Differential lexical correlates of social cognition and metacognition in schizophrenia; a study of spontaneously-generated life narratives

Quantifying abnormal emotion processing: A novel computational assessment method and application in schizophrenia

Abnormal emotion processing is a core feature of schizophrenia spectrum disorders (SSDs) that encompasses multiple operations. While deficits in some areas have been well-characterized, we understand less about abnormalities in the emotion processing that happens through language, which is highly relevant for social life. Here, we introduce a novel method using deep learning to estimate emotion processing rapidly from spoken language, testing this approach in male-identified patients with SSDs (n = 37) and healthy controls (n = 51). Using free responses to evocative stimuli, we derived a measure of appropriateness, or "emotional alignment" (EA). We examined psychometric characteristics of EA and its sensitivity to a single-dose challenge of oxytocin, a neuropeptide shown to enhance the salience of socioemotional information in SSDs. Patients showed impaired EA relative to controls, and impairment correlated with poorer social cognitive skill and more severe motivation and pleasure deficits. Adding EA to a logistic regression model with language-based measures of formal thought disorder (FTD) improved classification of patients versus controls. Lastly, oxytocin administration improved EA but not FTD among patients. While additional validation work is needed, these initial results suggest that an automated assay using spoken language may be a promising approach to assess emotion processing in SSDs.

Narrative-Derived Indices of Metacognition among People with Schizophrenia: Associations with Self-Reported and Performance-Based Social Functioning

Metacognitive functioning-which broadly encompasses the mental processes involved in thinking about the thinking of one's self and the thinking of others-is often impaired among individuals living with schizophrenia and may contribute to difficulties in social and interpersonal functioning. Although the majority of studies assessing metacognition among individuals with schizophrenia use standardized, laboratory-based measurements, an increasing number of studies have measured metacognitive capacity using natural language produced by individuals living with mental illness. At the same time, less is known about how language-derived indices of metacognitive function relate to key social outcomes among people with schizophrenia. The primary objective of this study was to employ a validated language coding system (the Metacognition Assessment Scale, Abbreviated; MAS-A) to assess metacognitive functioning from the spoken life narratives of individuals with schizophrenia (n = 32) and community controls (n = 15). Among individuals with schizophrenia, we also examined the associations between language-derived metacognition and measures of self-reported and performance-based social functioning. Our results suggest that most aspects of metacognition in our sample were not significantly diminished in people with schizophrenia compared to community controls. Unexpectedly, the MAS-A subscale related to one's ability to master psychological difficulties was rated higher among individuals with schizophrenia. Further, our results suggest that among people with schizophrenia, higher metacognitive functioning in the domain of self-reflectivity was associated with poorer self-reported social functioning, while a greater metacognitive awareness of other individuals' minds was associated with better scores on aspects of performance-based social functioning. Collectively, these results underscore the utility of assessing metacognitive functioning via life-story narratives to understand social outcomes and highlight possible aspects of resiliency among individuals who have experienced a serious mental illness.

Clinical and computational speech measures are associated with social cognition in schizophrenia spectrum disorders

In this study, we compared three domains of social cognition (emotion processing, mentalizing, and attribution bias) to clinical and computational language measures in 63 participants with schizophrenia spectrum disorders. Based on the active inference model for discourse, we hypothesized that emotion processing and mentalizing, but not attribution bias, would be related to language disturbances. Clinical ratings for speech disturbance assessed disorganized and underproductive dimensions. Computational features included speech graph metrics, use of modal verbs, use of first-person pronouns, cosine similarity of adjacent utterances, and measures of sentiment; these were represented by four principal components. We found that higher clinical ratings for disorganized speech were predicted by greater impairments in both emotion processing and mentalizing, and that these relationships remained significant when accounting for demographic variables, overall psychosis symptoms, and verbal ability. Similarly, a computational speech component reflecting insular speech was consistently predicted by impairment in emotion processing. There were notable trends for computational speech components reflecting underproductive speech and decreased content-rich speech predicting mentalizing ability. Exploratory longitudinal analyses in a small subset of participants (n = 17) found that improvements in both emotion processing and mentalizing predicted improvements in disorganized speech. Attribution bias did not demonstrate strong relationships with language measures. Altogether, our findings are consistent with the active inference model of discourse and suggest greater emphasis on treatments that target social cognitive and language systems.

An evolutionary account of impairment of self in cognitive disorders

Recent research has proposed that certain aspects of psychosis, as experienced in, e.g., schizophrenia (SCZ), but also aspects of other cognitive conditions, such as autism spectrum disorders (ASD) and synesthesia, can be related to a shattered sense of the notion of self. In this paper, our goal is to show that altered processing of self can be attributed to an abnormal functioning of cortico-striatal brain networks supporting, among other, one key human distinctive cognitive ability, namely cross-modality, which plays multiple roles in human cognition and language. Specifically, our hypothesis is that this cognitive mechanism sheds light both on some basic aspects of the minimal self and on some aspects related to higher forms of self, such as the narrative self. We further link the atypical functioning in these conditions to some recent evolutionary changes in our species, specifically, an atypical presentation of human self-domestication (HSD) features. In doing so, we also lean on previous work concerning the link between cognitive disorders and language evolution under the effects of HSD. We further show that this approach can unify both linguistic and non-linguistic symptoms of these conditions through deficits in the notion of self. Our considerations provide further support for the hypothesis that SCZ and ASD are diametrically opposed cognitive conditions, as well for the hypothesis that their etiology is associated with recent human evolution, leading to a deeper understanding of the causes and symptoms of these disorders, and providing new cues, which can be used for an earlier and more accurate diagnostics.

Automated measures of speech content and speech organization in schizophrenia: Test-retest reliability and generalizability across demographic variables

Technological advances in artificial intelligence and natural language processing have increased efficiency of assessing speech content and speech organization in schizophrenia. Despite these developments, there has been little focus on the psychometrics of these approaches. Using two common assessments, the current study addressed this gap by: 1) measuring test-retest reliability; and 2) assessing whether speech content and/or speech organization generalize across demographics. To test these aims, we examined psychometric properties of the Linguistic Inquiry Word Count (LIWC), a speech content measure, and the Coh-Metrix, a speech organization measure. Across baseline to six month (n = 101) and baseline to one year (n = 47) narrative speech samples, we generally observed fair reliability for speech content measures and fair to good reliability for speech organization measures. Regarding demographics, multiple speech indices varied by race, income, and education. The lack of excellent reliability scores for speech indices holds important implications for examining speech variables in clinical trials and highlights the dynamic nature of speech. This work illustrates the importance of designing speech content and speech organization measures with external validity across demographic factors. Future studies examining speech in schizophrenia should account for potential biases against demographic groups introduced by linguistic analysis tools.

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.

Deconstructing heterogeneity in schizophrenia through language: a semi-automated linguistic analysis and data-driven clustering approach

Previous works highlighted the relevance of automated language analysis for predicting diagnosis in schizophrenia, but a deeper language-based data-driven investigation of the clinical heterogeneity through the illness course has been generally neglected. Here we used a semiautomated multidimensional linguistic analysis innovatively combined with a machine-driven clustering technique to characterize the speech of 67 individuals with schizophrenia. Clusters were then compared for psychopathological, cognitive, and functional characteristics. We identified two subgroups with distinctive linguistic profiles: one with higher fluency, lower lexical variety but greater use of psychological lexicon; the other with reduced fluency, greater lexical variety but reduced psychological lexicon. The former cluster was associated with lower symptoms and better quality of life, pointing to the existence of specific language profiles, which also show clinically meaningful differences. These findings highlight the importance of considering language disturbances in schizophrenia as multifaceted and approaching them in automated and data-driven ways.

More than a biomarker: could language be a biosocial marker of psychosis?

Automated extraction of quantitative linguistic features has the potential to predict objectively the onset and progression of psychosis. These linguistic variables are often considered to be biomarkers, with a large emphasis placed on the pathological aberrations in the biological processes that underwrite the faculty of language in psychosis. This perspective offers a reminder that human language is primarily a social device that is biologically implemented. As such, linguistic aberrations in patients with psychosis reflect both social and biological processes affecting an individual. Failure to consider the sociolinguistic aspects of NLP measures will limit their usefulness as digital tools in clinical settings. In the context of psychosis, considering language as a biosocial marker could lead to less biased and more accessible tools for patient-specific predictions in the clinic.

Natural language processing methods are sensitive to sub-clinical linguistic differences in schizophrenia spectrum disorders

Computerized natural language processing (NLP) allows for objective and sensitive detection of speech disturbance, a hallmark of schizophrenia spectrum disorders (SSD). We explored several methods for characterizing speech changes in SSD (n = 20) compared to healthy control (HC) participants (n = 11) and approached linguistic phenotyping on three levels: individual words, parts-of-speech (POS), and sentence-level coherence. NLP features were compared with a clinical gold standard, the Scale for the Assessment of Thought, Language and Communication (TLC). We utilized Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art embedding algorithm incorporating bidirectional context. Through the POS approach, we found that SSD used more pronouns but fewer adverbs, adjectives, and determiners (e.g., “the,” “a,”). Analysis of individual word usage was notable for more frequent use of first-person singular pronouns among individuals with SSD and first-person plural pronouns among HC. There was a striking increase in incomplete words among SSD. Sentence-level analysis using BERT reflected increased tangentiality among SSD with greater sentence embedding distances. The SSD sample had low speech disturbance on average and there was no difference in group means for TLC scores. However, NLP measures of language disturbance appear to be sensitive to these subclinical differences and showed greater ability to discriminate between HC and SSD than a model based on clinical ratings alone. These intriguing exploratory results from a small sample prompt further inquiry into NLP methods for characterizing language disturbance in SSD and suggest that NLP measures may yield clinically relevant and informative biomarkers.

Identifying signals associated with psychiatric illness utilizing language and images posted to Facebook

Prior research has identified associations between social media activity and psychiatric diagnoses; however, diagnoses are rarely clinically confirmed. Toward the goal of applying novel approaches to improve outcomes, research using real patient data is necessary. We collected 3,404,959 Facebook messages and 142,390 images across 223 participants (mean age = 23.7; 41.7% male) with schizophrenia spectrum disorders (SSD), mood disorders (MD), and healthy volunteers (HV). We analyzed features uploaded up to 18 months before the first hospitalization using machine learning and built classifiers that distinguished SSD and MD from HV, and SSD from MD. Classification achieved AUC of 0.77 (HV vs. MD), 0.76 (HV vs. SSD), and 0.72 (SSD vs. MD). SSD used more (P < 0.01) perception words (hear, see, feel) than MD or HV. SSD and MD used more (P < 0.01) swear words compared to HV. SSD were more likely to express negative emotions compared to HV (P < 0.01). MD used more words related to biological processes (blood/pain) compared to HV (P < 0.01). The height and width of photos posted by SSD and MD were smaller (P < 0.01) than HV. MD photos contained more blues and less yellows (P < 0.01). Closer to hospitalization, use of punctuation increased (SSD vs HV), use of negative emotion words increased (MD vs. HV), and use of swear words increased (P < 0.01) for SSD and MD compared to HV. Machine-learning algorithms are capable of differentiating SSD and MD using Facebook activity alone over a year in advance of hospitalization. Integrating Facebook data with clinical information could one day serve to inform clinical decision-making.

Lowering costs for large-scale screening in psychosis: a systematic review and meta-analysis of performance and value of information for speech-based psychiatric evaluation

OBJECTIVE

Obstacles for computational tools in psychiatry include gathering robust evidence and keeping implementation costs reasonable. We report a systematic review of automated speech evaluation for the psychosis spectrum and analyze the value of information for a screening program in a healthcare system with a limited number of psychiatrists (Maputo, Mozambique).

METHODS

Original studies on speech analysis for forecasting of conversion in individuals at clinical high risk (CHR) for psychosis, diagnosis of manifested psychotic disorder, and first-episode psychosis (FEP) were included in this review. Studies addressing non-verbal components of speech (e.g., pitch, tone) were excluded.

RESULTS

Of 168 works identified, 28 original studies were included. Valuable speech features included direct measures (e.g., relative word counting) and mathematical embeddings (e.g.: word-to-vector, graphs). Accuracy estimates reported for schizophrenia diagnosis and CHR conversion ranged from 71 to 100% across studies. Studies used structured interviews, directed tasks, or prompted free speech. Directed-task protocols were faster while seemingly maintaining performance. The expected value of perfect information is USD 9.34 million. Imperfect tests would nevertheless yield high value.

CONCLUSION

Accuracy for screening and diagnosis was high. Larger studies are needed to enhance precision of classificatory estimates. Automated analysis presents itself as a feasible, low-cost method which should be especially useful for regions in which the physician pool is insufficient to meet demand.

Identifying emerging mental illness utilizing search engine activity: A feasibility study

Mental illness often emerges during the formative years of adolescence and young adult development and interferes with the establishment of healthy educational, vocational, and social foundations. Despite the severity of symptoms and decline in functioning, the time between illness onset and receiving appropriate care can be lengthy. A method by which to objectively identify early signs of emerging psychiatric symptoms could improve early intervention strategies. We analyzed a total of 405,523 search queries from 105 individuals with schizophrenia spectrum disorders (SSD, N = 36), non-psychotic mood disorders (MD, N = 38) and healthy volunteers (HV, N = 31) utilizing one year's worth of data prior to the first psychiatric hospitalization. Across 52 weeks, we found significant differences in the timing (p<0.05) and frequency (p<0.001) of searches between individuals with SSD and MD compared to HV up to a year in advance of the first psychiatric hospitalization. We additionally identified significant linguistic differences in search content among the three groups including use of words related to sadness and perception, use of first and second person pronouns, and use of punctuation (all p<0.05). In the weeks before hospitalization, both participants with SSD and MD displayed significant shifts in search timing (p<0.05), and participants with SSD displayed significant shifts in search content (p<0.05). Our findings demonstrate promise for utilizing personal patterns of online search activity to inform clinical care.

Piecing together fragments: Linguistic cohesion mediates the relationship between executive function and metacognition in schizophrenia

Speech disturbances are prevalent in psychosis. These may arise in part from executive function impairment, as research suggests that inhibition and monitoring are associated with production of cohesive discourse. However, it is not yet understood how linguistic and executive function impairments in psychosis interact with disrupted metacognition, or deficits in the ability to integrate information to form a complex sense of oneself and others and use that synthesis to respond to psychosocial challenges. Whereas discourse studies have historically employed manual hand-coding techniques, automated computational tools can characterize deep semantic structures that may be closely linked with metacognition. In the present study, we examined whether higher executive functioning promotes metacognition by way of altering linguistic cohesion. Ninety-four individuals with schizophrenia-spectrum disorders provided illness narratives and completed an executive function task battery (Delis-Kaplan Executive Function System). We assessed the narratives for linguistic cohesion (Coh-Metrix 3.0) and metacognitive capacity (Metacognition Assessment Scale - Abbreviated). Selected linguistic indices measured the frequency of connections between causal and intentional content (deep cohesion), word and theme overlap (referential cohesion), and unique word usage (lexical diversity). In path analyses using bootstrapped confidence intervals, we found that deep cohesion and lexical diversity independently mediated the relationship between executive functioning and metacognitive capacity. Findings suggest that executive control abilities support integration of mental experiences by way of increasing causal, goal-driven speech and word expression in individuals with schizophrenia. Metacognitive-based therapeutic interventions for psychosis may promote insight and recovery in part by scaffolding use of language that links ideas together.

