An Online Attachment Style Recognition System Based on Voice and Machine Learning - Attachment Style - Remote Recognition Accuracy Results

Aug 5, 2026

Upload by Maeve

Attachment styles show strong links to mental and physical health, where insecure patterns increase risk for mental disorders and chronic conditions. The study develops a voice-based recognition model to distinguish secure versus insecure attachment styles by leveraging acoustic characteristics and examining gender effects. Responses from 199 participants were collected through a web-based interrogation system, processed with eGeMAPS features and feature selection via recursive feature elimination. Supervised models achieved higher test accuracy under gender-dependent evaluation, highlighting gender influence and supporting objective remote screening using speech recordings.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

Introduction

Attachment theory and internal working models

Adult attachment categories

Health implications of attachment styles

An Online Attachment Style Recognition System Based on Voice and Machine Learning Lucía Gómez-Zaragozá , Javier Marín-Morales , Elena Parra Vargas , Irene Alice Chicchi Giglioli , and Mariano Alcañiz Raya Abstract—Attachment styles are known to have signiﬁcant associations with mental and physical health. Specifically, insecure attachment leads individuals to higher risk of suffering from mental disorders and chronic diseases. The aim of this study is to develop an attachment recognition model that can distinguish between secure and insecure attachment styles from voice recordings, exploring the importance of acoustic features while also evaluating gender differences. A total of 199 participants recorded their responses to four open questions intended to trigger their attachment system using a web-based interrogation system. The recordings were processed to obtain the standard acoustic feature set eGeMAPS, and recursive feature elimination was applied to select the relevant features. Different supervised machine learning models were trained to recognize attachment styles using both gender-dependent and gender-independent approaches. The gender-independent model achieved a test accuracy of 58.88%, whereas the gender-dependent models obtained 63.88% and 83.63% test accuracy for women and men respectively, indicating a strong inﬂuence of gender on attachment style recognition and the need to consider them separately in further studies. These results also demonstrate the potential of acoustic properties for remote assessment of attachment style, enabling fast and objective identiﬁcation of this health risk factor, and thus supporting the implementation of largescale mobile screening systems. Index Terms—Acoustic features, artiﬁcial intelligence, attachment, gender, psychometrics, speech analysis, statistical machine learning, voice. I. INTRODUCTION ATTACHMENT theory is a wide-ranging social develop ment theory introduced by John Bowlby that describes Manuscript received 6 April 2023; revised 5 July 2023; accepted 4 August 2023 . Date of publication 11 August 2023; date of current version 7 November 2023 . This work was supported in part by the Generalitat Valenciana under Grant ACIF/2021/187, and its funded Project Mixed reality and brain decision - REBRAND under Grant PROMETEO/2019/105, and in part by the Universitat Politècnica de València under Grants PAID-10-20 and PAID-PD-22 . (Corresponding author: Lucía Gómez-Zaragozá.) This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the Research Ethics Committee of the Polytechnic University of Valencia Application No. P01_08_07_20. The authors are with the Instituto Universitario de Investigaciónen Tecnología Centrada en el Ser Humano, Universitat Politècnica de València, 46022 Valencia, Spain (e-mail: lugoza@htech.upv. es; jamarmo@htech.upv.es; elparvar@htech.upv.es; alice.chicchi@ [gmail.com](gmail.com) ; [malcaniz@htech.upv.es](malcaniz@htech.upv.es)). Digital Object Identiﬁer 10.1109/JBHI.2023.3304369 Fig. 1. Four-category model of adult attachment. Adapted from [5] . the origin of the patterns that take place in close interpersonal relationships, known as attachment styles [1] . Bowlby proposed the attachment behavioral system as a psychological organization that regulates behaviors that are necessary for acquiring and maintaining stable and valuable emotional relationships across the lifespan. The theory states that throughout their early stages of life, children develop attachment behaviors in the form of basic emotional expression as a mechanism to obtain the closeness of their attachment ﬁgures (typically their parents) during uncertain and stressful situations [1] . Depending on how the attachment ﬁgures respond, children adapt their behaviorsand construct what Bowlby called internal working models of the self and others [2] . The self-model refers to the me

FAQs

What is the goal of the proposed system?

Develop a model that recognizes secure versus insecure attachment styles from voice recordings, focusing on acoustic features and evaluating gender differences.

How were the voice recordings processed and features selected?

Recordings were converted into eGeMAPS acoustic features, then recursive feature elimination was used to select the most relevant features.

How did gender affect recognition performance?

The gender-independent model achieved 58.88% test accuracy, while gender-dependent models reached 63.88% for women and 83.63% for men, indicating a strong gender influence.

Aug 5, 2026

Upload by Maeve