{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/107881"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/107881","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Data-driven adaptive learning systems","abstract":"\"Adaptive learning systems are capable of providing more adaptive and efficient assessment and learning experiences for learners than traditional classroom settings. A conventional adaptive learning system involves a learner, a latent trait estimator, and a learning strategy/plan. The latent trait estimator measures the learner's latent traits from his/her responses to the test, where computerized adaptive testing (CAT) or computerized classification testing (CCT) tailors test items to learners' abilities so as to give a more efficient latent trait estimation. On the other hand, the learning plan (called policy) is another key component of such systems. It is the algorithm that designs the learning paths, or in other words, selects learning materials for learners based on the information such as the learners' current progresses and skills, learning material contents. In this thesis, we discuss and address issues related to the adaptive test and learning problems using data-driven methods. In the first chapter, we discuss the challenge of content balancing in variable-length adaptive tests and propose feasible data-driven methods. Content balancing is one of the most important issues in CCT. To adapt to variable-length forms, special treatments are needed to successfully control content constraints without knowledge of the test length during the test. To this end, we propose the concept of \"\"look ahead\"\" and \"\"step size\"\" to adaptively control content constraints in each item selection step. The step size gives a prediction of the number of items to be selected at the current stage, that is, how far we will look ahead. Two look-ahead content balancing (LA-CB) methods, one with a constant step size and another with an adaptive step size, are proposed as feasible solutions to balancing content areas in variable-length computerized classification testing (VL-CCT). The proposed LA-CB methods are compared with conventional item selection methods in variable-length tests under different classification methods' settings. Simulation results show that integrated with heuristic item selection methods, the proposed LA-CB methods outperform the conventional item selection methods with fewer constraint violations and higher classification accuracy. The second issue we address is to find the learning policy that designs the optimal learning path in an adaptive learning system under hierarchical skill structures. To this end, we first develop a model for learners' hierarchical skills in the adaptive learning system. Based on the hierarchical skill model and the classical cognitive diagnosis model, we further develop a framework to model various levels of proficiency related to hierarchical skills. The optimal learning policy in consideration of the hierarchical structure of skills is found by applying a data-driven algorithm-reinforcement learning method, which does not require information about learners' learning transition processes. The effectiveness of the proposed framework is demonstrated via simulation studies. Lastly, we solve the problem of finding a learning policy assuming latent traits to be continuous with an unknown transition model. We formulate the adaptive learning problem as a Markov decision process (MDP). We apply a model-free deep reinforcement learning algorithm---the deep Q-learning algorithm---that is data-driven and can effectively find the optimal learning policy from data on learners' learning process without knowing the actual transition model of the learner's continuous latent traits. To efficiently utilize available data, we further develop a transition model estimator that emulates the learner's learning process using neural networks. The transition model estimator can be used in the deep Q-learning algorithm so that it can more efficiently discover the optimal learning policy for a learner. Numerical simulation studies verify that the proposed algorithm is very efficient in finding a good learning policy, especially with the aid of a transition model estimator, it can find the optimal learning policy after training using a small number of learners.\"","abstract_html":""Adaptive learning systems are capable of providing more adaptive and efficient assessment and learning experiences for learners than traditional classroom settings. A conventional adaptive learning system involves a learner, a latent trait estimator, and a learning strategy/plan. The latent trait estimator measures the learner's latent traits from his/her responses to the test, where computerized adaptive testing (CAT) or computerized classification testing (CCT) tailors test items to learners' abilities so as to give a more efficient latent trait estimation. On the other hand, the learning plan (called policy) is another key component of such systems. It is the algorithm that designs the learning paths, or in other words, selects learning materials for learners based on the information such as the learners' current progresses and skills, learning material contents. In this thesis, we discuss and address issues related to the adaptive test and learning problems using data-driven methods. In the first chapter, we discuss the challenge of content balancing in variable-length adaptive tests and propose feasible data-driven methods. Content balancing is one of the most important issues in CCT. To adapt to variable-length forms, special treatments are needed to successfully control content constraints without knowledge of the test length during the test. To this end, we propose the concept of ""look ahead"" and ""step size"" to adaptively control content constraints in each item selection step. The step size gives a prediction of the number of items to be selected at the current stage, that is, how far we will look ahead. Two look-ahead content balancing (LA-CB) methods, one with a constant step size and another with an adaptive step size, are proposed as feasible solutions to balancing content areas in variable-length computerized classification testing (VL-CCT). The proposed LA-CB methods are compared with conventional item selection methods in variable-length tests under different classification methods' settings. Simulation results show that integrated with heuristic item selection methods, the proposed LA-CB methods outperform the conventional item selection methods with fewer constraint violations and higher classification accuracy. The