Detecting relapse in youth with psychotic disorders utilizing patient-generated and patient-contributed digital data from Facebook

Although most patients who experience a first-episode of psychosis achieve remission of positive psychotic symptoms, relapse is common. Existing relapse evaluation strategies are limited by their reliance on direct and timely contact with professionals, and accurate reporting of symptoms. A method by which to objectively identify early relapse warning signs could facilitate swift intervention. We collected 52,815 Facebook posts across 51 participants with recent onset psychosis (mean age = 23.96 years; 70.58% male) and applied anomaly detection to explore linguistic and behavioral changes associated with psychotic relapse. We built a one-class classification model that makes patient-specific personalized predictions on risk to relapse. Significant differences were identified in the words posted to Facebook in the month preceding a relapse hospitalization compared to periods of relative health, including increased usage of words belonging to the swear (p < 0.0001, Wilcoxon signed rank test), anger (p < 0.001), and death (p < 0.0001) categories, decreased usage of words belonging to work (p = 0.00579), friends (p < 0.0001), and health (p < 0.0001) categories, as well as a significantly increased use of first (p < 0.0001) and second-person (p  < 0.001) pronouns. We additionally observed a significant increase in co-tagging (p < 0.001) and friending (p < 0.0001) behaviors in the month before a relapse hospitalization. Our classifier achieved a specificity of 0.71 in predicting relapse. Results indicate that social media activity captures objective linguistic and behavioral markers of psychotic relapse in young individuals with recent onset psychosis. Machine-learning models were capable of making personalized predictions of imminent relapse hospitalizations at the patient-specific level.

Measuring disorganized speech in schizophrenia: automated analysis explains variance in cognitive deficits beyond clinician-rated scales

BACKGROUND

Conveying information cohesively is an essential element of communication that is disrupted in schizophrenia. These disruptions are typically expressed through disorganized symptoms, which have been linked to neurocognitive, social cognitive, and metacognitive deficits. Automated analysis can objectively assess disorganization within sentences, between sentences, and across paragraphs by comparing explicit communication to a large text corpus.

METHOD

Little work in schizophrenia has tested: (1) links between disorganized symptoms measured via automated analysis and neurocognition, social cognition, or metacognition; and (2) if automated analysis explains incremental variance in cognitive processes beyond clinician-rated scales. Disorganization was measured in schizophrenia (n = 81) with Coh-Metrix 3.0, an automated program that calculates basic and complex language indices. Trained staff also assessed neurocognition, social cognition, metacognition, and clinician-rated disorganization.

RESULTS

Findings showed that all three cognitive processes were significantly associated with at least one automated index of disorganization. When automated analysis was compared with a clinician-rated scale, it accounted for significant variance in neurocognition and metacognition beyond the clinician-rated measure. When combined, these two methods explained 28-31% of the variance in neurocognition, social cognition, and metacognition.

CONCLUSIONS

This study illustrated how automated analysis can highlight the specific role of disorganization in neurocognition, social cognition, and metacognition. Generally, those with poor cognition also displayed more disorganization in their speech-making it difficult for listeners to process essential information needed to tie the speaker's ideas together. Our findings showcase how implementing a mixed-methods approach in schizophrenia can explain substantial variance in cognitive processes.

Evidence of disturbances of deep levels of semantic cohesion within personal narratives in schizophrenia

Since initial conceptualizations, schizophrenia has been thought to involve core disturbances in the ability to form complex, integrated ideas. Although this has been studied in terms of formal thought disorder, the level of involvement of altered latent semantic structure is less clear. To explore this question, we compared the personal narratives of adults with schizophrenia (n=200) to those produced by an HIV+ sample (n=55) using selected indices from Coh-Metrix. Coh-Metrix is a software system designed to compute various language usage statistics from transcribed written and spoken language documents. It differs from many other frequency-based systems in that Coh-Metrix measures a wide range of language processes, ranging from basic descriptors (e.g., total words) to indices assessing more sophisticated processes within sentences, between sentences, and across paragraphs (e.g., deep cohesion). Consistent with predictions, the narratives in schizophrenia exhibited less cohesion even after controlling for age and education. Specifically, the schizophrenia group spoke fewer words, demonstrated less connection between ideas and clauses, provided fewer causal/intentional markers, and displayed lower levels of deep cohesion. A classification model using only Coh-Metrix indices found language markers correctly classified participants in nearly three-fourths of cases. These findings suggest a particular pattern of difficulties cohesively connecting thoughts about oneself and the world results in a perceived lack of coherence in schizophrenia. These results are consistent with Bleuler's model of schizophrenia and offer a novel way to understand and measure alterations in thought and speech over time.

Automated analysis of written narratives reveals abnormalities in referential cohesion in youth at ultra high risk for psychosis

Schizophrenia and at-risk populations are suggested to exhibit referential cohesion deficits in language production (e.g., producing fewer pronouns or nouns that clearly link to concepts from previous sentences). Much of this work has focused on transcribed speech samples, while no work to our knowledge has examined referential cohesion in written narratives among ultra high risk (UHR) youth using Coh-Metrix, an automated analysis tool. In the present study, written narratives from 84 individuals (UHR=41, control=43) were examined. Referential cohesion variables and relationships with symptoms and relevant cognitive variables were also investigated. Findings reveal less word "stem" overlap in narratives produced by UHR youth compared to controls, and correlations with symptom domains and verbal learning. The present study highlights the potential usefulness of automated analysis of written narratives in identifying at-risk youth and these data provide critical information in better understanding the etiology of psychosis. As writing production is commonly elicited in educational contexts, markers of aberrant cohesion in writing represent significant potential for identifying youth who could benefit from further screening, and utilizing software that is easily accessible and free may provide utility in academic and clinical settings.

When Proactivity Fails: An Electrophysiological Study of Establishing Reference in Schizophrenia

BACKGROUND

Schizophrenia is characterized by abnormalities in referential communication, which may be linked to more general deficits in proactive cognitive control. We used event-related potentials to probe the timing and nature of the neural mechanisms engaged as people with schizophrenia linked pronouns to their preceding referents during word-by-word sentence comprehension.

METHODS

We measured event-related potentials to pronouns in two-clause sentences in 16 people with schizophrenia and 20 demographically matched control participants. Our design crossed the number of potential referents (1-referent, 2-referent) with whether the pronoun matched the gender of its preceding referent(s) (matching, mismatching). This gave rise to four conditions: 1) 1-referent matching ("Edward took courses in accounting but he . . ."); 2) 2-referent matching ("Edward and Phillip took courses but he . . . "); 3) 1-referent mismatching ("Edward took courses in accounting but she . . ."); and 4) 2-referent mismatching ("Edward and Phillip took courses but she . . .").

RESULTS

Consistent with previous findings, healthy control participants produced a larger left anteriorly distributed negativity between 400 and 600 ms to 2-referent matching than to 1-referent matching pronouns (the "Nref effect"). In contrast, people with schizophrenia produced a larger centroposterior positivity effect between 600 and 800 ms. Both patient and control groups produced a larger positivity between 400 and 800 ms to mismatching than to matching pronouns.

CONCLUSIONS

These findings suggest that proactive mechanisms of referential processing, reflected by the Nref effect, are impaired in schizophrenia, while reactive mechanisms, reflected by the positivity effects, are relatively spared. Indeed, patients may compensate for proactive deficits by retroactively engaging with context to influence the processing of inputs at a later stage of analysis.

Using lexical analysis to identify emotional distress in psychometric schizotypy

Through the use of lexical analysis software, researchers have demonstrated a greater frequency of negative affect word use in those with schizophrenia and schizotypy compared to the general population. In addition, those with schizotypy endorse greater emotional distress than healthy controls. In this study, our aim was to expand on previous findings in schizotypy to determine whether negative affect word use could be linked to emotional distress. Schizotypy (n=33) and non-schizotypy groups (n=33) completed an open-ended, semi-structured interview and negative affect word use was analyzed using a validated lexical analysis instrument. Emotional distress was assessed using subjective questionnaires of depression and psychological quality of life (QOL). When groups were compared, those with schizotypy used significantly more negative affect words; endorsed greater depression; and reported lower QOL. Within schizotypy, a trend level association between depression and negative affect word use was observed; QOL and negative affect word use showed a significant inverse association. Our findings offer preliminary evidence of the potential effectiveness of lexical analysis as an objective, behavior-based method for identifying emotional distress throughout the schizophrenia-spectrum. Utilizing lexical analysis in schizotypy offers promise for providing researchers with an assessment capable of objectively detecting emotional distress.

