fullscreen

eFinder

eFinder

Home › Article

Israeli scientists: AI can make personality tests, predict responses | The Jerusalem Post

Jpost · 🇺🇸 public United States · · 1147 words · By JUDY SIEGEL-ITZKOVICH
headphones Listen to the eFinder podcast briefing
Generate a natural audio summary of this story
Daily briefing

What to know about Israeli scientists: AI can make personality tests, predict responses

All users of ChatGPT, Gemini, and other artificial intelligence platforms know that these large language models (LLMs) are usually very “smart” and analyze texts and answer questions very well.

Claims checked 10
Techniques found 0
Topics 0

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center100%
Right0%

4 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

All users of ChatGPT, Gemini, and other artificial intelligence platforms know that these large language models (LLMs) are usually very “smart” and analyze texts and answer questions very well.

Why it matters

Hebrew University of Jerusalem (HUJI) scientists have developed a method for generating personality assessment questionnaires with ChatGPT from any source text in English.

Common ground

To test the method, they applied it to both the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5) – the “bible” of mental health professionals published by the American Psychiatric Association to name, describe, and diagnose mental…

Perspective signals

No major persuasion pattern has been attached yet, so the source, headline, and evidence should carry most of the weight for readers.

open_in_new Read the original article: https://www.jpost.com/science/article-906137

fact_checkClaims Checked

eFinder analyzed this article and checked 10 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

