Improving the Automatic Classification of Interviewer Questions in Avatar‐Based Child Investigative Interview Simulations: A Transformer Approach

Abstract Purpose Interviewer questioning style, including the types of questions asked, represents one measurable and trainable component of child investigative interview quality. Although automated approaches to question classification have been explored, previous systems have shown only moderate performance, particularly when distinguishing fine‐grained categories of questions. The present study aimed to improve the automatic multi‐class classification of interviewer questions and the detection of repetitive questioning patterns in avatar‐based simulations of child sexual abuse investigative interviews using transformer‐based architectures. Method The system was trained on 17,425 annotated questions derived from controlled avatar‐based interview simulations and categorized into 14 question‐category labels. A transformer model (F2LLM‐0.6B) was fine‐tuned for multi‐class classification using weighted loss to address class imbalance. A separate LLM‐based module (Qwen3.5‐9B) detected semantically repeated or reformulated questions within interview sequences. Performance was evaluated using accuracy, macro‐ and weighted F1‐scores, and confusion matrix analyses. On a held‐out test set ( N = 2, 614), the classification model achieved an overall accuracy of 86.8% and a macro‐F1 score of 79.0%, while the repetition‐detection module achieved an accuracy of 84.9%. Conclusions These findings indicate that AI systems can approximate the available human‐coded reference labels for interviewer question types and identify repeated or reformulated questioning patterns. The system supports taxonomy‐based coding of interviewer questions; it does not independently determine their pragmatic or contextual appropriateness within the broader interview sequence, nor does it assess overall interview quality. The proposed approach provides a scalable framework for automated question‐type coding in avatar‐based training and research settings while preserving the central role of professional judgement.

Authors

Institutions

Publication Details

Journal
Legal and Criminological Psychology
Published
2026-11-14
DOI
https://doi.org/10.1111/lcrp.70073
Primary Topic
Deception detection and forensic psychology
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Improving the Automatic Classification of Interviewer Questions in Avatar‐Based Child Investigative Interview Simulations: A Transformer Approach

Antonietta Curci, Pekka Olavi Santtila, Francesco Pompedda, Alessia Anna Catalano et al.
Legal and Criminological Psychology
Deception detection and forensic psychology
article

Improving the Automatic Classification of Interviewer Questions in Avatar‐Based Child Investigative Interview Simulations: A Transformer Approach

Antonietta Curci, Pekka Olavi Santtila, Francesco Pompedda, Alessia Anna Catalano, Fabiana Battista, Roberto Vadacca
article en

Abstract

Abstract Purpose Interviewer questioning style, including the types of questions asked, represents one measurable and trainable component of child investigative interview quality. Although automated approaches to question classification have been explored, previous systems have shown only moderate performance, particularly when distinguishing fine‐grained categories of questions. The present study aimed to improve the automatic multi‐class classification of interviewer questions and the detection of repetitive questioning patterns in avatar‐based simulations of child sexual abuse investigative interviews using transformer‐based architectures. Method The system was trained on 17,425 annotated questions derived from controlled avatar‐based interview simulations and categorized into 14 question‐category labels. A transformer model (F2LLM‐0.6B) was fine‐tuned for multi‐class classification using weighted loss to address class imbalance. A separate LLM‐based module (Qwen3.5‐9B) detected semantically repeated or reformulated questions within interview sequences. Performance was evaluated using accuracy, macro‐ and weighted F1‐scores, and confusion matrix analyses. On a held‐out test set ( N = 2, 614), the classification model achieved an overall accuracy of 86.8% and a macro‐F1 score of 79.0%, while the repetition‐detection module achieved an accuracy of 84.9%. Conclusions These findings indicate that AI systems can approximate the available human‐coded reference labels for interviewer question types and identify repeated or reformulated questioning patterns. The system supports taxonomy‐based coding of interviewer questions; it does not independently determine their pragmatic or contextual appropriateness within the broader interview sequence, nor does it assess overall interview quality. The proposed approach provides a scalable framework for automated question‐type coding in avatar‐based training and research settings while preserving the central role of professional judgement.

Legal and Criminological Psychology
University of Salento (IT), University of Turku (FI), New York University Shanghai (CN), Innovation Engineering (Italy) (IT), Pegaso University (IT), University of Bari Aldo Moro (IT)
Deception detection and forensic psychology
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon