducing the anxiety of the patients.

CONCLUSION

Cognitive-behavioral group therapy can be effective in reducing depression in hospitalized patients with mood disorders.

Personalized State Anxiety Detection: An Empirical Study with Linguistic Biomarkers and A Machine Learning Pipeline

Individuals high in social anxiety symptoms often exhibit elevated state anxiety in social situations. Research has shown it is possible to detect state anxiety by leveraging digital biomarkers and machine learning techniques. However, most existing work trains models on an entire group of participants, failing to capture individual differences in their psychological and behavioral responses to social contexts. To address this concern, in Study 1, we collected linguistic data from N=35 high socially anxious participants in a variety of social contexts, finding that digital linguistic biomarkers significantly differ between evaluative vs. non-evaluative social contexts and between individuals having different trait psychological symptoms, suggesting the likely importance of personalized approaches to detect state anxiety. In Study 2, we used the same data and results from Study 1 to model a multilayer personalized machine learning pipeline to detect state anxiety that considers contextual and individual differences. This personalized model outperformed the baseline's F1-score by 28.0%. Results suggest that state anxiety can be more accurately detected with personalized machine learning approaches, and that linguistic biomarkers hold promise for identifying periods of state anxiety in an unobtrusive way.

Depressive symptoms are specifically related to speech pauses in schizophrenia spectrum disorders

Depression is a common and debilitating mental illness associated with sadness and negativity and is often comorbid with other psychiatric conditions, such as schizophrenia. Depressive symptoms are presently primarily assessed through clinical interviews, however there are other behavioural indicators being investigated as more objective methods of depressive symptom assessment. The present study aimed to evaluate the utility of assessing depression using quantitative speech parameters by comparing speech between 23 schizophrenia/schizoaffective patients with clinically significant depressive symptoms (DP) 19 schizophrenia/schizoaffective patients without depressive symptoms (NDP) and 22 healthy controls with no psychiatric history (HC). Participant audio recordings were transcribed and analyzed to extract five types of speech variables: utterances, words, speaking rate, formulation errors and pauses. The results indicated that DP patients produced significantly more pauses within utterances, and had more utterances with pauses compared to NDP patients and HCs (p = <.05), who performed similarly to each other. Word, speaking rate and formulation errors variables were not significantly different between the patient groups (p > .05). The findings suggest that depressive symptoms may have a specific relationship to speech pauses, and support the potential future use of speech pause assessments as an alternative and objective depression rating and monitoring tool.

Applications of Speech Analysis in Psychiatry

ABSTRACT

The need for objective measurement in psychiatry has stimulated interest in alternative indicators of the presence and severity of illness. Speech may offer a source of information that bridges the subjective and objective in the assessment of mental disorders. We systematically reviewed the literature for articles exploring speech analysis for psychiatric applications. The utility of speech analysis depends on how accurately speech features represent clinical symptoms within and across disorders. We identified four domains of the application of speech analysis in the literature: diagnostic classification, assessment of illness severity, prediction of onset of illness, and prognosis and treatment outcomes. We discuss the findings in each of these domains, with a focus on how types of speech features characterize different aspects of psychopathology. Models that bring together multiple speech features can distinguish speakers with psychiatric disorders from healthy controls with high accuracy. Differentiating between types of mental disorders and symptom dimensions are more complex problems that expose the transdiagnostic nature of speech features. Convergent progress in speech research and computer sciences opens avenues for implementing speech analysis to enhance objectivity of assessment in clinical practice. Application of speech analysis will need to address issues of ethics and equity, including the potential to perpetuate discriminatory bias through models that learn from clinical assessment data. Methods that mitigate bias are available and should play a key role in the implementation of speech analysis.

