View in EDS HTML Full Text PDF Full Text

Using Speech Features and Machine Learning Models to Predict Emotional and Behavioral Problems in Chinese Adolescents.

Saved in:
Bibliographic Details
Title: Using Speech Features and Machine Learning Models to Predict Emotional and Behavioral Problems in Chinese Adolescents.
Authors: Li, Jinyu (AUTHOR), Wang, Yang (AUTHOR), Wang, Fei (AUTHOR), Zhang, Ran (AUTHOR), Wang, Ning (AUTHOR), Zhu, Yue (AUTHOR), Zhao, Taihong (AUTHOR), Ai, Sizhi (AUTHOR)
Source: Depression & Anxiety (1091-4269). 6/16/2025, Vol. 2025, p1-13. 13p.
Subjects: Machine learning, Conduct disorders in adolescence, Gender differences (Sociology), Phonetics, Psychological distress, Teenagers
Abstract: Background: Current assessments of adolescent emotional and behavioral problems rely heavily on subjective reports, which are prone to biases. Aim: This study is the first to explore the potential of speech signals as objective markers for predicting emotional and behavioral problems (hyperactivity, emotional symptoms, conduct problems, and peer problems) in adolescents using machine learning techniques. Materials and Methods: We analyzed speech data from 8215 adolescents aged 12–18 years, extracting four categories of speech features: mel‐frequency cepstral coefficients (MFCC), mel energy spectrum (MELS), prosodic features (PROS), and formant features (FORM). Machine learning models—logistic regression (LR), support vector machine (SVM), and gradient boosting decision trees (GBDT)—were employed to classify hyperactivity, emotional symptoms, conduct problems, and peer problems as defined by the Strengths and Difficulties Questionnaire (SDQ). Model performance was assessed using area under the curve (AUC), F1‐score, and Shapley additive explanations (SHAP) values. Results: The GBDT model achieved the highest accuracy for predicting hyperactivity (AUC = 0.78) and emotional symptoms (AUC = 0.74 for males and 0.66 for females), while performance was weaker for conduct and peer problems. SHAP analysis revealed gender‐specific feature importance patterns, with certain speech features being more critical for males than females. Conclusion: These findings demonstrate the feasibility of using speech features to objectively predict emotional and behavioral problems in adolescents and identify gender‐specific markers. This study lays the foundation for developing speech‐based assessment tools for early identification and intervention, offering an objective alternative to traditional subjective evaluation methods. [ABSTRACT FROM AUTHOR]
Copyright of Depression & Anxiety (1091-4269) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Psychology and Behavioral Sciences Collection
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: pbh
DbLabel: Psychology and Behavioral Sciences Collection
An: 185963724
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Using Speech Features and Machine Learning Models to Predict Emotional and Behavioral Problems in Chinese Adolescents.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Li%2C+Jinyu%22">Li, Jinyu</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Yang%22">Wang, Yang</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Fei%22">Wang, Fei</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Ran%22">Zhang, Ran</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Ning%22">Wang, Ning</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhu%2C+Yue%22">Zhu, Yue</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhao%2C+Taihong%22">Zhao, Taihong</searchLink> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Ai%2C+Sizhi%22">Ai, Sizhi</searchLink> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Depression+%26+Anxiety+%281091-4269%29%22">Depression & Anxiety (1091-4269)</searchLink>. 6/16/2025, Vol. 2025, p1-13. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Conduct+disorders+in+adolescence%22">Conduct disorders in adolescence</searchLink><br /><searchLink fieldCode="DE" term="%22Gender+differences+%28Sociology%29%22">Gender differences (Sociology)</searchLink><br /><searchLink fieldCode="DE" term="%22Phonetics%22">Phonetics</searchLink><br /><searchLink fieldCode="DE" term="%22Psychological+distress%22">Psychological distress</searchLink><br /><searchLink fieldCode="DE" term="%22Teenagers%22">Teenagers</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Current assessments of adolescent emotional and behavioral problems rely heavily on subjective reports, which are prone to biases. Aim: This study is the first to explore the potential of speech signals as objective markers for predicting emotional and behavioral problems (hyperactivity, emotional symptoms, conduct problems, and peer problems) in adolescents using machine learning techniques. Materials and Methods: We analyzed speech data from 8215 adolescents aged 12–18 years, extracting four categories of speech features: mel‐frequency cepstral coefficients (MFCC), mel energy spectrum (MELS), prosodic features (PROS), and formant features (FORM). Machine learning models—logistic regression (LR), support vector machine (SVM), and gradient boosting decision trees (GBDT)—were employed to classify hyperactivity, emotional symptoms, conduct problems, and peer problems as defined by the Strengths and Difficulties Questionnaire (SDQ). Model performance was assessed using area under the curve (AUC), F1‐score, and Shapley additive explanations (SHAP) values. Results: The GBDT model achieved the highest accuracy for predicting hyperactivity (AUC = 0.78) and emotional symptoms (AUC = 0.74 for males and 0.66 for females), while performance was weaker for conduct and peer problems. SHAP analysis revealed gender‐specific feature importance patterns, with certain speech features being more critical for males than females. Conclusion: These findings demonstrate the feasibility of using speech features to objectively predict emotional and behavioral problems in adolescents and identify gender‐specific markers. This study lays the foundation for developing speech‐based assessment tools for early identification and intervention, offering an objective alternative to traditional subjective evaluation methods. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Depression & Anxiety (1091-4269) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=pbh&AN=185963724
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1155/da/5734107
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 1
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Conduct disorders in adolescence
        Type: general
      – SubjectFull: Gender differences (Sociology)
        Type: general
      – SubjectFull: Phonetics
        Type: general
      – SubjectFull: Psychological distress
        Type: general
      – SubjectFull: Teenagers
        Type: general
    Titles:
      – TitleFull: Using Speech Features and Machine Learning Models to Predict Emotional and Behavioral Problems in Chinese Adolescents.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Li, Jinyu
      – PersonEntity:
          Name:
            NameFull: Wang, Yang
      – PersonEntity:
          Name:
            NameFull: Wang, Fei
      – PersonEntity:
          Name:
            NameFull: Zhang, Ran
      – PersonEntity:
          Name:
            NameFull: Wang, Ning
      – PersonEntity:
          Name:
            NameFull: Zhu, Yue
      – PersonEntity:
          Name:
            NameFull: Zhao, Taihong
      – PersonEntity:
          Name:
            NameFull: Ai, Sizhi
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 16
              M: 06
              Text: 6/16/2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10914269
          Numbering:
            – Type: volume
              Value: 2025
          Titles:
            – TitleFull: Depression & Anxiety (1091-4269)
              Type: main
ResultId 1