Question-based computational language approach outperforms rating scales in quantifying emotional states
Ontology highlight
ABSTRACT:
SUBMITTER: Sikstrom S
PROVIDER: S-EPMC11332055 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Rating scales are the dominating tool for the quantitative assessment of mental health. They are often believed to have a higher validity than language-based responses, which are the natural way of communicating mental states. Furthermore, it is unclear how difficulties articulating emotions-alexithymia-affect the accuracy of language-based communication of emotions. We investigated whether narratives describing emotional states are more accurately classified by questions-based computational analysis of language (QCLA) compared to commonly used rating scales. Additionally, we examined how this is affected by alexithymia. In Phase 1, participants (N = 348) generated narratives describing events related to depression, anxiety, satisfaction, and harmony. In Phase 2, another set of participants summarized the emotions described in the narratives of Phase 1 in five descriptive words and rating scales (PHQ-9, GAD-7, SWLS, and HILS). The words were quantified with a natural language processing model (i.e., LSA) and classified with machine learning (i.e., multinomial regression). The results showed that the language-based responses can be more accurate in classifying the emotional states compared to the rating scales. The degree of alexithymia did not influence the correctness of classification based on words or rating scales, suggesting that QCLA is not sensitive to alexithymia. However, narratives generated by people with high alexithymia were more difficult to classify than those generated by people with low alexithymia. These results suggest that the assessment of mental health may be improved by language-based responses analyzed by computational methods compared to currently used rating scales.
| S-EPMC11291691 | biostudies-literature
Project description:Different types of well-being are likely to be associated with different kinds of behaviors. The first objective of this study was, from a subjective well-being perspective, to examine whether harmony in life and satisfaction with life are related differently to cooperative behaviors depending on individuals' social value orientation. The second objective was, from a methodological perspective, to examine whether language-based assessments called computational language assessments (CLA), which enable respondents to answer with words that are analyzed using natural language processing, demonstrate stronger correlations with cooperation than traditional rating scales. Participants reported their harmony in life, satisfaction with life, and social value orientation before taking part in an online cooperative task. The results show that the CLA of overall harmony in life correlated with cooperation (all participants: r = 0.18, p < 0.05, n = 181) and that this was particularly true for prosocial participants (r = 0.35, p < 0.001, n = 96), whereas rating scales were not correlated (p > 0.05). No significant correlations (measured by the CLA or traditional rating scales) were found between satisfaction with life and cooperation. In conclusion, our study reveals an important behavioral difference between different types of subjective well-being. To our knowledge, this is the first study supporting the validity of self-reported CLA over traditional rating scales in relation to actual behaviors.
| S-EPMC8144476 | biostudies-literature
Project description:Middle aged adults experience depression and anxiety differently than younger adults. Age may affect life circumstances, depending on accessibility of social connections, jobs, physical health, etc, as these factors influence the prevalence and symptomatology. Depression and anxiety are typically measured using rating scales; however, recent research suggests that such symptoms can be assessed by open-ended questions that are analysed by question-based computational language assessments (QCLA). Here, we study middle aged and younger adults' responses about their mental health using open-ended questions and rating scales about their mental health. We then analyse their responses with computational methods based on natural language processing (NLP). The results demonstrate that: (1) middle aged adults describe their mental health differently compared to younger adults; (2) where, for example, middle aged adults emphasise depression and loneliness whereas young adults list anxiety and financial concerns; (3) different semantic models are warranted for younger and middle aged adults; (4) compared to young participants, the middle aged participants described their mental health more accurately with words; (5) middle-aged adults have better mental health than younger adults as measured by semantic measures. In conclusion, NLP combined with machine learning methods may provide new opportunities to identify, model, and describe mental health in middle aged and younger adults and could possibly be applied to the older adults in future research. These semantic measures may provide ecological validity and aid the assessment of mental health.
| S-EPMC10955843 | biostudies-literature
Project description:Aphasia nearly affects half of all poststroke patients. Furthermore, aphasia affects all language functions, well-being, and quality of life of patients. Therefore, rehabilitation of patients with aphasia requires an accurate assessment of language function and psychological aspects. However, assessment scales for language function and psychological aspects of patients with aphasia are said to be inaccurate. In Japan, this sign is more prominent than in English-speaking countries. Therefore, we are putting together a scoping review of research articles published in English and Japanese to date, with the aim of summarizing the accuracy of rating scales for language function and psychological aspects of people with aphasia. The scoping review was intended to be a comprehensive examination of the accuracy of rating scales for people with aphasia. We will search the article databases PubMed, MEDLINE, Embase, PsycINFO, Web of Science, and the Medical Journal Web (Japan). The observational studies that describe the reliability and validity of the rating scales in adult aphasic after stroke will be searched for. There will be no publication date for the articles that will be searched. We believe that this scoping review aims to assess the accuracy of rating scales used to measure different aspects of aphasia, with a focus on research conducted in English-speaking countries and Japan. By conducting this review, we believe to identify any problems with rating scales used in English and Japanese research and improve their accuracy.
| S-EPMC10187900 | biostudies-literature
Project description:Background Closed-ended rating scales are the most used response format for researchers and clinicians to quantify mental states, whereas in natural contexts people communicate with natural language. The reason for using such scales is that they are typically argued to be more precise in measuring mental constructs; however, the respondents’ views as to what best communicates mental states are frequently ignored, which is important for making them comply with assessment. Methods We assessed respondents’ (N = 304) degree of depression using rating scales, descriptive words, selected words, and free text responses and probed the respondents for their preferences concerning the response formats across twelve dimensions related to the precision of communicating their mental states and the ease of responding. This was compared with the clinicians’ (N = 40) belief of the respondent’s view. Results Respondents found free text to be more precise (e.g., precision d’ = .88, elaboration d’ = 2.0) than rating scales, whereas rating scales were rated as easier to respond to (e.g., easier d’ = –.67, faster d’ = –1.13). Respondents preferred the free text responses to a greater degree than rating scales compared to clinicians’ belief of the respondents’ views. Conclusions These findings support previous studies concluding that future assessment of mental health can be aided by computational methods based on text data. Participants prefer an open response format as it allows them to elaborate, be precise, etc., with respect to their mental health issues, although rating scales are viewed as faster and easier.
| S-EPMC9931093 | biostudies-literature
Project description:Inattention, impulsivity and hyperactivity are the primary behaviors associated with Attention Deficit / Hyperactivity Disorder (ADHD). Previous studies proved that peripheral blood gene expression signature could mirror central nervous system disease. This study determined if gene expression in blood correlated with inattention, hyperactivity/impulsivity rating scales and/or both in subjects with Tourette syndrome (TS).
2014-06-30 | GSE30470 | GEO
Project description:Many rating scales have been applied to the evaluation of dystonia, but only few have been assessed for clinimetric properties. The Movement Disorders Society commissioned this task force to critique existing dystonia rating scales and place them in the clinical and clinimetric context. A systematic literature review was conducted to identify rating scales that have either been validated or used in dystonia. Thirty-six potential scales were identified. Eight were excluded because they did not meet review criteria, leaving 28 scales that were critiqued and rated by the task force. Seven scales were found to meet criteria to be "recommended": the Blepharospasm Disability Index is recommended for rating blepharospasm; the Cervical Dystonia Impact Scale and the Toronto Western Spasmodic Torticollis Rating Scale for rating cervical dystonia; the Craniocervical Dystonia Questionnaire for blepharospasm and cervical dystonia; the Voice Handicap Index (VHI) and the Vocal Performance Questionnaire (VPQ) for laryngeal dystonia; and the Fahn-Marsden Dystonia Rating Scale for rating generalized dystonia. Two "recommended" scales (VHI and VPQ) are generic scales validated on few patients with laryngeal dystonia, whereas the others are disease-specific scales. Twelve scales met criteria for "suggested" and 7 scales met criteria for "listed." All the scales are individually reviewed in the online information. The task force recommends 5 specific dystonia scales and suggests to further validate 2 recommended generic voice-disorder scales in dystonia. Existing scales for oromandibular, arm, and task-specific dystonia should be refined and fully assessed. Scales should be developed for body regions for which no scales are available, such as lower limbs and trunk.