second issue we address is to find the learning policy that designs the optimal learning path in an adaptive learning system under hierarchical skill structures. To this end, we first develop a model for learners' hierarchical skills in the adaptive learning system. Based on the hierarchical skill model and the classical cognitive diagnosis model, we further develop a framework to model various levels of proficiency related to hierarchical skills. The optimal learning policy in consideration of the hierarchical structure of skills is found by applying a data-driven algorithm-reinforcement learning method, which does not require information about learners' learning transition processes. The effectiveness of the proposed framework is demonstrated via simulation studies. Lastly, we solve the problem of finding a learning policy assuming latent traits to be continuous with an unknown transition model. We formulate the adaptive learning problem as a Markov decision process (MDP). We apply a model-free deep reinforcement learning algorithm---the deep Q-learning algorithm---that is data-driven and can effectively find the optimal learning policy from data on learners' learning process without knowing the actual transition model of the learner's continuous latent traits. To efficiently utilize available data, we further develop a transition model estimator that emulates the learner's learning process using neural networks. The transition model estimator can be used in the deep Q-learning algorithm so that it can more efficiently discover the optimal learning policy for a learner. Numerical simulation studies verify that the proposed algorithm is very efficient in finding a good learning policy, especially with the aid of a transition model estimator, it can find the optimal learning policy after training using a small number of learners."","abstract_has_math":false,"creators":["Li, Xiao"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Educational Psychology","degree_department":null,"school":null,"contributors":["Zhang, Jinming","Chang, Hua-hua","Anderson, Carolyn Jane","Kern, Justin Louis"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-26T21:54:19Z","date_published":"2020-08-26T21:54:19Z","updated_at":"2026-07-22T22:24:47Z","subjects":["Adaptive learning system","Data-driven"],"languages":["en"],"rights":["Copyright 2020 Xiao Li"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/107881","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Zhang, Jinming","Chang, Hua-hua","Anderson, Carolyn Jane","Kern, Justin Louis"]},{"key":"dc:creator","label":"Author","values":["Li, Xiao"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-26T21:54:19Z","2020-04-14","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Educational Psychology"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Adaptive learning system","Data-driven"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Xiao Li"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/107881"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["\"Adaptive learning systems are capable of providing more adaptive and efficient assessment and learning experiences for learners than traditional classroom settings. A conventional adaptive learning system involves a learner, a latent trait estimator, and a learning strategy/plan. The latent trait estimator measures the learner's latent traits from his/her responses to the test, where computerized adaptive testing (CAT) or computerized classification testing (CCT) tailors test items to learners' abilities so as to give a more efficient latent trait estimation. On the other hand, the learning plan (called policy) is another key component of such systems. It is the algorithm that designs the learning paths, or in other words, selects learning materials for learners based on the information such as the learners' current progresses and skills, learning material contents. In this thesis, we discuss and address issues related to the adaptive test and learning problems using data-driven methods. In the first chapter, we discuss the challenge of content balancing in variable-length adaptive tests and propose feasible data-driven methods. Content balancing is one of the most important issues in CCT. To adapt to variable-length forms, special treatments are needed to successfully control content constraints without knowledge of the test length during the test. To this end, we propose the concept of \"\"look ahead\"\" and \"\"step size\"\" to adaptively control content constraints in each item selection step. The step size gives a prediction of the number of items to be selected at the current stage, that is, how far we will look ahead. Two look-ahead content balancing (LA-CB) methods, one with a constant step size and another with an adaptive step size, are proposed as feasible solutions to balancing content areas in variable-length computerized classification testing (VL-CCT). The proposed LA-CB methods are compared with conventional item selection methods in variable-length tests under different classification methods' settings. Simulation results show that integrated with heuristic item selection methods, the proposed LA-CB methods outperform the conventional item selection methods with fewer constraint violations and higher classification accuracy. The second issue we address is to find the learning policy that designs the optimal learning path in an adaptive learning system under hierarchical skill structures. To this end, we first develop a model for learners' hierarchical skills in the adaptive learning system. Based on the hierarchical skill model and the classical cognitive diagnosis model, we further develop a framework to model various levels of proficiency related to hierarchical skills. The optimal learning policy in consideration of the hierarchical structure of skills is found by applying a data-driven algorithm-reinforcement learning method, which does not require information about learners' learning transition processes. The effectiveness of the proposed framework is demonstrated via simulation studies. Lastly, we solve the problem of finding a learning policy assuming latent traits to be continuous with an unknown transition model. We formulate the adaptive learning problem as a Markov decision process (MDP). We apply a model-free deep reinforcement learning algorithm---the deep Q-learning algorithm---that is data-driven and can effectively find the optimal learning policy from data on learners' learning process without knowing the actual transition model of the learner's continuous latent traits. To efficiently utilize available data, we further develop a transition model estimator that emulates the learner's learning process using neural networks. The transition model estimator can be used in the deep Q-learning algorithm so that it can more efficiently discover the optimal learning policy for a learner. Numerical simulation studies verify that the proposed algorithm is very efficient in finding a good learning policy, especially with the aid of a transition model estimator, it can find the optimal learning policy after training using a small number of learners.