Loading…

SEPN: A Sequential Engagement Based Academic Performance Prediction Model

Students’ performance prediction is a crucial task in today's online education. By predicting a student's final grade in an academic examination, intervene can be applied in advance. Recently, many machine learning models have been designed to couple students’ online activity with their ac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE intelligent systems 2021-01, Vol.36 (1), p.46-53
Main Authors: Song, Xiangyu, Li, Jianxin, Sun, Shijie, Yin, Hui, Dawson, Phillip, Doss, Robin Ram Mohan
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043
cites cdi_FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043
container_end_page 53
container_issue 1
container_start_page 46
container_title IEEE intelligent systems
container_volume 36
creator Song, Xiangyu
Li, Jianxin
Sun, Shijie
Yin, Hui
Dawson, Phillip
Doss, Robin Ram Mohan
description Students’ performance prediction is a crucial task in today's online education. By predicting a student's final grade in an academic examination, intervene can be applied in advance. Recently, many machine learning models have been designed to couple students’ online activity with their academic performance. However, it is difficult for these models to effectively make prediction due to the excessive difference in feature selection. While in most cases, too many parameters and heterogeneous features can also be one of the main sticking points. To this end, we propose a sequential engagement based academic performance prediction network. It consists of two main components: an engagement detector and a sequential predictor. The engagement detector leverages the advantages of a convolutional neural network to detect students’ engagement patterns through their daily activities. The sequential predictor adopts the structure of long short-term memory and learns the interaction from the engagement feature spaces and demographic features. By comparing with various existing advanced machine learning models, the results show that this method has better performance than the existing ones when involving the engagement detection mechanism.
doi_str_mv 10.1109/MIS.2020.3006961
format article
fullrecord <record><control><sourceid>proquest_ieee_</sourceid><recordid>TN_cdi_ieee_primary_9136846</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9136846</ieee_id><sourcerecordid>2503502099</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043</originalsourceid><addsrcrecordid>eNo9kMFLwzAUxoMoOKd3wUvAc-tL0qaNtzmmDjYdbPeQpi-jY21n0h38783Y8PS-B9_33sePkEcGKWOgXpbzdcqBQyoApJLsioyYyljCuMquo85PWhb8ltyFsAPgAlg5IvP1bPX1Sid0jT9H7IbG7Oms25ottnGjbyZgTSfW1Ng2lq7Qu963prNIVx7rxg5N39FlX-P-ntw4sw_4cJljsnmfbaafyeL7Yz6dLBLLFRsS6SQYLEWmqgIgr2rGJRMMBTfSOOe4KyrOSwfWVVCiKaosF5XIC2EUQCbG5Pl89uD72DgMetcffRc_ap6DyCMCpaILzi7r-xA8On3wTWv8r2agT7x05KVPvPSFV4w8nSMNIv7bFROyzKT4AwSRZHs</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2503502099</pqid></control><display><type>article</type><title>SEPN: A Sequential Engagement Based Academic Performance Prediction Model</title><source>Library &amp; Information Science Abstracts (LISA)</source><source>IEEE Xplore (Online service)</source><creator>Song, Xiangyu ; Li, Jianxin ; Sun, Shijie ; Yin, Hui ; Dawson, Phillip ; Doss, Robin Ram Mohan</creator><creatorcontrib>Song, Xiangyu ; Li, Jianxin ; Sun, Shijie ; Yin, Hui ; Dawson, Phillip ; Doss, Robin Ram Mohan</creatorcontrib><description>Students’ performance prediction is a crucial task in today's online education. By predicting a student's final grade in an academic examination, intervene can be applied in advance. Recently, many machine learning models have been designed to couple students’ online activity with their academic performance. However, it is difficult for these models to effectively make prediction due to the excessive difference in feature selection. While in most cases, too many parameters and heterogeneous features can also be one of the main sticking points. To this end, we propose a sequential engagement based academic performance prediction network. It consists of two main components: an engagement detector and a sequential predictor. The engagement detector leverages the advantages of a convolutional neural network to detect students’ engagement patterns through their daily activities. The sequential predictor adopts the structure of long short-term memory and learns the interaction from the engagement feature spaces and demographic features. By comparing with various existing advanced machine learning models, the results show that this method has better performance than the existing ones when involving the engagement detection mechanism.