2026-10-10T19:21:49Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34032495 2026-09-30T13:03:34Z category_173 portal_316 item_type_3 month_year_09_2026

Supplementary file 1_From direct scoring to cue integration: big five prediction from spoken responses to a picture-based self-projection task.docx Qifan Yang (2900150) Jian Li (41607) Applied Psychology big five personality cue integration LLM-assisted measurement picture-based self-projection task spoken responses trait recoverability Objective<p>Open-ended language tasks are increasingly used in personality assessment, but their psychometric value largely depends on two factors: the type of evidence a task elicits and how that evidence is represented before scoring.</p>Methods<p>In this study, we examined five spoken responses to a picture-based self-projection task collected from 374 participants during in-person workplace training sessions. Participants first completed the Big Five Inventory-2 questionnaire; the spoken task was administered approximately 1 day later, and responses were transcribed using a Whisper-based automatic speech recognition pipeline. We compared four approaches applied to the same transcribed corpus: Linguistic Inquiry and Word Count (a lexical dictionary method), contextual semantic embeddings, holistic large language model (LLM) appraisal (holistic appraisal route; HAR), and hierarchical cue integration route (HCIR).</p>Results<p>The results were trait-specific: extraversion was the most recoverable domain across methods, whereas Openness was the least recoverable. HAR preserved rank-order information, particularly for Extraversion, but exhibited poor calibration, evidenced by negative mean R² values and systematic directional bias in extreme score bands. In the retained comparison, HCIR-Grounded showed the most favorable observed association–calibration profile among the evaluated approaches (mean |r| = 0.264, mean R² = 0.073), with notably higher observed correlations for Agreeableness, Conscientiousness, and Neuroticism.</p>Discussion<p>We refrain from attributing this pattern solely to cue integration, however, as HCIR included a supervised calibration stage that HAR lacked; the comparison therefore reflects the joint contribution of cue organization and supervised calibration. By explicitly organizing cue provenance, self-relevance, quality indicators, and trait-specific evidence before supervised calibration, HCIR supports a measurement-oriented interpretation of LLM-assisted personality inference from spoken responses that combine self-projection, preference, and normative evaluation.</p> 2026-09-30T13:03:34Z Dataset Dataset 10.3389/fpsyg.2026.1930314.s001 https://figshare.com/articles/dataset/Supplementary_file_1_From_direct_scoring_to_cue_integration_big_five_prediction_from_spoken_responses_to_a_picture-based_self-projection_task_docx/34032495 CC BY 4.0