A Machine Learning Approach to Relationships Among Alexithymia Components.

Area of Science:

• Psychology
• Network Science

Background:

• Alexithymia is a complex psychological construct.
• Understanding its internal structure is crucial for diagnosis and treatment.

Purpose of the Study:

• To explore the network structures of alexithymia components.
• To compare these structures with existing literature.

Main Methods:

• Utilized state-of-the-art network analysis and structure learning tools.
• Estimated undirected and directed network structures using the Bermond Vorst Alexithymia Questionnaire (BVAQ-B) in a large university student sample.
• Employed centrality estimates to identify item redundancy and key alexithymia components.

Main Results:

• Alexithymia components exhibit both positive and negative interconnections within the network.
• Poor fantasy and emotional insight were identified as central items, suggesting their significance in the alexithymia construct.
• Network analysis revealed novel features in the undirected structure compared to prior research.

Conclusions:

• The study presents new network structures for alexithymia components.
• Directed network analysis provides novel insights into the alexithymia construct.
• Findings contribute to a more nuanced understanding of alexithymia's internal organization.