Interpretable machine learning for hikikomori screening: The adaptive HRI-15

Daiana Colledani, Pasquale Anselmi, Lucia Monacis, Bruno Genetti, Daniele Fassinato, Luis J Gomez Perez, Adele Minutillo, Luisa Mastrobattista · 2026

Read Interpretable machine learning for hikikomori screening: The adaptive HRI-15 by Daiana Colledani, Pasquale Anselmi, Lucia Monacis, Bruno Genetti, Daniele Fassinato, Luis J Gomez Perez, Adele Minutillo, Luisa Mastrobattista (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355595.txt.

Description

Daiana Colledani and seven colleagues improve a screening tool for hikikomori, the severe and prolonged social withdrawal first described in Japan, in this 2026 study. Data came from a national survey of nearly nine thousand Italian teenagers who completed a fifteen-item questionnaire about withdrawal. The goal was to make the tool faster and more clinically useful without losing accuracy.

The researchers set a cutoff score that best separated at-risk teenagers and identified four distinct profiles that differed in anxiety, depression, impulsivity, and risky behavior. They then built an adaptive version that asks only the questions each person needs, cutting the length roughly in half while reproducing full scores closely. Packaged into an app that handles scoring and reporting, the short test could help schools and clinics spot withdrawn teenagers far earlier.

Catalog record

CREATORDaiana Colledani, Pasquale Anselmi, Lucia Monacis, Bruno Genetti, Daniele Fassinato, Luis J Gomez Perez, Adele Minutillo, Luisa Mastrobattista
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE82754
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355595

Browse the full library · About the Tower of Babel