| S-EPMC4207366 | biostudies-literature
Project description:BackgroundTo evaluate the effect of (new) treatments or analyse prevalence and risk factors of contractures, rating scales are used based on joint range of motion. However, cut-off points for levels of severity vary between scales, and it seems unclear how cut-off points relate to function. The purpose of this study was to compare severity ratings of different rating scales for the shoulder and elbow and relate these with functional range of motion.MethodsOften used contracture severity rating scales in orthopedics, physiotherapy, and burns were included. Functional range of motion angles for the shoulder and elbow were derived from a recent synthesis published by our group. Shoulder flexion and elbow flexion range of motion data of patients three months after a burn injury were rated with each of the scales to illustrate the effects of differences in classifications. Secondly, the shoulder and elbow flexion range of motion angles were related to the required angles to perform over 50 different activities of daily living tasks.ResultsEighteen rating scales were included (shoulder: 6, elbow: 12). Large differences in the number of severity levels and the cut-off points between scales were determined. Rating the measured range of motions with the different scales showed substantial inconsistency in the number of joints without impairment (shoulder: 14-36%, elbow: 26-100%) or with severe impairment (shoulder: < 10%-29%, elbow 0%-17%). Cut-off points of most scales were not related to actual function in daily living.ConclusionThere is an urgent need for rating scales that express the severity of contractures in terms of loss of functionality. This study proposes a direction for a solution.
| S-EPMC6070201 | biostudies-literature
Project description:A variety of tools and methods have been used to measure behavioral symptoms of attention-deficit/hyperactivity disorder (ADHD). Missing data is a major concern in ADHD behavioral studies. This study used a deep learning method to impute missing data in ADHD rating scales and evaluated the ability of the imputed dataset (i.e., the imputed data replacing the original missing values) to distinguish youths with ADHD from youths without ADHD. The data were collected from 1220 youths, 799 of whom had an ADHD diagnosis, and 421 were typically developing (TD) youths without ADHD, recruited in Northern Taiwan. Participants were assessed using the Conners' Continuous Performance Test, the Chinese versions of the Conners' rating scale-revised: short form for parent and teacher reports, and the Swanson, Nolan, and Pelham, version IV scale for parent and teacher reports. We used deep learning, with information from the original complete dataset (referred to as the reference dataset), to perform missing data imputation and generate an imputation order according to the imputed accuracy of each question. We evaluated the effectiveness of imputation using support vector machine to classify the ADHD and TD groups in the imputed dataset. The imputed dataset can classify ADHD vs. TD up to 89% accuracy, which did not differ from the classification accuracy (89%) using the reference dataset. Most of the behaviors related to oppositional behaviors rated by teachers and hyperactivity/impulsivity rated by both parents and teachers showed high discriminatory accuracy to distinguish ADHD from non-ADHD. Our findings support a deep learning solution for missing data imputation without introducing bias to the data.
| S-EPMC7379397 | biostudies-literature
Project description:Measures of psychological attributes, such as motivation, typically involve rating scales, assuming that an attribute can be ordered. If an attribute has an ordinal structure, its levels stand in ordinal relations to one another, and these must be transitive. We tested if transitivity is preserved when people compare different motives in terms of their importance to learning. We found transitivity violations in both strict (Study 1) and non-strict (Study 2) orderings in about half of the participants. Nevertheless, based on the distribution of such violations, we conclude that an ordinal structure of motivation can be found, but only when levels of motives differ noticeably. As the levels become subjectively similar, transitivity is not preserved, and the ordinal structure cannot be justified even in non-strict ordering. The findings question the mainstream practice of measuring psychological attributes before their structure is properly explored.
| S-EPMC8514613 | biostudies-literature