Fluctuations of psychological states on Twitter before and during COVID-19

The COVID-19 pandemic has been repeatedly associated with poor mental health. Previous studies have mostly focused on short time frames such as around the first lockdown periods, and the majority of research is based on self-report questionnaires. Less is known about the fluctuations of psychological states over longer time frames across the pandemic. Twitter timelines of 4,735 users from London and New York were investigated to shed light on potential fluctuations of several psychological states and constructs related to the pandemic. Moving averages are presented for the years 2020 and 2019. Further, mixed negative binomial regression models were fitted to estimate monthly word counts for the time before and during the pandemic. Several psychological states and constructs fluctuated heavily on Twitter during 2020 but not during 2019. Substantial increases in levels of sadness, anxiety, anger, and concerns about home and health were observed around the first lockdown periods in both cities. The levels of most constructs decreased after the initial spike, but negative emotions such as sadness, anxiety, and anger remained elevated throughout 2020 compared to the year prior to the pandemic. Tweets from both cities showed remarkably similar temporal patterns, and there are similarities to reactions found on Twitter following other previous traumatic events.

The Role of Online Social Support in Patients Undergoing Infertility Treatment - A Comparison of Pregnant and Non-pregnant Members

The role of social support in the online setting is explored in this study. For this purpose, the posts of infertility treatment patients participating in an infertility treatment online support group between 2002 and 2016 were retrieved. Members who contributed at least 100 words were divided into two groups according to the treatment outcome they reported (pregnancy). The association between the length of group membership, type of support provided, intensity of interaction, active support seeking, overall sentiment and the amount of sadness, anxiety and anger words and the treatment outcome was examined. The findings suggest that online social, in particular emotional, support acts as a buffer between the stressor and the treatment outcome. The expression of anger and initiating of communication by new members diminish this relationship.

Predicting Generalized Anxiety Disorder from Impromptu Speech Transcripts Using Context-Aware Transformer-Based Neural Networks: Model Evaluation study (Preprint)

BACKGROUND

The ability to automatically detect anxiety disorders from speech could be useful as a screening tool for an anxiety disorder. Prior studies have shown that individual words in textual transcripts of speech have an association with anxiety severity. Transformer-based neural networks are models that have been recently shown to have powerful predictive capabilities based on the context of more than one input word. Transformers detect linguistic patterns and can be separately trained to make specific predictions based on these patterns.

OBJECTIVE

This study aimed to determine whether a transformer-based language model can be used to screen for generalized anxiety disorder from impromptu speech transcripts.

METHODS

A total of 2000 participants provided an impromptu speech sample in response to a modified version of the Trier Social Stress Test (TSST). They also completed the Generalized Anxiety Disorder 7-item (GAD-7) scale. A transformer-based neural network model (pretrained on large textual corpora) was fine-tuned on the speech transcripts and the GAD-7 to predict whether a participant was above or below a screening threshold of the GAD-7. We reported the area under the receiver operating characteristic curve (AUROC) on the test data and compared the results with a baseline logistic regression model using the Linguistic Inquiry and Word Count (LIWC) features as input. Using the integrated gradient method to determine specific words that strongly affect the predictions, we inferred specific linguistic patterns that influence the predictions.

RESULTS

The baseline LIWC-based logistic regression model had an AUROC value of 0.58. The fine-tuned transformer model achieved an AUROC value of 0.64. Specific words that were often implicated in the predictions were also dependent on the context. For example, the first-person singular pronoun "I" influenced toward an anxious prediction 88% of the time and a nonanxious prediction 12% of the time, depending on the context. Silent pauses in speech, also often implicated in predictions, influenced toward an anxious prediction 20% of the time and a nonanxious prediction 80% of the time.

CONCLUSIONS

There is evidence that a transformer-based neural network model has increased predictive power compared with the single word-based LIWC model. We also showed that the use of specific words in a specific context-a linguistic pattern-is part of the reason for the better prediction. This suggests that such transformer-based models could play a useful role in anxiety screening systems.

The development and validation of the Romanian version of Linguistic Inquiry and Word Count 2015 (Ro-LIWC2015)

Today, performing automatic language analysis to extract meaning from natural language is one of the top-notch directions in social science research, but it can be challenging. Linguistic Inquiry and Word Count 2015 (LIWC2015; Pennebaker et al. 2015) is one of the most versatile, yet easy to master instruments to transform any text into data, meeting the needs of psychologists who are not usually proficient in data science. Moreover, LIWC2015 is already available in multiple languages, which opens the door to exciting intercultural quests. The current article introduces the first Romanian version of LIWC2015, Ro-LIWC2015, and thus, contributes to the line of research concerning multilingual analysis. Throughout the paper, we describe the challenges of creating the Romanian dictionary and discuss other linguistics aspects, which could be useful for new adaptations of LIWC2015. Also, we present the results of two studies for assessing the criterion validity of Ro-LIWC2015. The first study focuses on the consistency between the Romanian and the English dictionaries in analyzing a corpus of books. The second study tests whether Ro-LIWC2015 can acquire linguistic differences in contrasting corpora. For this purpose, we analyzed posts from help-seeking forums for anxiety, depression, and health issues, and leveraged supervised learning to address several classification problems. The selected algorithm allows feature ranking, which facilitates more thorough interpretations. The linguistic markers extracted with Ro-LIWC2015 mirrored a number of disorder-specific features of depression and anxiety. Given the obtained results, this research encourages the use of Ro-LIWC2015 for hypothesis testing.

Prediction of Online Psychological Help-Seeking Behavior During the COVID-19 Pandemic: An Interpretable Machine Learning Method

Online mental health service (OMHS) has been named as the best psychological assistance measure during the COVID-19 pandemic. An interpretable, accurate, and early prediction for the demand of OMHS is crucial to local governments and organizations which need to allocate and make the decision in mental health resources. The present study aimed to investigate the influence of the COVID-19 pandemic on the online psychological help-seeking (OPHS) behavior in the OMHS, then propose a machine learning model to predict and interpret the OPHS number in advance. The data was crawled from two Chinese OMHS platforms. Linguistic inquiry and word count (LIWC), neural embedding-based topic modeling, and time series analysis were utilized to build time series feature sets with lagging one, three, seven, and 14 days. Correlation analysis was used to examine the impact of COVID-19 on OPHS behaviors across different OMHS platforms. Machine learning algorithms and Shapley additive explanation (SHAP) were used to build the prediction. The result showed that the massive growth of OPHS behavior during the COVID-19 pandemic was a common phenomenon. The predictive model based on random forest (RF) and feature sets containing temporal features of the OPHS number, mental health topics, LIWC, and COVID-19 cases achieved the best performance. Temporal features of the OPHS number showed the biggest positive and negative predictive power. The topic features had incremental effects on performance of the prediction across different lag days and were more suitable for OPHS prediction compared to the LIWC features. The interpretable model showed that the increase in the OPHS behaviors was impacted by the cumulative confirmed cases and cumulative deaths, while it was not sensitive in the new confirmed cases or new deaths. The present study was the first to predict the demand for OMHS using machine learning during the COVID-19 pandemic. This study suggests an interpretable machine learning method that can facilitate quick, early, and interpretable prediction of the OPHS behavior and to support the operational decision-making; it also demonstrated the power of utilizing the OMHS platforms as an always-on data source to obtain a high-resolution timeline and real-time prediction of the psychological response of the online public.

Analysis of recreational psychedelic substance use experiences classified by substance

RATIONALE AND OBJECTIVES

Differences among psychedelic substances regarding their subjective experiences are clinically and scientifically interesting. Quantitative linguistic analysis is a powerful tool to examine such differences. This study compared five psychedelic substance report groups and a non-psychedelic report group on quantitative linguistic markers of psychological states and processes derived from recreational use-based online experience reports.

METHODS

Using 2947 publicly available online reports, we compared Ayahuasca and N,N-dimethyltryptamine (DMT, analyzed together), ketamine, lysergic acid diethylamide (LSD), 3,4-methylenedioxymethamphetamine (MDMA), psilocybin (mushroom), and antidepressant drug use experiences. We examined word frequencies related to various psychological states and processes and semantic proximity to psychedelic and mystical experience scales.

RESULTS

Linguistic markers of psychological function indicated distinct effect profiles. For example, MDMA experience reports featured an emotionally intensifying profile accompanied by many cognitive process words and dynamic-personal language. In contrast, Ayahuasca and DMT experience reports involved relatively little emotional language, few cognitive process words, increased analytical thinking-associated language, and the most semantic similarity with psychedelic and mystical experience descriptions. LSD, psilocybin mushroom, and ketamine reports showed only small differences on the emotion-, analytical thinking-, psychedelic, and mystical experience-related language outcomes. Antidepressant reports featured more negative emotional and cognitive process-related words, fewer positive emotional and analytical thinking-related words, and were generally not similar to mystical and psychedelic language.

