Incremental Knowledge Tracing from Multiple Schools

Incremental Knowledge Tracing from Multiple Schools

Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Suresh, Sujanya, Ramasamy, Savitha, Suganthan, P. N, Wong, Cheryl Sze Yin
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computers and Society
Computer Science - Learning
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Suresh, Sujanya
Ramasamy, Savitha
Suganthan, P. N
Wong, Cheryl Sze Yin
description Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner's data from all schools, due to data privacy and PDPA policies. Hence, this paper explores the feasibility of building knowledge tracing models while preserving the privacy of learners' data within their respective schools. This study is conducted using part of the ASSISTment 2009 dataset, with data from multiple schools being treated as separate tasks in a continual learning framework. The results show that learning sequentially with the Self Attentive Knowledge Tracing (SAKT) algorithm is able to achieve considerably similar performance to that of pooling all the data together.
doi_str_mv 10.48550/arxiv.2201.06941
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2201_06941</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2201_06941</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-b6a32d31667b1b3f5caebeb4a33b28c84dacdbd92b5263859b709f4d66a5fd863</originalsourceid><addsrcrecordid>eNotzrtOwzAUgGEvDKjwAEz4BZLaPrbjjKgqULWIgezROb6USE5SueX29qiF6d9-fYzdSVFrZ4xYYvkePmulhKyFbbW8ZrCZfIljnE6Y-Xaav3IM-8i7gn6Y9jyVeeQvH_k0HHLkb_59nvPxhl0lzMd4-98F6x7X3eq52r0-bVYPuwptIyuyCCqAtLYhSZCMx0iRNAKQct7pgD5QaBUZZcGZlhrRJh2sRZOCs7Bg93_bi7o_lGHE8tOf9f1FD79afz-_</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Incremental Knowledge Tracing from Multiple Schools</title><source>arXiv.org</source><creator>Suresh, Sujanya ; Ramasamy, Savitha ; Suganthan, P. N ; Wong, Cheryl Sze Yin</creator><creatorcontrib>Suresh, Sujanya ; Ramasamy, Savitha ; Suganthan, P. N ; Wong, Cheryl Sze Yin</creatorcontrib><description>Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner's data from all schools, due to data privacy and PDPA policies. Hence, this paper explores the feasibility of building knowledge tracing models while preserving the privacy of learners' data within their respective schools. This study is conducted using part of the ASSISTment 2009 dataset, with data from multiple schools being treated as separate tasks in a continual learning framework. The results show that learning sequentially with the Self Attentive Knowledge Tracing (SAKT) algorithm is able to achieve considerably similar performance to that of pooling all the data together.</description><identifier>DOI: 10.48550/arxiv.2201.06941</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computers and Society ; Computer Science - Learning</subject><creationdate>2022-01</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2201.06941$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2201.06941$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Suresh, Sujanya</creatorcontrib><creatorcontrib>Ramasamy, Savitha</creatorcontrib><creatorcontrib>Suganthan, P. N</creatorcontrib><creatorcontrib>Wong, Cheryl Sze Yin</creatorcontrib><title>Incremental Knowledge Tracing from Multiple Schools</title><description>Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner's data from all schools, due to data privacy and PDPA policies. Hence, this paper explores the feasibility of building knowledge tracing models while preserving the privacy of learners' data within their respective schools. This study is conducted using part of the ASSISTment 2009 dataset, with data from multiple schools being treated as separate tasks in a continual learning framework. The results show that learning sequentially with the Self Attentive Knowledge Tracing (SAKT) algorithm is able to achieve considerably similar performance to that of pooling all the data together.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computers and Society</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotzrtOwzAUgGEvDKjwAEz4BZLaPrbjjKgqULWIgezROb6USE5SueX29qiF6d9-fYzdSVFrZ4xYYvkePmulhKyFbbW8ZrCZfIljnE6Y-Xaav3IM-8i7gn6Y9jyVeeQvH_k0HHLkb_59nvPxhl0lzMd4-98F6x7X3eq52r0-bVYPuwptIyuyCCqAtLYhSZCMx0iRNAKQct7pgD5QaBUZZcGZlhrRJh2sRZOCs7Bg93_bi7o_lGHE8tOf9f1FD79afz-_</recordid><startdate>20220107</startdate><enddate>20220107</enddate><creator>Suresh, Sujanya</creator><creator>Ramasamy, Savitha</creator><creator>Suganthan, P. N</creator><creator>Wong, Cheryl Sze Yin</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20220107</creationdate><title>Incremental Knowledge Tracing from Multiple Schools</title><author>Suresh, Sujanya ; Ramasamy, Savitha ; Suganthan, P. N ; Wong, Cheryl Sze Yin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-b6a32d31667b1b3f5caebeb4a33b28c84dacdbd92b5263859b709f4d66a5fd863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computers and Society</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Suresh, Sujanya</creatorcontrib><creatorcontrib>Ramasamy, Savitha</creatorcontrib><creatorcontrib>Suganthan, P. N</creatorcontrib><creatorcontrib>Wong, Cheryl Sze Yin</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Suresh, Sujanya</au><au>Ramasamy, Savitha</au><au>Suganthan, P. N</au><au>Wong, Cheryl Sze Yin</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Incremental Knowledge Tracing from Multiple Schools</atitle><date>2022-01-07</date><risdate>2022</risdate><abstract>Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple schools. However, it is impossible to pool learner's data from all schools, due to data privacy and PDPA policies. Hence, this paper explores the feasibility of building knowledge tracing models while preserving the privacy of learners' data within their respective schools. This study is conducted using part of the ASSISTment 2009 dataset, with data from multiple schools being treated as separate tasks in a continual learning framework. The results show that learning sequentially with the Self Attentive Knowledge Tracing (SAKT) algorithm is able to achieve considerably similar performance to that of pooling all the data together.</abstract><doi>10.48550/arxiv.2201.06941</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2201.06941
ispartof
issn
language eng
recordid cdi_arxiv_primary_2201_06941
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computers and Society
Computer Science - Learning
title Incremental Knowledge Tracing from Multiple Schools
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T07%3A00%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Incremental%20Knowledge%20Tracing%20from%20Multiple%20Schools&rft.au=Suresh,%20Sujanya&rft.date=2022-01-07&rft_id=info:doi/10.48550/arxiv.2201.06941&rft_dat=%3Carxiv_GOX%3E2201_06941%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true