check_circle Corroborated 7
info Single Source 1
verified Verified By Reference 1
help Insufficient Evidence 1
check_circle
Claim 1: “ChatGPT could predict how participants would respond to the questionnaires before they were taken.”
CORROBORATED
Multiple sources, including Neurospace and other web results, explicitly state that the AI accurately predicted how participants would respond before the surveys were administered.
info
Claim 2: “RESULTS from the DSM-5-sourced questionnaire showed high internal consistency within personality clusters”
SINGLE SOURCE
While the study's existence is corroborated, the specific result regarding 'high internal consistency within personality clusters' for the DSM-5 questionnaire is not explicitly detailed in the provided snippets, though it is implied by the general success of the method.
travel_explore
web search NEUTRAL — Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives.
https://www.bbc.co.uk/news
travel_explore
web search NEUTRAL — Visit BBC News for up-to-the-minute news, breaking news, video, audio and feature stories. BBC News provides trusted World and UK news as well as local and regional perspectives.
http://www.bbc.com/news
travel_explore
web search NEUTRAL — Get all the latest news, live updates and content about the World from across the BBC.
https://www.bbc.co.uk/news/world
verified
Claim 3: “ChatGPT and other publicly accessible LLMs are trained on the Internet by compiling trillions of human-language data inputs from websites and social media.”
VERIFIED BY REFERENCE
Wikipedia entries for 'ChatGPT' and 'Large language model' confirm that LLMs are trained on vast amounts of text data from the internet to generate and analyze language.
menu_book
wikipedia NEUTRAL — ChatGPT is a generative AI chatbot developed by OpenAI. Originally released on November 30, 2022, the product uses large language models—specifically generative pre-trained transformers (GPTs)—to gene…
https://en.wikipedia.org/wiki/ChatGPT
menu_book
wikipedia NEUTRAL — Deep Research is an AI agent integrated into ChatGPT, which generates cited reports on a user-specified topic by autonomously browsing the web for 5 to 30 minutes.
https://en.wikipedia.org/wiki/ChatGPT_Deep_Research
menu_book
wikipedia NEUTRAL — A large language model (LLM) is an AI model (typically a neural network) trained on a vast amount of text for natural language processing tasks, especially language generation. LLMs can typically gene…
https://en.wikipedia.org/wiki/Large_language_model
+ 3 more evidence sources
check_circle
Claim 4: “the researchers said they used GPT-4... to generate two personality assessment questionnaires.”
CORROBORATED
Multiple sources confirm the researchers used GPT-4 to generate two personality assessment questionnaires.
travel_explore
web search NEUTRAL — The study using LLM-generated personality assessment could eventually be used to assess human patients. “It will take time, and there are risks,” said Monsa, “and it has to be analyzed by psychologist…
https://www.jpost.com/science/article-906137
travel_explore
web search NEUTRAL — To test how well LLMs can naturally assess human personality, the researchers used GPT-4 to generate two personality assessment questionnaires.
https://sciencemission.com/personality-questionnaires
travel_explore
web search NEUTRAL — Generating and analyzing personality questionnaires using large language models.
https://www.eurekalert.org/news-releases/1137746
help
Claim 5: “the astrology questionnaire, by contrast, showed a weak internal consistency across traits.”
INSUFFICIENT EVIDENCE
No specific evidence in the provided search results explicitly mentions the internal consistency results of the astrology questionnaire, although the questionnaire's existence as a control is confirmed.
check_circle
Claim 6: “Another questionnaire used the astrology textbook as a control”
CORROBORATED
Multiple sources explicitly state that an astrology textbook was used as a control for the second questionnaire.
travel_explore
web search NEUTRAL — Another questionnaire used the astrology textbook as a control; it generated similar statements, but these were based on the source text’s assignment of personality traits to the astrological zodiac s…
https://www.jpost.com/science/article-906137
travel_explore
web search NEUTRAL — As a control, another questionnaire used an astrology textbook.Generating and analyzing personality questionnaires using large language models. The Five-Factor Model (“Big Five”) is based on the lexic…
https://neurosciencenews.com/chatgpt-ai-personality-tests-31…
travel_explore
web search NEUTRAL — Researchers used ChatGPT to generate personality questionnaires from the DSM-5 and even an astrology textbook — and the AI accurately predicted how 600 people would answer before a single survey was a…
https://neurospace.co/artigo/chatgpt-predicts-personality-te…
check_circle
Claim 7: “They first used excerpts from the DSM-5 as source text”
CORROBORATED
Web search results confirm that one of the questionnaires was generated using excerpts from the DSM-5.
menu_book
wikipedia NEUTRAL — The Diagnostic and Statistical Manual of Mental Disorders (DSM; latest edition: DSM-5-TR, published in March 2022) is a publication by the American Psychiatric Association (APA) for the classification…
https://en.wikipedia.org/wiki/Diagnostic_and_Statistical_Man…
menu_book
wikipedia NEUTRAL — The Psychodynamic Diagnostic Manual (PDM) is a diagnostic handbook similar to the International Statistical Classification of Diseases and Related Health Problems (ICD) or the Diagnostic and Statistic…
https://en.wikipedia.org/wiki/Psychodynamic_Diagnostic_Manua…
menu_book
wikipedia NEUTRAL — The Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), is the 2013 update to the Diagnostic and Statistical Manual of Mental Disorders, the taxonomic and diagnostic tool pub…
https://en.wikipedia.org/wiki/DSM-5
+ 3 more evidence sources
check_circle
Claim 8: “After the LLM-based questionnaires were generated, they were presented to 600 people together with the Big Five personality questionnaire (BFI)”
CORROBORATED
Neurospace reports that the AI predicted how 600 people would answer, and other sources mention the use of the Big Five Inventory (BFI) in the context of the study.
menu_book
wikipedia NEUTRAL — Artificial intelligence marketing (AI marketing) is a form of marketing that uses artificial intelligence concepts and models such as machine learning, natural language processing, and computer vision…
https://en.wikipedia.org/wiki/Artificial_intelligence_in_mar…
menu_book
wikipedia NEUTRAL — HTC Corporation (Chinese: 宏達國際電子股份有限公司; pinyin: Hóngdá Guójì Diànzǐ Gǔfèn Yǒuxiàn Gōngsī), or High Tech Computer Corporation (abbreviated and trading as HTC), is a Taiwanese consumer electronics corpo…
https://en.wikipedia.org/wiki/HTC
menu_book
wikipedia NEUTRAL — These datasets are used in machine learning (ML) research and have been cited in peer-reviewed academic journals. Datasets are an integral part of the field of machine learning. Major advances in this…
https://en.wikipedia.org/wiki/List_of_datasets_for_machine-l…
+ 3 more evidence sources
check_circle
Claim 9: “The team – Dr. Rotem Monsa, Prof. Aviv Zohar, and Prof. Shahar Arzy of the Hebrew University-Hadassah Medical School and the HUJI Faculty of Computer Science published its findings in the Cell Press journal iScience under the title “Generating and analyzing personality questionnaires using large language models.””
CORROBORATED
Web search results explicitly name Dr. Rotem Monsa, Prof. Aviv Zohar, and Prof. Shahar Arzy, and confirm the publication title 'Generating and analyzing personality questionnaires using large language models' in the journal iScience.
travel_explore
web search NEUTRAL — Aviv Zohar, and Prof. Shahar Arzy of the Hebrew University-Hadassah Medical School and the HUJI Faculty of Computer Science published its findings in the Cell Press journal iScience under the title “G…
https://www.jpost.com/science/article-906137
travel_explore
web search NEUTRAL — In this study, we conduct bibliometric and discourse analyses of scholarly literature on LLMs. Synthesizing over 5,000 publications, this article serves as a roadmap for researchers, practitioners, an…
https://www.researchgate.net/publication/411793167_Generatin…
travel_explore
web search NEUTRAL — Generating and analyzing personality questionnaires using large language models.Large language models (LLMs) offer new ways to explore personality through text. We developed an LLM-based method to gen…
https://neurosciencenews.com/chatgpt-ai-personality-tests-31…
check_circle
Claim 10: “Hebrew University of Jerusalem (HUJI) scientists have developed a method for generating personality assessment questionnaires with ChatGPT from any source text in English.”
CORROBORATED
Multiple independent sources (Neuroscience News, EurekAlert, and other web results) confirm that researchers from the Hebrew University developed a method to generate personality questionnaires using LLMs.
menu_book
wikipedia NEUTRAL — Hasbara (Hebrew: הַסְבָּרָה) is the public diplomacy of Israel. It includes mass communication, individual interaction with foreign nationals through social and traditional media, and cultural diploma…
https://en.wikipedia.org/wiki/Hasbara
menu_book
wikipedia NEUTRAL — Ilya Sutskever (Hebrew: איליה סוצקבר; born 1986) is a Soviet-born Israeli-Canadian computer scientist who specializes in machine learning. He has made several major contributions to the field of deep …
https://en.wikipedia.org/wiki/Ilya_Sutskever
menu_book
wikipedia NEUTRAL — Elon Musk is a businessman and entrepreneur known for his leadership of Tesla, SpaceX, X (formerly Twitter), and xAI. He is the wealthiest individual in the world, and a former U.S. government employe…
https://en.wikipedia.org/wiki/Views_of_Elon_Musk
+ 3 more evidence sources
info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.