</description><identifier>ISSN: 1541-1672</identifier><identifier>EISSN: 1941-1294</identifier><identifier>DOI: 10.1109/MIS.2020.3006961</identifier><identifier>CODEN: IISYF7</identifier><language>eng</language><publisher>Los Alamitos: IEEE</publisher><subject>Academic achievement ; Adaptive and intelligent educational systems ; Artificial neural networks ; CAI ; Computer assisted instruction ; Data mining ; Feature extraction ; Feature selection ; Information technology ; Intelligent systems ; Learning systems ; Machine learning ; Online instruction ; Performance prediction ; Prediction models ; Predictive models ; Students ; Time series analysis</subject><ispartof>IEEE intelligent systems, 2021-01, Vol.36 (1), p.46-53</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043</citedby><cites>FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043</cites><orcidid>0000-0003-4043-8448 ; 0000-0002-9059-330X ; 0000-0002-5550-6354 ; 0000-0001-6143-6850 ; 0000-0002-1786-4951</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9136846$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,34135,54796</link.rule.ids></links><search><creatorcontrib>Song, Xiangyu</creatorcontrib><creatorcontrib>Li, Jianxin</creatorcontrib><creatorcontrib>Sun, Shijie</creatorcontrib><creatorcontrib>Yin, Hui</creatorcontrib><creatorcontrib>Dawson, Phillip</creatorcontrib><creatorcontrib>Doss, Robin Ram Mohan</creatorcontrib><title>SEPN: A Sequential Engagement Based Academic Performance Prediction Model</title><title>IEEE intelligent systems</title><addtitle>MIS</addtitle><description>Students’ performance prediction is a crucial task in today's online education. By predicting a student's final grade in an academic examination, intervene can be applied in advance. Recently, many machine learning models have been designed to couple students’ online activity with their academic performance. However, it is difficult for these models to effectively make prediction due to the excessive difference in feature selection. While in most cases, too many parameters and heterogeneous features can also be one of the main sticking points. To this end, we propose a sequential engagement based academic performance prediction network. It consists of two main components: an engagement detector and a sequential predictor. The engagement detector leverages the advantages of a convolutional neural network to detect students’ engagement patterns through their daily activities. The sequential predictor adopts the structure of long short-term memory and learns the interaction from the engagement feature spaces and demographic features. By comparing with various existing advanced machine learning models, the results show that this method has better performance than the existing ones when involving the engagement detection mechanism.</description><subject>Academic achievement</subject><subject>Adaptive and intelligent educational systems</subject><subject>Artificial neural networks</subject><subject>CAI</subject><subject>Computer assisted instruction</subject><subject>Data mining</subject><subject>Feature extraction</subject><subject>Feature selection</subject><subject>Information technology</subject><subject>Intelligent systems</subject><subject>Learning systems</subject><subject>Machine learning</subject><subject>Online instruction</subject><subject>Performance prediction</subject><subject>Prediction models</subject><subject>Predictive models</subject><subject>Students</subject><subject>Time series analysis</subject><issn>1541-1672</issn><issn>1941-1294</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>F2A</sourceid><recordid>eNo9kMFLwzAUxoMoOKd3wUvAc-tL0qaNtzmmDjYdbPeQpi-jY21n0h38783Y8PS-B9_33sePkEcGKWOgXpbzdcqBQyoApJLsioyYyljCuMquo85PWhb8ltyFsAPgAlg5IvP1bPX1Sid0jT9H7IbG7Oms25ottnGjbyZgTSfW1Ng2lq7Qu963prNIVx7rxg5N39FlX-P-ntw4sw_4cJljsnmfbaafyeL7Yz6dLBLLFRsS6SQYLEWmqgIgr2rGJRMMBTfSOOe4KyrOSwfWVVCiKaosF5XIC2EUQCbG5Pl89uD72DgMetcffRc_ap6DyCMCpaILzi7r-xA8On3wTWv8r2agT7x05KVPvPSFV4w8nSMNIv7bFROyzKT4AwSRZHs</recordid><startdate>202101</startdate><enddate>202101</enddate><creator>Song, Xiangyu</creator><creator>Li, Jianxin</creator><creator>Sun, Shijie</creator><creator>Yin, Hui</creator><creator>Dawson, Phillip</creator><creator>Doss, Robin Ram Mohan</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>E3H</scope><scope>F2A</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0003-4043-8448</orcidid><orcidid>https://orcid.org/0000-0002-9059-330X</orcidid><orcidid>https://orcid.org/0000-0002-5550-6354</orcidid><orcidid>https://orcid.org/0000-0001-6143-6850</orcidid><orcidid>https://orcid.org/0000-0002-1786-4951</orcidid></search><sort><creationdate>202101</creationdate><title>SEPN: A Sequential Engagement Based Academic Performance Prediction Model</title><author>Song, Xiangyu ; Li, Jianxin ; Sun, Shijie ; Yin, Hui ; Dawson, Phillip ; Doss, Robin Ram Mohan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Academic achievement</topic><topic>Adaptive and intelligent educational