Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering
IntroductionUnderstanding individual cognitive profiles is crucial for developing personalized educational interventions, as cognitive differences can significantly impact how students learn. While traditional methods like factor mixture modeling (FMM) have proven robust for identifying latent cogni...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-05-01
|
| Series: | Frontiers in Psychology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1474292/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849324094491721728 |
|---|---|
| author | Matteo Orsoni Sara Giovagnoli Sara Garofalo Noemi Mazzoni Matilde Spinoso Mariagrazia Benassi |
| author_facet | Matteo Orsoni Sara Giovagnoli Sara Garofalo Noemi Mazzoni Matilde Spinoso Mariagrazia Benassi |
| author_sort | Matteo Orsoni |
| collection | DOAJ |
| description | IntroductionUnderstanding individual cognitive profiles is crucial for developing personalized educational interventions, as cognitive differences can significantly impact how students learn. While traditional methods like factor mixture modeling (FMM) have proven robust for identifying latent cognitive structures, recent advancements in deep learning may offer the potential to capture more intricate and complex cognitive patterns.MethodsThis study compares FMM (specifically, FMM-1 and FMM-2 models using age as a covariate) with a Conditional Gaussian Mixture Variational Autoencoder (CGMVAE). The comparison utilizes six cognitive dimensions obtained from the PROFFILO assessment game.ResultsThe FMM-1 model, identified as the superior FMM solution, yielded two well-separated clusters (Silhouette score = 0.959). These clusters represent distinct average cognitive levels, with age significantly predicting class membership. In contrast, the CGMVAE identified ten more nuanced cognitive profiles, exhibiting clear developmental trajectories across different age groups. Notably, one dominant cluster (Cluster 9) showed an increase in representation from 44 to 54% with advancing age, indicating a normative developmental pattern. Other clusters displayed diverse profiles, ranging from subtle domain-specific strengths to atypical profiles characterized by significant deficits balanced by compensatory abilities.DiscussionThese findings highlight a trade-off between the methodologies. FMM provides clear, interpretable groupings suitable for broad classification purposes. Conversely, CGMVAE reveals subtle, non-linear variations in cognitive profiles, potentially reflecting complex developmental pathways. Despite practical challenges associated with CGMVAE's complexity and potential cluster overlap, its capacity to uncover nuanced cognitive patterns demonstrates significant promise for informing the development of highly tailored educational strategies. |
| format | Article |
| id | doaj-art-e53178e3718c439284f2a682ea4d1941 |
| institution | Kabale University |
| issn | 1664-1078 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychology |
| spelling | doaj-art-e53178e3718c439284f2a682ea4d19412025-08-20T03:48:47ZengFrontiers Media S.A.Frontiers in Psychology1664-10782025-05-011610.3389/fpsyg.2025.14742921474292Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clusteringMatteo OrsoniSara GiovagnoliSara GarofaloNoemi MazzoniMatilde SpinosoMariagrazia BenassiIntroductionUnderstanding individual cognitive profiles is crucial for developing personalized educational interventions, as cognitive differences can significantly impact how students learn. While traditional methods like factor mixture modeling (FMM) have proven robust for identifying latent cognitive structures, recent advancements in deep learning may offer the potential to capture more intricate and complex cognitive patterns.MethodsThis study compares FMM (specifically, FMM-1 and FMM-2 models using age as a covariate) with a Conditional Gaussian Mixture Variational Autoencoder (CGMVAE). The comparison utilizes six cognitive dimensions obtained from the PROFFILO assessment game.ResultsThe FMM-1 model, identified as the superior FMM solution, yielded two well-separated clusters (Silhouette score = 0.959). These clusters represent distinct average cognitive levels, with age significantly predicting class membership. In contrast, the CGMVAE identified ten more nuanced cognitive profiles, exhibiting clear developmental trajectories across different age groups. Notably, one dominant cluster (Cluster 9) showed an increase in representation from 44 to 54% with advancing age, indicating a normative developmental pattern. Other clusters displayed diverse profiles, ranging from subtle domain-specific strengths to atypical profiles characterized by significant deficits balanced by compensatory abilities.DiscussionThese findings highlight a trade-off between the methodologies. FMM provides clear, interpretable groupings suitable for broad classification purposes. Conversely, CGMVAE reveals subtle, non-linear variations in cognitive profiles, potentially reflecting complex developmental pathways. Despite practical challenges associated with CGMVAE's complexity and potential cluster overlap, its capacity to uncover nuanced cognitive patterns demonstrates significant promise for informing the development of highly tailored educational strategies.https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1474292/fullvariational autoencodersclusteringmachine learningcognitive profilesfactor mixture modeling |
| spellingShingle | Matteo Orsoni Sara Giovagnoli Sara Garofalo Noemi Mazzoni Matilde Spinoso Mariagrazia Benassi Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering Frontiers in Psychology variational autoencoders clustering machine learning cognitive profiles factor mixture modeling |
| title | Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering |
| title_full | Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering |
| title_fullStr | Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering |
| title_full_unstemmed | Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering |
| title_short | Comparing factor mixture modeling and conditional Gaussian mixture variational autoencoders for cognitive profile clustering |
| title_sort | comparing factor mixture modeling and conditional gaussian mixture variational autoencoders for cognitive profile clustering |
| topic | variational autoencoders clustering machine learning cognitive profiles factor mixture modeling |
| url | https://www.frontiersin.org/articles/10.3389/fpsyg.2025.1474292/full |
| work_keys_str_mv | AT matteoorsoni comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering AT saragiovagnoli comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering AT saragarofalo comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering AT noemimazzoni comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering AT matildespinoso comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering AT mariagraziabenassi comparingfactormixturemodelingandconditionalgaussianmixturevariationalautoencodersforcognitiveprofileclustering |