CONCLUSION

This article addresses an existing research gap regarding the comparison of different psychedelic drugs on linguistic profiles of psychological states, processes, and experiences. The large sample of experience reports involving multiple psychedelic drugs provides valuable information that would otherwise be difficult to obtain. The results could inform experimental research into psychedelic drug effects in healthy populations and clinical trials for psychedelic treatments of psychiatric problems.

Natural Language Processing as an Emerging Tool to Detect Late-Life Depression

Late-life depression (LLD) is a major public health concern. Despite the availability of effective treatments for depression, barriers to screening and diagnosis still exist. The use of current standardized depression assessments can lead to underdiagnosis or misdiagnosis due to subjective symptom reporting and the distinct cognitive, psychomotor, and somatic features of LLD. To overcome these limitations, there has been a growing interest in the development of objective measures of depression using artificial intelligence (AI) technologies such as natural language processing (NLP). NLP approaches focus on the analysis of acoustic and linguistic aspects of human language derived from text and speech and can be integrated with machine learning approaches to classify depression and its severity. In this review, we will provide rationale for the use of NLP methods to study depression using speech, summarize previous research using NLP in LLD, compare findings to younger adults with depression and older adults with other clinical conditions, and discuss future directions including the use of complementary AI strategies to fully capture the spectrum of LLD.

Behavioral Activation and Depression Symptomatology: Longitudinal Assessment of Linguistic Indicators in Text-Based Therapy Sessions

BACKGROUND

Behavioral activation (BA) is rooted in the behavioral theory of depression, which states that increased exposure to meaningful, rewarding activities is a critical factor in the treatment of depression. Assessing constructs relevant to BA currently requires the administration of standardized instruments, such as the Behavioral Activation for Depression Scale (BADS), which places a burden on patients and providers, among other potential limitations. Previous work has shown that depressed and nondepressed individuals may use language differently and that automated tools can detect these differences. The increasing use of online, chat-based mental health counseling presents an unparalleled resource for automated longitudinal linguistic analysis of patients with depression, with the potential to illuminate the role of reward exposure in recovery.

OBJECTIVE

This work investigated how linguistic indicators of planning and participation in enjoyable activities identified in online, text-based counseling sessions relate to depression symptomatology over time.

METHODS

Using distributional semantics methods applied to a large corpus of text-based online therapy sessions, we devised a set of novel BA-related categories for the Linguistic Inquiry and Word Count (LIWC) software package. We then analyzed the language used by 10,000 patients in online therapy chat logs for indicators of activation and other depression-related markers using LIWC.

RESULTS

Despite their conceptual and operational differences, both previously established LIWC markers of depression and our novel linguistic indicators of activation were strongly associated with depression scores (Patient Health Questionnaire [PHQ]-9) and longitudinal patient trajectories. Emotional tone; pronoun rates; words related to sadness, health, and biology; and BA-related LIWC categories appear to be complementary, explaining more of the variance in the PHQ score together than they do independently.

CONCLUSIONS

This study enables further work in automated diagnosis and assessment of depression, the refinement of BA psychotherapeutic strategies, and the development of predictive models for decision support.

Emotions in Covid-19 Twitter discourse following the introduction of social contact restrictions in Central Europe

Aim

Non-pharmaceutical interventions such as lockdowns have played a critical role in preventing the spread of the Covid-19 pandemic, but may increase psychological burden. This study sought to examine emotions reflected in social media discourse following the introduction of social contact restrictions in Central Europe.

Subjects and methods

German-language Twitter posts containing ‘#corona’ and ‘#covid-19’ were collected between 2020/03/18 – 2020/04/24. A total of 79,760 tweets were included in the final analysis. Rates of expressions of positive emotion, anxiety, sadness and anger were compared over time. Bi-term topic models were applied to extract topics of discussion and examine association with emotions.

Results

Rates of anxiety, sadness and positive emotion decreased in the period following the introduction of social contact restrictions. A total of 16 topics were associated with emotions, which related to four general themes: social contact restrictions, life during lockdown, infection-related issues, and impact of the pandemic on public and private life. Several unique patterns of association between topics and emotions emerged.

