Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Language and Cognition01:27

Language and Cognition

704
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
704
Nominal Level of Measurement00:56

Nominal Level of Measurement

37.0K
The way a set of data is measured is called its level of measurement. Correct statistical procedures depend on a researcher being familiar with levels of measurement. Not every statistical operation can be used with every set of data. For analysis, data are classified into four levels of measurement—nominal, ordinal, interval, and ratio.
The data that cannot be measured but can be grouped into categories fall under the nominal level of measurement. Data that is measured using a nominal...
37.0K
Stereotype Content Model02:16

Stereotype Content Model

15.3K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.3K
Language Development01:22

Language Development

841
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
841
Measures of Intelligence01:29

Measures of Intelligence

8.3K
Psychologists measure intelligence by using standardized tests that produce a score known as the intelligence quotient or IQ. To understand IQ tests, it's important to recognize the key principles behind their construction: validity, reliability, and standardization.
Validity refers to how well a test measures what it claims to measure. An intelligence test should accurately assess intelligence rather than another characteristic, like anxiety. Criterion validity is one way to evaluate this;...
8.3K
Ordinal Level of Measurement00:55

Ordinal Level of Measurement

31.9K
The way a set of data is measured is called its level of measurement. Correct statistical procedures depend on a researcher being familiar with levels of measurement. For analysis, data are classified into four levels of measurement—nominal, ordinal, interval, and ratio.
Data measured using an ordinal scale are similar to nominal scale data, but there is one major difference. The ordinal scale data can be ordered. An example of ordinal scale data is a list of the top five national parks...
31.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Developmental high-risk criteria for severe mental illness: a neurodevelopmental framework for premorbid detection.

Frontiers in psychiatry·2026
Same author

Altered mirroring and self-face processing in schizophrenia: A systematic review.

Schizophrenia research·2026
Same author

Ipseity-Disturbance and the Nature of Self-Disorder in Schizophrenia: Clarifying Conceptual and Empirical Foundations (a Constructive Reply to Feyaerts and Sass).

Schizophrenia bulletin·2026
Same author

Familial high-risk (FHR) for severe mental illness in clinical high-risk for psychosis (CHR-P): a systematic review and meta-analysis.

European archives of psychiatry and clinical neuroscience·2026
Same author

Bayesian uncertainty quantification to identify population level vaccine hesitancy behaviours.

PloS one·2026
Same author

Rethinking the p-factor: A model of cumulative risk aggregation across development-Commentary on Caspi et al. (2026).

Journal of psychopathology and clinical science·2026

Related Experiment Video

Updated: Jan 14, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K

Rethinking psychometrics through LLMs: how item semantics shape measurement and prediction in psychological

Federico Ravenda1, Antonio Preti2, Michele Poletti3

  • 1Euler Institute, Faculty of Informatics, Università della Svizzera italiana, Lugano, Switzerland. federico.ravenda@usi.ch.

Scientific Reports
|October 24, 2025
PubMed
Summary

Large language models (LLMs) reveal that item semantics significantly influence psychological questionnaire results. This finding suggests a need to re-examine how we design and interpret psychological measurements.

Keywords:
Large Language ModelsPsychological QuestionnairePsychometrics

More Related Videos

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

8.0K
Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.7K

Related Experiment Videos

Last Updated: Jan 14, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.0K
Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
08:05

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

8.0K
Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment
06:48

Lexical Decision Task for Studying Written Word Recognition in Adults with and without Dementia or Mild Cognitive Impairment

Published on: June 25, 2019

9.7K

Area of Science:

  • Psychometrics
  • Computational Linguistics
  • Psychological Measurement

Background:

  • Psychological questionnaires rely on semantically related items to measure latent constructs.
  • The inherent semantic structure of questionnaire items may influence collected data, independent of the underlying construct.
  • The extent to which item semantics shape measurement outcomes versus empirical correlations is an open epistemological question.

Purpose of the Study:

  • To introduce LLMs Psychometrics, a novel paradigm using LLMs to investigate the influence of item semantics on psychometric outcomes.
  • To test the hypothesis that linguistic similarity between items predicts their empirical correlations, even without empirical data.
  • To develop and validate a model (PsychoLLM) that leverages item semantics for response prediction.

Main Methods:

  • Comparison of empirical correlation matrices from established psychological instruments (Big 5 Personality, DASS-42) with semantic similarity structures derived from LLMs.
  • Development of PsychoLLM, a neural architecture utilizing item semantics to predict questionnaire responses.
  • Validation of PsychoLLM using datasets from the Generalized Anxiety Disorder-7 (GAD-7) and Patient Health Questionnaire-9 (PHQ-9).

Main Results:

  • LLMs accurately predicted item correlations, with the most correlated item found within the top 3 semantically similar items in 95% of DASS-42 cases and 82% of Big 5 cases.
  • PsychoLLM achieved 70% accuracy in predicting responses between different psychological scales (GAD-7 and PHQ-9) based solely on item semantics.
  • The study demonstrated that item semantics impose a predictable structure on psychometric data.

Conclusions:

  • Item semantics exert a significant, previously underestimated influence on psychological measurement outcomes.
  • LLMs can be leveraged to expose the a priori semantic structure within questionnaires, aiding in questionnaire design and data quality assessment.
  • This research necessitates a re-evaluation of measurement principles in psychology, considering the role of linguistic properties in psychometric data.