Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection

Effective detection and identification of disruptive talk is of significant practical value for improving collaborative learning quality and optimizing the online education environment. However, existing research on disruptive talk detection, which often relies on features from a single dimension, s...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuang Yu, Junmin Ye, Chen Zhang, Qingtang Liu, Sheng Luo, Mengting Nan, Qi Xu, Xinghan Yin
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10945836/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185119500861440
author Shuang Yu
Junmin Ye
Chen Zhang
Qingtang Liu
Sheng Luo
Mengting Nan
Qi Xu
Xinghan Yin
author_facet Shuang Yu
Junmin Ye
Chen Zhang
Qingtang Liu
Sheng Luo
Mengting Nan
Qi Xu
Xinghan Yin
author_sort Shuang Yu
collection DOAJ
description Effective detection and identification of disruptive talk is of significant practical value for improving collaborative learning quality and optimizing the online education environment. However, existing research on disruptive talk detection, which often relies on features from a single dimension, struggles to comprehensively capture the semantic information of talk and learner characteristics, thereby limiting the detection effectiveness. To address this, we propose a multi-feature fusion model. Based on social cognitive theory, this model captures learner features from multiple dimensions, including the week of discussion, talk length, sentiment polarity of talk, the learner’s demographic factor and pre-test knowledge level. The model integrates both Bidirectional Encoder Representations from Transformers (BERT) and Bidirectional Long Short-Term Memory (Bi-LSTM) models. This integration achieves deep fusion of talk semantics and time-series features, thereby enabling more accurate identification of disruptive talk. Experimental results on real classroom datasets show that our method outperforms existing baseline models across multiple metrics, fully demonstrating its effectiveness and practical value. This research not only advances the development of disruptive talk detection but also provides feasible insights for optimizing collaborative learning environments. Future work will explore the scalability of this model in different educational settings, and investigate its integration with real-time learning platforms.
format Article
id doaj-art-cd7d1c3a5dd740be963cb4209e76c415
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-cd7d1c3a5dd740be963cb4209e76c4152025-08-20T02:16:49ZengIEEEIEEE Access2169-35362025-01-0113612616127310.1109/ACCESS.2025.355636910945836Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk DetectionShuang Yu0https://orcid.org/0009-0007-5780-6389Junmin Ye1Chen Zhang2https://orcid.org/0000-0002-4357-4560Qingtang Liu3https://orcid.org/0000-0001-9410-9856Sheng Luo4Mengting Nan5Qi Xu6Xinghan Yin7Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, Hubei, ChinaSchool of Computer, Central China Normal University, Wuhan, Hubei, ChinaFinancial Office, Central China Normal University, Wuhan, Hubei, ChinaHubei Research Center for Educational Informationization, Central China Normal University, Wuhan, ChinaSchool of Computer, Central China Normal University, Wuhan, Hubei, ChinaSchool of Computer, Central China Normal University, Wuhan, Hubei, ChinaFaculty of Artificial Intelligence in Education, Central China Normal University, Wuhan, Hubei, ChinaSchool of Computer, Central China Normal University, Wuhan, Hubei, ChinaEffective detection and identification of disruptive talk is of significant practical value for improving collaborative learning quality and optimizing the online education environment. However, existing research on disruptive talk detection, which often relies on features from a single dimension, struggles to comprehensively capture the semantic information of talk and learner characteristics, thereby limiting the detection effectiveness. To address this, we propose a multi-feature fusion model. Based on social cognitive theory, this model captures learner features from multiple dimensions, including the week of discussion, talk length, sentiment polarity of talk, the learner’s demographic factor and pre-test knowledge level. The model integrates both Bidirectional Encoder Representations from Transformers (BERT) and Bidirectional Long Short-Term Memory (Bi-LSTM) models. This integration achieves deep fusion of talk semantics and time-series features, thereby enabling more accurate identification of disruptive talk. Experimental results on real classroom datasets show that our method outperforms existing baseline models across multiple metrics, fully demonstrating its effectiveness and practical value. This research not only advances the development of disruptive talk detection but also provides feasible insights for optimizing collaborative learning environments. Future work will explore the scalability of this model in different educational settings, and investigate its integration with real-time learning platforms.https://ieeexplore.ieee.org/document/10945836/Disruptive talk detectionmulti-feature fusioncollaborative dialogueeducational technology
spellingShingle Shuang Yu
Junmin Ye
Chen Zhang
Qingtang Liu
Sheng Luo
Mengting Nan
Qi Xu
Xinghan Yin
Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
IEEE Access
Disruptive talk detection
multi-feature fusion
collaborative dialogue
educational technology
title Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
title_full Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
title_fullStr Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
title_full_unstemmed Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
title_short Enhancing Collaborative Learning Environments: A Multi-Feature Fusion Model for Disruptive Talk Detection
title_sort enhancing collaborative learning environments a multi feature fusion model for disruptive talk detection
topic Disruptive talk detection
multi-feature fusion
collaborative dialogue
educational technology
url https://ieeexplore.ieee.org/document/10945836/
work_keys_str_mv AT shuangyu enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT junminye enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT chenzhang enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT qingtangliu enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT shengluo enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT mengtingnan enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT qixu enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection
AT xinghanyin enhancingcollaborativelearningenvironmentsamultifeaturefusionmodelfordisruptivetalkdetection