Recent advances in text mining have provided new methods for capitalizing on the voluminous natural language data created by organizations, their employees, and customers. Although often overlooked, decisions made during preprocessing affect whether content and/or style of are captured, statistical power subsequent analyses, validity insights derived from mining. Past methodological articles described general process obtaining analyzing data, but recommendations were inconsistent....

Organizations are increasingly adopting automated video interviews (AVIs) to screen job applicants despite a paucity of research on their reliability, validity, and generalizability. In this study, we address gap by developing AVIs that use verbal, paraverbal, nonverbal behaviors extracted from assess Big Five personality traits. We developed validated machine learning models within (using nested cross-validation) across three separate samples mock (total N = 1,073). Also, examined...

In the age of big data, substantial research is now moving toward using digital footprints like social media text data to assess personality. Nevertheless, there are concerns and questions regarding psychometric validity evidence such approaches. We seek address this issue by focusing on (i) conducting a review validation efforts in mining (SMTM) for personality assessment discussing additional work that needs be done; (ii) considering issues from standpoint reference (i.e. ‘ground truth’)...

Given significant concerns about fairness and bias in the use of artificial intelligence (AI) machine learning (ML) for psychological assessment, we provide a conceptual framework investigating mitigating machine-learning measurement (MLMB) from psychometric perspective. MLMB is defined as differential functioning trained ML model between subgroups. manifests empirically when produces different predicted score levels subgroups (e.g., race, gender) despite them having same ground-truth...

Abstract Unproctored assessments are widely used in pre‐employment assessment. However, accessible large language models (LLMs) pose challenges for unproctored personnel assessments, given that applicants may use them to artificially inflate their scores beyond true abilities. This be particularly concerning cognitive ability tests, which and traditionally considered less fakeable by humans than personality tests. Thus, this study compares the performance of LLMs on two common types tests:...

Abstract Researchers have investigated whether machine learning (ML) may be able to resolve one of the most fundamental concerns in personnel selection, which is by helping reduce subgroup differences (and resulting adverse impact) race and gender selection procedure scores. This article presents three such investigations. The findings show that growing practice making statistical adjustments (nonlinear) ML algorithms must create predictive bias (differential prediction) as a mathematical...

We introduce the psychometric concepts of bias and fairness in a multimodal machine learning context assessing individuals' hireability from prerecorded video interviews. collected interviews 733 participants ratings panel trained annotators simulated hiring study, then interpretable models on verbal, paraverbal, visual features extracted videos to investigate unimodal versus fairness. Our results demonstrate that, absence any mitigation strategy, combining multiple modalities only...

Abstract Organisations are increasingly relying on people analytics to aid human resources decision‐making. One application involves using machine learning automatically infer applicant characteristics from employment interview responses. However, management research has provided scant validity evidence guide organisations' decisions about whether and how best implement these algorithmic approaches. To address this gap, we use closed vocabulary text mining mock video interviews train test...

Abstract Assessment center (AC) exercises such as role‐plays have established themselves valuable approaches for obtaining insights into interpersonal behavior, but they are often considered the “Rolls Royce” of personnel assessment due to their high costs. The observation and rating process comprises a substantial part these In an exploratory case study, we capitalize on recent advances in natural language processing (NLP) by developing NLP‐based machine learning (ML) models investigate...

Modeling politeness across cultures helps to improve intercultural communication by uncovering what is considered appropriate and polite. We study the linguistic features associated with American English Mandarin Chinese. First, we annotate 5,300 Twitter posts from United States (US) Sina Weibo China for scores. Next, develop an Chinese feature set, 'PoliteLex'. Combining it validated psycholinguistic dictionaries, correlations between perceived cultures. find that on Weibo, future-focusing...

Personal qualities like prosocial purpose and leadership predict important life outcomes, including college success. Unfortunately, the holistic assessment of personal in admissions is opaque resource intensive. Can artificial intelligence (AI) advance goals admissions? While cost-effective, AI has been criticized as a "black box" that may inadvertently penalize already disadvantaged subgroups when used high-stakes settings. Here, we consider an approach to assessing aims overcome these...

ABSTRACT The release of new generative artificial intelligence (AI) tools, including large language models (LLMs), continues at a rapid pace. Upon the OpenAI's o1 models, I reconducted Hickman et al.'s (2024) analyses examining how well LLMs perform on quantitative ability (number series) test. GPT‐4 scored below 20th percentile (compared to thousands human test takers), but 95th percentile. In response these updated findings and Lievens Dunlop's (2025) article about effects validity...