A Collaborative Approach to Identifying Social Media Markers of Schizophrenia by Employing Machine Learning and Clinical Appraisals

Background

Linguistic analysis of publicly available Twitter feeds have achieved success in differentiating individuals who self-disclose online as having schizophrenia from healthy controls. To date, limited efforts have included expert input to evaluate the authenticity of diagnostic self-disclosures.

Objective

This study aims to move from noisy self-reports of schizophrenia on social media to more accurate identification of diagnoses by exploring a human-machine partnered approach, wherein computational linguistic analysis of shared content is combined with clinical appraisals.

Methods

Twitter timeline data, extracted from 671 users with self-disclosed diagnoses of schizophrenia, was appraised for authenticity by expert clinicians. Data from disclosures deemed true were used to build a classifier aiming to distinguish users with schizophrenia from healthy controls. Results from the classifier were compared to expert appraisals on new, unseen Twitter users.

Results

Significant linguistic differences were identified in the schizophrenia group including greater use of interpersonal pronouns (P<.001), decreased emphasis on friendship (P<.001), and greater emphasis on biological processes (P<.001). The resulting classifier distinguished users with disclosures of schizophrenia deemed genuine from control users with a mean accuracy of 88% using linguistic data alone. Compared to clinicians on new, unseen users, the classifier’s precision, recall, and accuracy measures were 0.27, 0.77, and 0.59, respectively.

Conclusions

These data reinforce the need for ongoing collaborations integrating expertise from multiple fields to strengthen our ability to accurately identify and effectively engage individuals with mental illness online. These collaborations are crucial to overcome some of mental illnesses’ biggest challenges by using digital technology.

Self-reference in psychosis and depression: a language marker of illness

BACKGROUND

Language use is of increasing interest in the study of mental illness. Analytical approaches range from phenomenological and qualitative to formal computational quantitative methods. Practically, the approach may have utility in predicting clinical outcomes. We harnessed a real-world sample (blog entries) from groups with psychosis, strong beliefs, odd beliefs, illness, mental illness and/or social isolation to validate and extend laboratory findings about lexical differences between psychosis and control subjects.

METHOD

We describe the results of two experiments using Linguistic Inquiry and Word Count software to assess word category frequencies. In experiment 1, we compared word use in psychosis and control subjects in the laboratory (23 per group), and related results to subject symptoms. In experiment 2, we examined lexical patterns in blog entries written by people with psychosis and eight comparison groups. In addition to between-group comparisons, we used factor analysis followed by clustering to discern the contributions of strong belief, odd belief and illness identity to lexical patterns.

RESULTS

Consistent with others' work, we found that first-person pronouns, biological process words and negative emotion words were more frequent in psychosis language. We tested lexical differences between bloggers with psychosis and multiple relevant comparison groups. Clustering analysis revealed that word use frequencies did not group individuals with strong or odd beliefs, but instead grouped individuals with any illness (mental or physical).

CONCLUSIONS

Pairing of laboratory and real-world samples reveals that lexical markers previously identified as specific language changes in depression and psychosis are probably markers of illness in general.

Lexical Characteristics of Emotional Narratives in Schizophrenia: Relationships With Symptoms, Functioning, and Social Cognition

Previous research has suggested that complexity of speech, speech rate, use of emotion words, and use of pronouns are all potential indicators of important clinical components of schizophrenia, but little research has examined the relationships of these disturbances to cognitive variables impaired in schizophrenia, including social cognition. The current study examined these lexical differences to better characterize the cognitive substrates of speech disturbances in schizophrenia. Brief narratives of individuals with schizophrenia (n = 42) and non-clinical controls (n = 48) were compared according to their lexical characteristics, and these were examined for relationships to social cognition and real-world functioning. Significant differences between the groups were found in words per sentence (related to functioning, but not negative symptoms) as well as pronoun use (related to attributional style and theory of mind). Additionally, lexical characteristics effectively distinguished individuals with schizophrenia from non-clinical controls. Language disturbances in schizophrenia seem related to social cognition impairments and real-world functioning, and are a robust indicator of clinical status.