Automatic Item Generation for Personality Situational Judgment Tests with Large Language Models

情境伦理学 人格 心理学 计算机科学 自然语言处理 认知心理学 社会心理学
作者
Changjin Li,Jiyuan Zhang,Yun Tang,Jian Li
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2412.12144
摘要

Personality assessment, particularly through situational judgment tests (SJTs), is a vital tool for psychological research, talent selection, and educational evaluation. This study explores the potential of GPT-4, a state-of-the-art large language model (LLM), to automate the generation of personality situational judgment tests (PSJTs) in Chinese. Traditional SJT development is labor-intensive and prone to biases, while GPT-4 offers a scalable, efficient alternative. Two studies were conducted: Study 1 evaluated the impact of prompt design and temperature settings on content validity, finding that optimized prompts with a temperature of 1.0 produced creative and accurate items. Study 2 assessed the psychometric properties of GPT-4-generated PSJTs, revealing that they demonstrated satisfactory reliability and validity, surpassing the performance of manually developed tests in measuring the Big Five personality traits. This research highlights GPT-4's effectiveness in developing high-quality PSJTs, providing a scalable and innovative method for psychometric test development. These findings expand the possibilities of automatic item generation and the application of LLMs in psychology, and offer practical implications for streamlining test development processes in resource-limited settings.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
优秀的小豆芽完成签到,获得积分10
刚刚
916应助科研通管家采纳,获得10
1秒前
SciGPT应助科研通管家采纳,获得10
1秒前
CodeCraft应助科研通管家采纳,获得10
2秒前
hhllhh完成签到,获得积分10
2秒前
Ava应助科研通管家采纳,获得10
2秒前
深情安青应助科研通管家采纳,获得10
2秒前
2秒前
2秒前
pluto应助杪夏二八采纳,获得30
2秒前
2秒前
916应助科研通管家采纳,获得10
2秒前
科研通AI5应助科研通管家采纳,获得10
2秒前
自由飞翔发布了新的文献求助10
3秒前
Naza1119完成签到,获得积分10
3秒前
学分完成签到 ,获得积分10
9秒前
10秒前
无语的安白应助nimonimo采纳,获得10
10秒前
LLII完成签到,获得积分10
12秒前
万金油完成签到 ,获得积分10
15秒前
小玉完成签到,获得积分10
17秒前
tyh完成签到,获得积分10
18秒前
19秒前
十三完成签到,获得积分10
23秒前
姜酱江酱发布了新的文献求助10
23秒前
LiZH发布了新的文献求助10
25秒前
liugm发布了新的文献求助10
25秒前
wanci应助颜凡桃采纳,获得10
29秒前
萌萌完成签到,获得积分10
32秒前
33秒前
34秒前
小蘑菇应助燕子非采纳,获得10
35秒前
35秒前
36秒前
碗在水中央完成签到 ,获得积分0
36秒前
芊芊完成签到 ,获得积分10
37秒前
不管啦发布了新的文献求助10
37秒前
h7nho发布了新的文献求助10
39秒前
SciGPT应助Duuuu采纳,获得10
43秒前
44秒前
高分求助中
Applied Survey Data Analysis (第三版, 2025) 800
Narcissistic Personality Disorder 700
Assessing and Diagnosing Young Children with Neurodevelopmental Disorders (2nd Edition) 700
Handbook of Experimental Social Psychology 500
The Martian climate revisited: atmosphere and environment of a desert planet 500
Transnational East Asian Studies 400
Towards a spatial history of contemporary art in China 400
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3846188
求助须知:如何正确求助?哪些是违规求助? 3388570
关于积分的说明 10553483
捐赠科研通 3109110
什么是DOI,文献DOI怎么找? 1713336
邀请新用户注册赠送积分活动 824732
科研通“疑难数据库(出版商)”最低求助积分说明 774982