Comparing emotion feature extraction approaches for predicting depression and anxiety

Burkhardt, Hannah A; Pullmann, Michael D.; Hull, Thomas; Aren, Patricia; Cohen, Trevor

doi:10.18653/v1/2022.clpsych-1.9

Cited by 15 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although requiring massive text corpora to initially train on masked language, language models build linguistic representations that can then be fine-tuned to downstream clinical tasks [ 69 ]. Applications examined include fine-tuning BERT for domain adaptation to mental health language (MentalBERT) [ 70 ], for sentiment analysis via transfer learning (e.g., using the GoEmotions corpus) [ 71 ], and detection of topics [ 72 ]. Generative language models were used for revising interventions [ 73 ], session summarizations [ 74 ], or data augmentation for model training [ 70 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

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

Malgaroli,

Hull,

Zech

et al. 2023

Transl Psychiatry

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Sentiment analysis performed similarly to human raters (Cohen’s K = 0.58) [ 101 ]. Across studies, the latest Transformer-based models were shown to capture emotional valiance [ 102 ] and associations with symptom ratings more accurately than other language features [ 71 ]. Suicide Risk .…”

Section: Resultsmentioning

confidence: 99%

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

Malgaroli,

Hull,

Zech

et al. 2023

Transl Psychiatry

View full text Add to dashboard Cite

show abstract

“…The relationship between positive emotions and sentiment with depression, however, has been studied less than negative emotions and sentiment. Nevertheless, recent research has found that depressed individuals use fewer positive emotions in their writing (Burkhardt et al, 2022;Stamatis et al, 2022).…”

Section: Natural Language Processingmentioning

confidence: 99%

Semantic signals in self-reference: The detection and prediction of depressive symptoms from the daily diary entries of a sample with major depressive disorder

Collins¹,

Lekkas²,

Nemesure³

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Depressed individuals experience fewer positive and more negative emotions and use fewer positive words to describe themselves. Natural language processing (NLP) techniques have been used to predict depression, with pronoun usage and positive and negative emotions being identified as important features. However, it is unclear whether use of positive and negative words when referring to oneself can classify depression and predict depression severity using NLP.Methods: Fifty-one individuals diagnosed with major depressive disorder through structured clinical interviews completed ecological momentary assessments, which included a mobile-friendly Patient Health Questionnaire-9 (PHQ-9) and text-based daily diary entries. Using NLP techniques, word affect, and emotion intensity lexicon, we generated 20 model features to detect and predict average weekly depression from 316 diary entries. We utilized four independent, tree-based, and cross-validated machine learning models and used SHapely Additive exPlanations to evaluate relative importance of each model feature. Two regression models detected and predicted total PHQ-9 score, and two classification models detected and predicted moderate to severe depression (PHQ-9≥10).Results: The models explained 22% and 15% of the variance in same-week and next-week PHQ-9 scores, respectively. Additionally, the models significantly classified current and future depression (AUC=0.72 and AUC=0.68, respectively). These results suggest that (i) lower joy intensity, (ii) higher sadness intensity, (iii) lower valence of passages with “I”/“me” as the subject, and (iv) increased usage of “I”/“me”/“my” all influence model predictions towards more severe depression.Conclusions: These findings support prior research indicating that depressed individuals use fewer positive intensity words, more negative intensity words, and more first-person pronouns in their writing. Moreover, this work highlights that depressed individuals use less positive and more negative words when referring to themselves. Positive affect treatments and digital interventions, including written components, may be beneficial for targeting these linguistic features of depression.

show abstract

“…Emotions are important in most clinical psychology theoretical orientations 46,48,49,52 . Nevertheless, there is strong disagreement on how to measure emotionality 55,102,103 . We chose to use the NRC Emotion Lexicon (EmoLex) to measure whether a word conveyed positive or negative sentiment because of its expansive coverage (14,182 unigrams/words) and inspectable approach, rooted in a crowdsourced layman's understanding of each word.…”

Section: Datasetmentioning

confidence: 99%

A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency

Miner

Fleming

Haque

et al. 2022

npj Mental Health Res

View full text Add to dashboard Cite

Although individual psychotherapy is generally effective for a range of mental health conditions, little is known about the moment-to-moment language use of effective therapists. Increased access to computational power, coupled with a rise in computer-mediated communication (telehealth), makes feasible the large-scale analyses of language use during psychotherapy. Transparent methodological approaches are lacking, however. Here we present novel methods to increase the efficiency of efforts to examine language use in psychotherapy. We evaluate three important aspects of therapist language use - timing, responsiveness, and consistency - across five clinically relevant language domains: pronouns, time orientation, emotional polarity, therapist tactics, and paralinguistic style. We find therapist language is dynamic within sessions, responds to patient language, and relates to patient symptom diagnosis but not symptom severity. Our results demonstrate that analyzing therapist language at scale is feasible and may help answer longstanding questions about specific behaviors of effective therapists.

show abstract

Comparing emotion feature extraction approaches for predicting depression and anxiety

Cited by 15 publications

References 25 publications

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

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

Semantic signals in self-reference: The detection and prediction of depressive symptoms from the daily diary entries of a sample with major depressive disorder

A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency

Contact Info

Product

Resources

About