Conclusion

Results suggest decreasing polarity of emotions among the public following the introduction of social contact restrictions. Monitoring of social media activity may prove beneficial for an adaptive understanding of changing public concerns during the Covid-19 pandemic.

Physiological sensation word usage in social anxiety disorder with and without comorbid depression

BACKGROUND & OBJECTIVES

Social anxiety disorder (SAD) is characterized by a fear of showing anxiety symptoms, which may manifest in greater physiological sensation (PS) word usage, especially when describing their anxious experiences. However, the role of comorbid major depressive disorder (MDD) is unknown. Given blunted physiological arousal in MDD, the SAD only group (SAD) may use more PS words than the comorbid (COM) group with SAD and MDD when discussing anxious memories. Due to more severe symptomology, however, the COM group may use more PS words than the SAD group. We examined these competing hypotheses.

METHODS

The SAD (n = 30), COM (n = 19), and control (CTL; n = 30) groups recalled their happiest, saddest, and most anxious events. The proportion of PS words was examined.

RESULTS

The SAD group used significantly more PS words than the CTL group, whose PS words did not differ significantly from the COM group; the SAD group used marginally more PS words than the COM group. Anxious memories contained significantly more PS words than happiest and saddest memories. Happiest and saddest memories did not significantly differ in PS words.

LIMITATIONS

The PS words list was created by the authors, and a LIWC dictionary was not used.

CONCLUSIONS

Blunted physiological arousal in MDD may have contributed to lower PS word usage in the COM group than the SAD group. Understanding linguistic differences between these groups may provide clinicians with insight into these individuals' preoccupations with bodily sensations that may maintain or exacerbate symptoms of anxiety.

Quantitative language features identify placebo responders in chronic back pain

ABSTRACT

Although placebo effect sizes in clinical trials of chronic pain treatments have been increasing, it remains unknown if characteristics of individuals' thoughts or previous experiences can reliably infer placebo pill responses. Research using language to investigate emotional and cognitive processes has recently gained momentum. Here, we quantified placebo responses in chronic back pain using more than 300 semantic and psycholinguistic features derived from patients' language. This speech content was collected in an exit interview as part of a clinical trial investigating placebo analgesia (62 patients, 42 treated; 20 not treated). Using a nested leave-one-out cross-validated approach, we distinguished placebo responders from nonresponders with 79% accuracy using language features alone; a subset of these features-semantic distances to identity and stigma and the number of achievement-related words-also explained 46% of the variance in placebo analgesia. Importantly, these language features were not due to generic treatment effects and were associated with patients' specific baseline psychological traits previously shown to be predictive of placebo including awareness and personality characteristics, explaining an additional 31% of the variance in placebo analgesia beyond that of personality. Initial interpretation of the features suggests that placebo responders differed in how they talked about negative emotions and the extent that they expressed awareness to various aspects of their experiences; differences were also seen in time spent talking about leisure activities. These results indicate that patients' language is sufficient to identify a placebo response and implie that specific speech features may be predictive of responders' previous treatment.

Identification of Emotional Expression With Cancer Survivors: Validation of Linguistic Inquiry and Word Count

Background

Given the high volume of text-based communication such as email, Facebook, Twitter, and additional web-based and mobile apps, there are unique opportunities to use text to better understand underlying psychological constructs such as emotion. Emotion recognition in text is critical to commercial enterprises (eg, understanding the valence of customer reviews) and to current and emerging clinical applications (eg, as markers of clinical progress and risk of suicide), and the Linguistic Inquiry and Word Count (LIWC) is a commonly used program.

Objective

Given the wide use of this program, the purpose of this study is to update previous validation results with two newer versions of LIWC.

Methods

Tests of proportions were conducted using the total number of emotion words identified by human coders for each emotional category as the reference group. In addition to tests of proportions, we calculated F scores to evaluate the accuracy of LIWC 2001, LIWC 2007, and LIWC 2015.