Purpose Effective leadership has been the focus of much research in recent years, but development is still understudied. Information technology (IT) continues to grow importance due industries IT creates, disrupts, and potential holds for all companies. Because highly context bound, purpose this paper examine take first steps toward establishing best practices development. Design/methodology/approach This conceptual reviews general before performing an integrated literature review as it...

The Problem Employers view today’s science, technology, engineering, and math (STEM) program graduates as deficient in interpersonal skills that are essential for team organizational performance. However, STEM programs continue to effectively engage development college level, instead placing the responsibility of such on employers. Solution A competency modeling framework should inform design education programs, this article describes a an educational used identify needed successfully...

Effective ways to measure employee job satisfaction are fraught with problems of scale, misrepresentation, and timeliness. Current methodologies limited in capturing subjective differences expectations, needs, values at work, they do not lay emphasis on demographic differences, which may impact people's perceptions satisfaction. This study proposes an approach assess by leveraging large-scale social media data. Starting initial Twitter dataset 1.5M posts, we examine two facets satisfaction,...

The 21st century workplace is an increasingly intercultural and collaborative environment. As a result, soft skills are being recognized as deficient in science, technology, engineering, math (STEM) graduates, documented survey commissioned by the Association of American Colleges Universities. social sciences humanities lag significantly behind science medicine utilization new immersive technologies such virtual reality. Our program seeks to improve essential for STEM students through...

Technological advances have led to the development of automated methods for personnel assessment that are purported augment or outperform human judgment. However, empirical research providing validity evidence such techniques in selection context remains scarce. In addressing this void, study focuses on language-based personality assessments using an off-the-shelf, commercially available product (i.e., IBM Watson Personality Insights) video-based interviews. The scores derived from were...

Abstract Sourcing algorithms are technologies used in online platforms to identify, screen, and inform potential applicants about job openings. The popularity of such is rapidly increasing due their pervasiveness advertising beliefs that sourcing can decrease time hire while improving the quality new hires. What little known, however, risks: could (intentionally or unintentionally) encode exacerbate occupational demographic disparities, thereby hindering organizational diversity and/or...

Organizations, researchers, and software increasingly use automatic speech recognition (ASR) to transcribe text. However, ASR can be less accurate for (i.e., biased against) certain demographic subgroups. This is concerning, given that the machine-learning (ML) models used automatically score video interviews transcriptions of interviewee responses as inputs. To address these concerns, we investigate extent bias its effects in scored interviews. Specifically, compare accuracy transcription...

We provide a psychometric-grounded exposition of bias and fairness as applied to typical machine learning (ML) pipeline for affective computing (AC). expand on an interpersonal communication framework elucidate how identify sources that may arise in the process inferring human emotions other psychological constructs from observed behavior. The various methods metrics measuring are discussed, along with pertinent implications within U.S. legal context. illustrate measure some types case study...

Purpose: Stakeholder theory (ST) is a reconceptualization of the firm that seeks to change business culture from being focused solely on profit and loss creating value for various stakeholders are affected by or can affect firm.Total Quality Management (TQM) philosophy focuses satisfying customer improving organizational processes improve quality products services while meeting predetermined standards.Nearly third U.S. voters believe colleges universities have negative effect nation,...

The 21st century workplace is an increasingly intercultural and collaborative environment. As a result, soft skills are being recognized as deficient in science, technology, engineering, math (STEM) graduates. Our program, Purdue Polytechnic Leadership Academy seeks to improve essential for STEM students through virtual reality (VR) simulations that immerse leadership case studies. Experiencing something from distance new type of technology enabled by the internet things known telehora....

Organizations are increasingly adopting automated video interviews (AVIs) to screen job applicants despite a paucity of research on their reliability, validity, and generalizability. In this study, we address gap by developing AVIs that use verbal, paraverbal, nonverbal behaviors extracted from assess Big Five personality traits. We developed validated machine learning models within (using nested cross-validation) across three separate samples mock (total N = 1,073). Also, examined...

Research on humility has burgeoned. However, behavioral assessments of that do not rely self-reports have developed much more slowly. The purpose this paper is to take stock existing approaches conceptualize and measure humility. Specifically, we provide a conceptual overview humility, including the limitations current methodological studying need for assessments. In addition, argue may inform broader measures virtues by considering both relevance degree which actual behaviors pertaining...