scholarly journals Natural Language Analyzed with AI-based Transformers Predict Traditional Well-Being Measures Approaching the Theoretical Upper Limits in Accuracy

2021 ◽  
Author(s):  
Oscar Nils Erik Kjell ◽  
Sverker Sikström ◽  
Katarina Kjell ◽  
H. Andrew Schwartz
Keyword(s):  
Natural Language ◽  
Web Search ◽  
Rating Scales ◽  
Rating Scale ◽  
Well Being ◽  
Human Condition ◽  
Psychological Assessments ◽  
Scale Reliability ◽  
Language Analysis ◽  
Upper Limits

We show that using a recent break-through in artificial intelligence –transformers–, psychological assessments from text-responses can approach theoretical upper limits in accuracy, converging with standard psychological rating scales. Text-responses use people's primary form of communication –natural language– and have been suggested as a more ecologically-valid response format than closed-ended rating scales that dominate social science. However, previous language analysis techniques left a gap between how accurately they converged with standard rating scales and how well ratings scales converge with themselves – a theoretical upper-limit in accuracy. Most recently, AI-based language analysis has gone through a transformation as nearly all of its applications, from Web search to personalized assistants (e.g., Alexa and Siri), have shown unprecedented improvement by using transformers. We evaluate transformers for estimating psychological well-being from questionnaire text- and descriptive word-responses, and find accuracies converging with rating scales that approach the theoretical upper limits (Pearson r = .85, p < .001, N = 608; in line with most metrics of rating scale reliability). These findings suggest an avenue for modernising the ubiquitous questionnaire and ultimately opening doors to a greater understanding of the human condition.

Comparisons of Narrative Psychotherapy to Conventional CBT for the Psychotherapy of Psychosis and Bipolar Disorder

2017 ◽  
Vol 41 (S1) ◽  
pp. s779-s779
Author(s):  
L. Mehl-Madrona ◽  
B. Mainguy
Keyword(s):  
Bipolar Disorder ◽  
Narrative Therapy ◽  
Rating Scales ◽  
Psychotic Disorders ◽  
Rating Scale ◽  
Therapy Group ◽  
Well Being ◽  
Outcome Data ◽  
Symptom Scale ◽  
Young Mania

IntroductionThere is ongoing debate about about both the value of psychotherapy in psychotic disorders and the best type of psychotherapy to use if necessary.MethodsWe conducted narrative psychotherapy with 18 adults, all diagnosed as having bipolar disorder with psychotic features and/or schizo-affective disorder. Outcome data consisted of the Positive and Negative Symptom Scale, the Clinical Global Impressions Scale, the Young Mania Rating Scale, the Hamilton Anxiety and Depression Scales, the My Medical Outcome Profile, Version 2(MYMOP2), and the Outcome Rating Scales of Duncan and Miller. We compare the outcomes of our patients to those of a matched comparison group receiving conventional psycho-education and cognitive behavioural therapy. Patients were seen for a minimum of 16 weeks over an average of 22 weeks. Average age was 31.5 years with a standard deviation of 8.1 years.ResultsThe narrative therapy group showed statistically significant reductions in all outcome measures compared to the conventional treatment group. They continued treatment significantly longer and had fewer re-hospitalizations. They were less distressed by voices.ConclusionsA narrative psychotherapy approach using dialogical theory and therapy ideas is a reasonable approach for the psychotherapy of psychosis. Review of psychotherapy notes showed that narrative approaches allowed the therapist to align with the patient as collaborator in considering the story presented and was therefore less productive of defensiveness and self-criticism than conventional approaches. The therapy included techniques for negotiating changes in illness narratives, identity narratives, and treatment narratives that were more conducive of well-being and recovery.Disclosure of interestThe authors have not supplied their declaration of competing interest.

scholarly journals Check the effects: systematic assessment of antipsychotic side-effects in an inpatient cohort

2020 ◽  
Vol 10 ◽  
pp. 204512532095711
Author(s):  
Caroline Hynes ◽  
Stephen McWilliams ◽  
Mark Clarke ◽  
Ita Fitzgerald ◽  
Larkin Feeney ◽  
...  
Keyword(s):  
Side Effects ◽  
Rating Scales ◽  
Rating Scale ◽  
Standard Dose ◽  
Well Being ◽  
High Dose ◽  
Negative Consequences ◽  
Adherence Assessment ◽  
Dose Combination ◽  
Antipsychotic Side Effects