Results

Results indicate that LIWC 2001, LIWC 2007, and LIWC 2015 each demonstrate good sensitivity for identifying emotional expression, whereas LIWC 2007 and LIWC 2015 were significantly more sensitive than LIWC 2001 for identifying emotional expression and positive emotion; however, more recent versions of LIWC were also significantly more likely to overidentify emotional content than LIWC 2001. LIWC 2001 demonstrated significantly better precision (F score) for identifying overall emotion, negative emotion, and anxiety compared with LIWC 2007 and LIWC 2015.

Conclusions

Taken together, these results suggest that LIWC 2001 most accurately reflects the emotional identification of human coders.

A complex systems approach to the study of change in psychotherapy

BACKGROUND

A growing body of research highlights the limitations of traditional methods for studying the process of change in psychotherapy. The science of complex systems offers a useful paradigm for studying patterns of psychopathology and the development of more functional patterns in psychotherapy. Some basic principles of change are presented from subdisciplines of complexity science that are particularly relevant to psychotherapy: dynamical systems theory, synergetics, and network theory. Two early warning signs of system transition that have been identified across sciences (critical fluctuations and critical slowing) are also described. The network destabilization and transition (NDT) model of therapeutic change is presented as a conceptual framework to import these principles to psychotherapy research and to suggest future research directions.

DISCUSSION

A complex systems approach has a number of implications for psychotherapy research. We describe important design considerations, targets for research, and analytic tools that can be used to conduct this type of research.

CONCLUSIONS

A complex systems approach to psychotherapy research is both viable and necessary to more fully capture the dynamics of human change processes. Research to date suggests that the process of change in psychotherapy can be nonlinear and that periods of increased variability and critical slowing might be early warning signals of transition in psychotherapy, as they are in other systems in nature. Psychotherapy research has been limited by small samples and infrequent assessment, but ambulatory and electronic methods now allow researchers to more fully realize the potential of concepts and methods from complexity science.

Patient access to clinical notes in oncology: A mixed method analysis of oncologists' attitudes and linguistic characteristics towards notes

BACKGROUND

Providers have expressed concern about patient access to clinical notes. There is the possibility that providers may linguistically censor notes knowing that patients have access.

PURPOSE

Qualitative interviews and a pre- and post- linguistic analysis of the implementation of OpenNotes was performed to determine whether oncologists changed the content and style of their notes.

METHODS

Mixed methods were utilized, including 13 semi-structured interviews with oncologists and random effects modeling of over 500 clinical notes. The Linguistic Inquiry and Word Count program was used to evaluate notes for emotions, thinking styles, and social concerns.

RESULTS

No significant differences from pre- and post-implementation of OpenNotes was found. Thematic analysis revealed that oncologists were concerned that changing their notes would negatively impact multidisciplinary communication. However, oncologists acknowledged that notes could be more patient-friendly and may stimulate patient-provider communication.

CONCLUSIONS

Although oncologists were aware that patients could have access, they felt strongly about not changing the content of notes. A comparison between pre- and post-implementation confirmed this view and found that notes did not change.

PRACTICE IMPLICATIONS

Patient access to oncologist's notes may serve as an opportunity to reinforce important aspects of the consultation.

Determining Emotional Tone and Verbal Behavior in Patients With Tinnitus and Hyperacusis: An Exploratory Mixed-Methods Study

Purpose The purpose of this study was to evaluate the emotional tone and verbal behavior of social media users who self-identified as having tinnitus and/or hyperacusis that caused self-described negative consequences on daily life or health. Research Design and Method An explanatory mixed-methods design was utilized. Two hundred "initial" and 200 "reply" Facebook posts were collected from members of a tinnitus group and a hyperacusis group. Data were analyzed via the LIWC 2015 software program and compared to typical bloggers. As this was an explanatory mixed-methods study, we used qualitative thematic analyses to explain, interpret, and illustrate the quantitative results. Results Overall, quantitative results indicated lower overall emotional tone for all categories (tinnitus and hyperacusis, initial and reply), which was mostly influenced by higher negative emotion. Higher levels of authenticity or truth were found in the hyperacusis sample but not in the tinnitus sample. Lower levels of clout (social standing) were indicated in all groups, and a lower level of analytical thinking style (concepts and complex categories rather than narratives) was found in the hyperacusis sample. Additional analysis of the language indicated higher levels of sadness and anxiety in all groups and lower levels of anger, particularly for initial replies. These data support prior findings indicating higher levels of anxiety and depression in this patient population based on the actual words in blog posts and not from self-report questionnaires. Qualitative results identified 3 major themes from both the tinnitus and hyperacusis texts: suffering, negative emotional tone, and coping strategies. Conclusions Results from this study suggest support for the predominant clinical view that patients with tinnitus and hyperacusis have higher levels of anxiety and depression than the general population. The extent of the suffering described and patterns of coping strategies suggest clinical practice patterns and the need for research in implementing improved practice plans.