systems</topic><topic>Artificial neural networks</topic><topic>CAI</topic><topic>Computer assisted instruction</topic><topic>Data mining</topic><topic>Feature extraction</topic><topic>Feature selection</topic><topic>Information technology</topic><topic>Intelligent systems</topic><topic>Learning systems</topic><topic>Machine learning</topic><topic>Online instruction</topic><topic>Performance prediction</topic><topic>Prediction models</topic><topic>Predictive models</topic><topic>Students</topic><topic>Time series analysis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Song, Xiangyu</creatorcontrib><creatorcontrib>Li, Jianxin</creatorcontrib><creatorcontrib>Sun, Shijie</creatorcontrib><creatorcontrib>Yin, Hui</creatorcontrib><creatorcontrib>Dawson, Phillip</creatorcontrib><creatorcontrib>Doss, Robin Ram Mohan</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library Online</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Library &amp; Information Sciences Abstracts (LISA)</collection><collection>Library &amp; Information Science Abstracts (LISA)</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE intelligent systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Song, Xiangyu</au><au>Li, Jianxin</au><au>Sun, Shijie</au><au>Yin, Hui</au><au>Dawson, Phillip</au><au>Doss, Robin Ram Mohan</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SEPN: A Sequential Engagement Based Academic Performance Prediction Model</atitle><jtitle>IEEE intelligent systems</jtitle><stitle>MIS</stitle><date>2021-01</date><risdate>2021</risdate><volume>36</volume><issue>1</issue><spage>46</spage><epage>53</epage><pages>46-53</pages><issn>1541-1672</issn><eissn>1941-1294</eissn><coden>IISYF7</coden><abstract>Students’ performance prediction is a crucial task in today's online education. By predicting a student's final grade in an academic examination, intervene can be applied in advance. Recently, many machine learning models have been designed to couple students’ online activity with their academic performance. However, it is difficult for these models to effectively make prediction due to the excessive difference in feature selection. While in most cases, too many parameters and heterogeneous features can also be one of the main sticking points. To this end, we propose a sequential engagement based academic performance prediction network. It consists of two main components: an engagement detector and a sequential predictor. The engagement detector leverages the advantages of a convolutional neural network to detect students’ engagement patterns through their daily activities. The sequential predictor adopts the structure of long short-term memory and learns the interaction from the engagement feature spaces and demographic features. By comparing with various existing advanced machine learning models, the results show that this method has better performance than the existing ones when involving the engagement detection mechanism.</abstract><cop>Los Alamitos</cop><pub>IEEE</pub><doi>10.1109/MIS.2020.3006961</doi><tpages>8</tpages><orcidid>https://orcid.org/0000-0003-4043-8448</orcidid><orcidid>https://orcid.org/0000-0002-9059-330X</orcidid><orcidid>https://orcid.org/0000-0002-5550-6354</orcidid><orcidid>https://orcid.org/0000-0001-6143-6850</orcidid><orcidid>https://orcid.org/0000-0002-1786-4951</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1541-1672
ispartof IEEE intelligent systems, 2021-01, Vol.36 (1), p.46-53
issn 1541-1672
1941-1294
language eng
recordid cdi_ieee_primary_9136846
source Library & Information Science Abstracts (LISA); IEEE Xplore (Online service)
subjects Academic achievement
Adaptive and intelligent educational systems
Artificial neural networks
CAI
Computer assisted instruction
Data mining
Feature extraction
Feature selection
Information technology
Intelligent systems
Learning systems
Machine learning
Online instruction
Performance prediction
Prediction models
Predictive models
Students
Time series analysis
title SEPN: A Sequential Engagement Based Academic Performance Prediction Model
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A43%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_ieee_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SEPN:%20A%20Sequential%20Engagement%20Based%20Academic%20Performance%20Prediction%20Model&rft.jtitle=IEEE%20intelligent%20systems&rft.au=Song,%20Xiangyu&rft.date=2021-01&rft.volume=36&rft.issue=1&rft.spage=46&rft.epage=53&rft.pages=46-53&rft.issn=1541-1672&rft.eissn=1941-1294&rft.coden=IISYF7&rft_id=info:doi/10.1109/MIS.2020.3006961&rft_dat=%3Cproquest_ieee_%3E2503502099%3C/proquest_ieee_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c291t-6f60ae8349b7005bd126131e32a6afff2f7b228f0cfb08ea7b453b3573a90043%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2503502099&rft_id=info:pmid/&rft_ieee_id=9136846&rfr_iscdi=true