Background: Antipsychotics are associated with a range of side-effects that can influence patients’ subjective well-being negatively resulting in poor adherence. In order to limit the negative consequences of side-effects, they should be regularly systematically assessed. The aim of this study was to systematically assess antipsychotic side-effects in an inpatient cohort using validated rating scales. Methods: Eligible individuals prescribed an antipsychotic for at least 2 weeks were invited to have their side-effects assessed systematically. Results: A total of 208 individuals were assessed systematically for antipsychotic side-effects; 71.5% ( n = 138) stated that they had not reported side-effects to their clinician prior to the assessment. The most commonly reported side-effects were daytime drowsiness (75%), dry mouth (58.2%) and weight gain (50.0%), while the most distressing side-effects reported were erectile dysfunction (35.0%), sexual dysfunction (26.3%) and amenorrhoea (26.3%). There was no evidence of an association between side-effect severity/number of side-effects reported/distress caused by those taking high dose/combination antipsychotics versus standard dose monotherapy. Conclusion: Side-effects must be regularly and systematically assessed using a validated rating scale. As distress caused by side-effects plays a major role in non-adherence, assessment should examine distress and data on distressing side-effects should be available to those choosing an antipsychotic. Given the lack of correlation between high dose/combination antipsychotics and side-effects, treatment should be tailored to the individual based on response/tolerance and dose reduction/avoidance of polypharmacy should not be recommended to minimise side-effects.

Reconsidering the Psychometrics of the GRS-S: Evidence for Parsimony in Measurement

2019 ◽  
Vol 46 (1) ◽  
pp. 55-66
Author(s):  
Yaacov Petscher ◽  
Steven I. Pfeiffer
Keyword(s):  
Rating Scales ◽  
Rating Scale ◽  
Area Under The Curve ◽  
Cut Scores ◽  
Scale Level ◽  
Intelligence Scale ◽  
Scale Reliability ◽  
Point Rating Scale ◽  
Item Level ◽  
Scale Down

The authors evaluated measurement-level, factor-level, item-level, and scale-level revisions to the Gifted Rating Scales–School Form (GRS-S). Measurement-level considerations tested the extent to which treating the Likert-type scale rating as categorical or continuous produced different fit across unidimensional, correlated trait, and bifactor latent factor structures. Item- and scale-level analyses demonstrated that the GRS-S could be reduced from a 72-item assessment on a 9-point rating scale down to a 30-item assessment on a 3-point rating scale. Reliability from the reduced assessment was high (ω > .95). Receiver operating characteristic (ROC) curve comparisons between the original and reduced versions of the GRS-S showed that diagnostic accuracy (i.e., area under the curve) of the scales was comparable when considering cut scores of 120, 125, and 130 on the WISC-IV Full Scale ( Wechsler Intelligence Scale for Child–Fourth Edition) and verbal IQ and the WIAT-III (Wechsler Individual Achievement Test–Third Edition) composite score. The findings suggest that a brief form of the GRS-S can be used as a universal or selective screener for giftedness without sacrificing key psychometric considerations.

scholarly journals French Validation PCOMS Outcome and Session rating scales ORS SRS Cazauvieilh et al .pdf

2019 ◽  
Author(s):  
Christophe Cazauvieilh ◽  
Kamel Gana ◽  
Scott D Miller ◽  
Bruno Quintard
Keyword(s):  
Therapeutic Relationship ◽  
Rating Scales ◽  
Rating Scale ◽  
Well Being ◽  
Routine Outcome Monitoring ◽  
Factorial Structure ◽  
Outcome Monitoring ◽  
Session Rating Scale ◽  
French Validation ◽  
Outcome Rating Scale

<b>French Validation of two brief Routine Outcome Monitoring (ROM)</b> scales <b>from the PCOMS system</b> : the <b>ORS</b> (Outcome Rating Scale, Miller et al., 2005) <b>designed to assess </b>various dimensions of <b>well-being and progression during care</b>, and the <b>SRS</b> (Session Rating Scale 3.0; Miller et al., 2002) <b>designed to assess dimensions of the therapeutic relationship</b>. <b>The research implied clinical and non clinical populations</b> <b>and brings estimates</b> <b>regarding</b> factorial structure, validity, reliability, preliminary index and norms of <b>the two scales in French.</b>

The Well-Being Index WHO-5: hedonistic foundation and practical limitations

2019 ◽  
Vol 46 (3) ◽  
pp. 333-339 ◽  
Author(s):  
Amalie Oxholm Kusier ◽  
Anna Paldam Folker
Keyword(s):  
Mental Health ◽  
Life Satisfaction ◽  
Rating Scales ◽  
Rating Scale ◽  
Well Being ◽  
Risk Groups ◽  
Mental Health Research ◽  
Philosophical Foundation ◽  
Philosophical Theory ◽  
Satisfaction Theory