\"","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Xiao Li, accepted the attached license on 2020-04-13 at 16:37.","The student, Xiao Li, submitted this Dissertation for approval on 2020-04-13 at 16:47.","This Dissertation was approved for publication on 2020-04-14 at 17:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14972 on 2020-08-25 at 17:06:51","Made available in DSpace on 2020-08-26T21:54:19Z (GMT). No. of bitstreams: 2 LI-DISSERTATION-2020.pdf: 937515 bytes, checksum: 2ccb92e2b202a70444dedba19b3b0e60 (MD5) LICENSE.txt: 4204 bytes, checksum: a474e3fecf0aad382d38b1383f79031a (MD5) Previous issue date: 2020-04-14"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Data-driven adaptive learning systems"]}]}],"canonical_facts":{"dc:contributor":["Zhang, Jinming","Chang, Hua-hua","Anderson, Carolyn Jane","Kern, Justin Louis"],"dc:creator":["Li, Xiao"],"dc:date":["2020-08-26T21:54:19Z","2020-04-14","2020-05"],"dc:description":["\"Adaptive learning systems are capable of providing more adaptive and efficient assessment and learning experiences for learners than traditional classroom settings. A conventional adaptive learning system involves a learner, a latent trait estimator, and a learning strategy/plan. The latent trait estimator measures the learner's latent traits from his/her responses to the test, where computerized adaptive testing (CAT) or computerized classification testing (CCT) tailors test items to learners' abilities so as to give a more efficient latent trait estimation. On the other hand, the learning plan (called policy) is another key component of such systems. It is the algorithm that designs the learning paths, or in other words, selects learning materials for learners based on the information such as the learners' current progresses and skills, learning material contents. In this thesis, we discuss and address issues related to the adaptive test and learning problems using data-driven methods. In the first chapter, we discuss the challenge of content balancing in variable-length adaptive tests and propose feasible data-driven methods. Content balancing is one of the most important issues in CCT. To adapt to variable-length forms, special treatments are needed to successfully control content constraints without knowledge of the test length during the test. To this end, we propose the concept of \"\"look ahead\"\" and \"\"step size\"\" to adaptively control content constraints in each item selection step. The step size gives a prediction of the number of items to be selected at the current stage, that is, how far we will look ahead. Two look-ahead content balancing (LA-CB) methods, one with a constant step size and another with an adaptive step size, are proposed as feasible solutions to balancing content areas in variable-length computerized classification testing (VL-CCT). The proposed LA-CB methods are compared with conventional item selection methods in variable-length tests under different classification methods' settings. Simulation results show that integrated with heuristic item selection methods, the proposed LA-CB methods outperform the conventional item selection methods with fewer constraint violations and higher classification accuracy. The second issue we address is to find the learning policy that designs the optimal learning path in an adaptive learning system under hierarchical skill structures. To this end, we first develop a model for learners' hierarchical skills in the adaptive learning system. Based on the hierarchical skill model and the classical cognitive diagnosis model, we further develop a framework to model various levels of proficiency related to hierarchical skills. The optimal learning policy in consideration of the hierarchical structure of skills is found by applying a data-driven algorithm-reinforcement learning method, which does not require information about learners' learning transition processes. The effectiveness of the proposed framework is demonstrated via simulation studies. Lastly, we solve the problem of finding a learning policy assuming latent traits to be continuous with an unknown transition model. We formulate the adaptive learning problem as a Markov decision process (MDP). We apply a model-free deep reinforcement learning algorithm---the deep Q-learning algorithm---that is data-driven and can effectively find the optimal learning policy from data on learners' learning process without knowing the actual transition model of the learner's continuous latent traits. To efficiently utilize available data, we further develop a transition model estimator that emulates the learner's learning process using neural networks. The transition model estimator can be used in the deep Q-learning algorithm so that it can more efficiently discover the optimal learning policy for a learner. Numerical simulation studies verify that the proposed algorithm is very efficient in finding a good learning policy, especially with the aid of a transition model estimator, it can find the optimal learning policy after training using a small number of learners.\"","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2020-08-25 without embargo terms","The student, Xiao Li, accepted the attached license on 2020-04-13 at 16:37.","The student, Xiao Li, submitted this Dissertation for approval on 2020-04-13 at 16:47.","This Dissertation was approved for publication on 2020-04-14 at 17:30.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14972 on 2020-08-25 at 17:06:51","Made available in DSpace on 2020-08-26T21:54:19Z (GMT). No. of bitstreams: 2 LI-DISSERTATION-2020.pdf: 937515 bytes, checksum: 2ccb92e2b202a70444dedba19b3b0e60 (MD5) LICENSE.txt: 4204 bytes, checksum: a474e3fecf0aad382d38b1383f79031a (MD5) Previous issue date: 2020-04-14"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/107881"],"dc:language":["en"],"dc:rights":["Copyright 2020 Xiao Li"],"dc:subject":["Adaptive learning system","Data-driven"],"dc:title":["Data-driven adaptive learning systems"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Educational Psychology"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:47Z"}