Discovering action insights from large-scale assessment log data using machine learning

Abstract This study introduces a novel machine learning algorithm that combines natural language processing techniques, such as Word2Vec and Doc2Vec, with neural networks to identify and validate significant actions within human action sequences. Using the 2012 Program for the International Assessme...

Full description

Saved in:
Bibliographic Details
Main Authors: Minyoung Yun, Minjeong Jeon, Heyoung Yang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-14802-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849226269377429504
author Minyoung Yun
Minjeong Jeon
Heyoung Yang
author_facet Minyoung Yun
Minjeong Jeon
Heyoung Yang
author_sort Minyoung Yun
collection DOAJ
description Abstract This study introduces a novel machine learning algorithm that combines natural language processing techniques, such as Word2Vec and Doc2Vec, with neural networks to identify and validate significant actions within human action sequences. Using the 2012 Program for the International Assessment of Adult Competencies dataset, the algorithm visualizes and analyzes action sequences in a 2D vector space to uncover high-impact behaviors that influence performance. The methodology, validated across two problem sets (“Party Invitation” and “Club Membership”), successfully distinguishes performance groups by focusing on critical actions, leading to enhanced classification accuracy (up to 94.6%) and clustering coherence (silhouette score of 0.491). This approach demonstrates potential applications in personalized education, healthcare diagnostics, and consumer behavior prediction, advancing the understanding of human behavior through digital footprints.
format Article
id doaj-art-4a19e2acd24d4a3593afb2ecc43a93b4
institution Kabale University
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-4a19e2acd24d4a3593afb2ecc43a93b42025-08-24T11:26:43ZengNature PortfolioScientific Reports2045-23222025-08-0115111310.1038/s41598-025-14802-6Discovering action insights from large-scale assessment log data using machine learningMinyoung Yun0Minjeong Jeon1Heyoung Yang2Laboratory PIMM, Arts et Métieres Paris TechSchool of Education and Information Studies, University of CaliforniaCenter for Future Technology Analysis, Korea Institute of Science and Technology InformationAbstract This study introduces a novel machine learning algorithm that combines natural language processing techniques, such as Word2Vec and Doc2Vec, with neural networks to identify and validate significant actions within human action sequences. Using the 2012 Program for the International Assessment of Adult Competencies dataset, the algorithm visualizes and analyzes action sequences in a 2D vector space to uncover high-impact behaviors that influence performance. The methodology, validated across two problem sets (“Party Invitation” and “Club Membership”), successfully distinguishes performance groups by focusing on critical actions, leading to enhanced classification accuracy (up to 94.6%) and clustering coherence (silhouette score of 0.491). This approach demonstrates potential applications in personalized education, healthcare diagnostics, and consumer behavior prediction, advancing the understanding of human behavior through digital footprints.https://doi.org/10.1038/s41598-025-14802-6Human action sequenceMeaningful actionsMachine learningNatural language processingPIAAC log data
spellingShingle Minyoung Yun
Minjeong Jeon
Heyoung Yang
Discovering action insights from large-scale assessment log data using machine learning
Scientific Reports
Human action sequence
Meaningful actions
Machine learning
Natural language processing
PIAAC log data
title Discovering action insights from large-scale assessment log data using machine learning
title_full Discovering action insights from large-scale assessment log data using machine learning
title_fullStr Discovering action insights from large-scale assessment log data using machine learning
title_full_unstemmed Discovering action insights from large-scale assessment log data using machine learning
title_short Discovering action insights from large-scale assessment log data using machine learning
title_sort discovering action insights from large scale assessment log data using machine learning
topic Human action sequence
Meaningful actions
Machine learning
Natural language processing
PIAAC log data
url https://doi.org/10.1038/s41598-025-14802-6
work_keys_str_mv AT minyoungyun discoveringactioninsightsfromlargescaleassessmentlogdatausingmachinelearning
AT minjeongjeon discoveringactioninsightsfromlargescaleassessmentlogdatausingmachinelearning
AT heyoungyang discoveringactioninsightsfromlargescaleassessmentlogdatausingmachinelearning