Research and policymaking on positive mental health and well-being have increased within the last decade, partly fueled by decreasing levels of well-being in the general population and among at-risk groups. However, measurement of well-being often takes place in the absence of reflection on the underlying theoretical conceptualisation of well-being. This disguises the fact that different rating scales of well-being often measure very different phenomena because rating scales are based on different philosophical assumptions, which represent radically different foundational views about the nature of well-being. The aim of this paper is to examine the philosophical foundation of the Well-Being Index WHO-5 in order to clarify the underlying normative commitments and the psychometric compromises involved in the translation of philosophical theory into practice. WHO-5 has been introduced as a rating scale that measures the affective and hedonistic dimensions of well-being. It is widely used within public health and mental health research. This paper introduces the philosophical theory of Hedonism and explores how two central assumptions that relate to hedonistic theory are reflected in the construction of WHO-5. The first concerns ‘the hedonic balance’, that is the relation between positive and negative emotions. The second assumption concerns ‘the value of emotions’, that is, how to determine the duration and intensity of emotions. At the end, Hedonism is contrasted with Life Satisfaction Theory, an alternative foundational theory of well-being, in order to clarify that the outlook of WHO-5 is more a rating system of positive affect than a cognitive judgement of overall life satisfaction. We conclude that it is important to examine the philosophical foundation of rating scales of well-being, such as WHO-5, in order to be fully able to assess the magnitude as well as the limits of their results.

scholarly journals Semantic Measures: Using Natural Language Processing to Measure, Differentiate and Describe Psychological Constructs

2018 ◽  
Author(s):  
Oscar Nils Erik Kjell ◽  
Katarina Kjell ◽  
Danilo Garcia ◽  
Sverker Sikström
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Rating Scales ◽  
Mental Health Problems ◽  
Well Being ◽  
Subjective Well Being ◽  
Validity And Reliability ◽  
Psychological Constructs ◽  
Numerical Rating

Psychological constructs, such as emotions, thoughts and attitudes are often measured by asking individuals to reply to questions using closed-ended numerical rating scales. However, when asking people about their state of mind in a natural context (“How are you?”), we receive open-ended answers using words (“fine and happy!”) and not closed-ended answers using numbers (“7”) or categories (“A lot”). Nevertheless, to date it has been difficult to objectively quantify responses to open-ended questions. We develop an approach using open-ended questions in which the responses are analyzed using natural language processing (Latent Semantic Analyses). This approach of using open-ended, semantic questions is compared with traditional rating scales in nine studies (N=92-854), including two different study paradigms. The first paradigm requires participants to describe psychological aspects of external stimuli (facial expressions) and the second paradigm involves asking participants to report their subjective well-being and mental health problems. The results demonstrate that the approach using semantic questions yields good statistical properties with competitive, or higher, validity and reliability compared with corresponding numerical rating scales. As these semantic measures are based on natural language and measure, differentiate and describe psychological constructs, they have the potential of complementing and extending traditional rating scales.

scholarly journals Measurement of Quality of Life III. From the IQOL Theory to the Global, Generic SEQOL Questionnaire

2003 ◽  
Vol 3 ◽  
pp. 972-991 ◽  
Author(s):  
Soren Ventegodt ◽  
Joav Merrick ◽  
Niels Jorgen Andersen
Keyword(s):  
Quality Of Life ◽  
Meaning In Life ◽  
Rating Scales ◽  
Satisfaction With Life ◽  
Rating Scale ◽  
Well Being ◽  
Human Existence ◽  
Clinical Databases ◽  
Global Quality Of Life

The Danish Quality of Life Survey is based on the philosophy of life known as the integrative quality-of-life (IQOL) theory. It consists of eight different quality-of-life concepts, ranging from the superficially subjective via the deeply existential to the superficially objective (well being, satisfaction with life, happiness, meaning in life, biological order, realizing life potential, fulfillment of needs, and objective factors [ability of functioning and fulfilling societal norms]).This paper presents the work underlying the formulation of the theories of a good life and how these theories came to be expressed in a comprehensive, multidimensional, generic questionnaire for the evaluation of the global quality of life � SEQOL (self-evaluation of quality of life) � presented in full length in this paper. The instruments and theories on which the Quality of Life Survey was based are constantly being updated. It is an on-going process due to aspects such as human development, language, and culture. We arrived at eight rating scales for the quality of life that, guided by the IQOL theory, were combined into a global and generic quality-of-life rating scale. This was simplified to the validated QOL5 with only five questions, made for use in clinical databases. Unfortunately, the depth of human existence is to some extent lost in QOL5.We continue to aim towards greater simplicity, precision, and depth in the questions in order to explore the depths of human existence. We have not yet found a final form that enables us to fully rate the quality of life in practice. We hope that the several hundred questions we found necessary to adequately implement the theories of the Quality of Life Survey can be replaced by far fewer; ideally, only eight questions representing the eight component theories. These eight ideal questions have not yet been evaluated, and therefore they should not form the basis of a survey. However, the perspective is clear. If eight simple questions can accurately rate the quality of life as well as its depth, we have found an instrument of immense practical scope.