Detecting Signs of Depression in Tweets in Spanish: Behavioral and Linguistic Analysis

BACKGROUND

Mental disorders have become a major concern in public health, and they are one of the main causes of the overall disease burden worldwide. Social media platforms allow us to observe the activities, thoughts, and feelings of people's daily lives, including those of patients suffering from mental disorders. There are studies that have analyzed the influence of mental disorders, including depression, in the behavior of social media users, but they have been usually focused on messages written in English.

OBJECTIVE

The study aimed to identify the linguistic features of tweets in Spanish and the behavioral patterns of Twitter users who generate them, which could suggest signs of depression.

METHODS

This study was developed in 2 steps. In the first step, the selection of users and the compilation of tweets were performed. A total of 3 datasets of tweets were created, a depressive users dataset (made up of the timeline of 90 users who explicitly mentioned that they suffer from depression), a depressive tweets dataset (a manual selection of tweets from the previous users, which included expressions indicative of depression), and a control dataset (made up of the timeline of 450 randomly selected users). In the second step, the comparison and analysis of the 3 datasets of tweets were carried out.

RESULTS

In comparison with the control dataset, the depressive users are less active in posting tweets, doing it more frequently between 23:00 and 6:00 (P<.001). The percentage of nouns used by the control dataset almost doubles that of the depressive users (P<.001). By contrast, the use of verbs is more common in the depressive users dataset (P<.001). The first-person singular pronoun was by far the most used in the depressive users dataset (80%), and the first- and the second-person plural pronouns were the least frequent (0.4% in both cases), this distribution being different from that of the control dataset (P<.001). Emotions related to sadness, anger, and disgust were more common in the depressive users and depressive tweets datasets, with significant differences when comparing these datasets with the control dataset (P<.001). As for negation words, they were detected in 34% and 46% of tweets in among depressive users and in depressive tweets, respectively, which are significantly different from the control dataset (P<.001). Negative polarity was more frequent in the depressive users (54%) and depressive tweets (65%) datasets than in the control dataset (43.5%; P<.001).

CONCLUSIONS

Twitter users who are potentially suffering from depression modify the general characteristics of their language and the way they interact on social media. On the basis of these changes, these users can be monitored and supported, thus introducing new opportunities for studying depression and providing additional health care services to people with this disorder.

Text-Based Detection of the Risk of Depression

This study examines the relationship between language use and psychological characteristics of the communicator. The aim of the study was to find models predicting the depressivity of the writer based on the computational linguistic markers of his/her written text. Respondents' linguistic fingerprints were traced in four texts of different genres. Depressivity was measured using the Depression, Anxiety and Stress Scale (DASS-21). The research sample (N = 172, 83 men, 89 women) was created by quota sampling an adult Czech population. Morphological variables of the texts showing differences (M-W test) between the non-depressive and depressive groups were incorporated into predictive models. Results: Across all participants, the data best fit predictive models of depressivity using morphological characteristics from the informal text "letter from holidays" (Nagelkerke r ² = 0.526 for men and 0.670 for women). For men, models for the formal texts "cover letter" and "complaint" showed moderate fit with the data (r ² = 0.479 and 0.435). The constructed models show weak to substantial recall (0.235 - 0.800) and moderate to substantial precision (0.571 - 0.889). Morphological variables appearing in the final models vary. There are no key morphological characteristics suitable for all models or for all genres. The resulting models' properties demonstrate that they should be suitable for screening individuals at risk of depression and the most suitable genre is informal text ("letter from holidays").