Reconsidering the Psychometrics of the Gifted Rating Scales – School Form: Evidence for Parsimony in Measurement

2018 ◽  
Author(s):  
Yaacov Petscher ◽  
Steven I. Pfeiffer
Keyword(s):  
Rating Scales ◽  
Rating Scale ◽  
Area Under The Curve ◽  
Cut Scores ◽  
Factor Level ◽  
Scale Level ◽  
Scale Reliability ◽  
Point Rating Scale ◽  
Item Level ◽  
Scale Down

The authors evaluated measurement-level, factor-level, item-level, and scale-level revisions to the Gifted Rating Scales – School Form (GRS-S). Measurement-level considerations tested the extent to which treating the Likert scale rating as categorical or continuous produced different fit across unidimensional, correlated trait, and bi-factor latent factor structures. Item- and scale-level analyses demonstrated that the GRS-S could be reduced from a 72-item assessment on a 9-point rating scale down to a 30-item assessment on a 3-point rating scale. Reliability from the reduced assessment was high (ω &gt; .95). ROC curve comparisons between the original and reduced versions of the GRS-S showed that diagnostic accuracy (i.e., area under the curve) of the scales was comparable when considering cut-scores of 120, 125, and 130 on the WISC-IV full scale and verbal IQ and the WIAT-III composite score. The findings suggest that a brief form of the GRS-S can be used as a universal or selective screener for giftedness without sacrificing key psychometric considerations.

AAC Collaboration Using the Self-Anchored Rating Scales (SARS): An Aphasia Case Study

2012 ◽  
Vol 21 (4) ◽  
pp. 136-143
Author(s):  
Lynn E. Fox
Keyword(s):  
Augmentative And Alternative Communication ◽  
Rating Scales ◽  
Rating Scale ◽  
Therapeutic Process ◽  
Family Counseling ◽  
The Self ◽  
Alternative Communication ◽  
Her Family ◽  
Solution Focused

Abstract The self-anchored rating scale (SARS) is a technique that augments collaboration between Augmentative and Alternative Communication (AAC) interventionists, their clients, and their clients' support networks. SARS is a technique used in Solution-Focused Brief Therapy, a branch of systemic family counseling. It has been applied to treating speech and language disorders across the life span, and recent case studies show it has promise for promoting adoption and long-term use of high and low tech AAC. I will describe 2 key principles of solution-focused therapy and present 7 steps in the SARS process that illustrate how clinicians can use the SARS to involve a person with aphasia and his or her family in all aspects of the therapeutic process. I will use a case study to illustrate the SARS process and present outcomes for one individual living with aphasia.

Childbirth and Posttraumatic Stress Responses

2006 ◽  
Vol 22 (4) ◽  
pp. 259-267 ◽  
Author(s):  
Eelco Olde ◽  
Rolf J. Kleber ◽  
Onno van der Hart ◽  
Victor J.M. Pop
Keyword(s):  
Posttraumatic Stress Disorder ◽  
Posttraumatic Stress ◽  
Stress Responses ◽  
Rating Scales ◽  
Rating Scale ◽  
Stress Disorder ◽  
Traumatic Experience ◽  
Event Scale ◽  
Self Rating ◽  
The Impact

Childbirth has been identified as a possible traumatic experience, leading to traumatic stress responses and even to the development of posttraumatic stress disorder (PTSD). The current study investigated the psychometric properties of the Dutch version of the Impact of Event Scale-Revised (IES-R) in a group of women who recently gave birth (N = 435). In addition, a comparison was made between the original IES and the IES-R. The scale showed high internal consistency (α = 0.88). Using confirmatory factor analysis no support was found for a three-factor structure of an intrusion, an avoidance, and a hyperarousal factor. Goodness of fit was only reasonable, even after fitting one intrusion item on the hyperarousal scale. The IES-R correlated significantly with scores on depression and anxiety self-rating scales, as well as with scores on a self-rating scale of posttraumatic stress disorder. Although the IES-R can be used for studying posttraumatic stress reactions in women who recently gave birth, the original IES proved to be a better instrument compared to the IES-R. It is concluded that adding the hyperarousal scale to the IES-R did not make the scale stronger.

Sign in / Sign up

Export Citation Format

Share Document