{"type":"ScholarlyArticle","title":"Content Matters: A Computational Investigation into the Effectiveness of Retrieval Practice and Worked Examples (Extended Abstract)","authors":[{"name":"Napol Rachatasumrit","slug":"napol-rachatasumrit","given":"Napol","family":"Rachatasumrit","affiliation":"Carnegie Mellon University"},{"name":"Paulo F. Carvalho","slug":"paulo-f-carvalho","given":"Paulo F.","family":"Carvalho","affiliation":"Carnegie Mellon University"},{"name":"Sophie Li","slug":"sophie-li","given":"Sophie","family":"Li","affiliation":"Carnegie Mellon University"},{"name":"Kenneth R. Koedinger","slug":"kenneth-r-koedinger","given":"Kenneth R.","family":"Koedinger","affiliation":"Carnegie Mellon University"}],"abstract":"In this paper, we argue that computational models of learning can contribute precise theory to explain surprising student learning phenomena. In some past studies, practice produces better learning than studying examples, whereas other studies show the opposite result. We explain this contradiction by suggesting that retrieval practice and example study involve different learning cognitive processes, memorization and induction, and each process is optimal for different types of knowledge. We implement and test this theoretical explanation by extending an AI model of human cognition to include both memory and induction processes and comparing the behavior of the simulated learners to those of human participants. We show that the behavior of simulated learners with forgetting matches that of human participants better than simulated learners without forgetting. Simulated learners with forgetting learn best using retrieval practice in situations that emphasize memorization (such as learning facts), whereas studying examples improves learning when multiple pieces of information are available, so induction and generalization are necessary (such as learning skills).","doi":"10.24963/ijcai.2024/940","url":"https://ijcai.org/proceedings/2024/940","pdf":"https://ijcai.org/proceedings/2024/0940.pdf","markdown":"https://ijcai.org/proceedings/2024/940.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/940","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":940,"pages":{"first":8450,"last":8454},"keywords":["Multidisciplinary Topics and Applications: MTA: Education","Humans and AI: HAI: Cognitive modeling"],"videos":[],"references":[{"position":1,"raw":"[Carvalho et al., 2022] Paulo F. Carvalho, Napol Rachata- sumrit, and Kenneth R Koedinger. Learning depends on knowledge: The benefits of retrieval practice vary for facts and skills. Proceedings of the Annual Meeting of the Cog- nitive Science Society, 2022.","title":"Learning depends on knowledge: The benefits of retrieval practice vary for facts and skills","authors":"Paulo F Carvalho, Napol Rachatasumrit, Kenneth R Koedinger","year":"2022","venue":"Proceedings of the Annual Meeting of the Cognitive Science Society","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Karpicke and Blunt, 2011] Jeffrey D Karpicke and Janell R Blunt. Retrieval practice produces more learning than elaborative studying with concept mapping. Science, 331(6018):772-775, 2011.","title":"Retrieval practice produces more learning than elaborative studying with concept mapping","authors":"D Jeffrey, Janell R Karpicke, Blunt","year":"2011","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Koedinger et al., 2012] Kenneth R Koedinger, Albert T Corbett, and Charles Perfetti. The knowledge-learning- instruction framework: Bridging the science-practice chasm to enhance robust student learning. Cognitive sci- ence, 36(5):757-798, 2012.","title":"The knowledge-learninginstruction framework: Bridging the science-practice chasm to enhance robust student learning","authors":"Albert T Kenneth R Koedinger, Charles Corbett, Perfetti","year":"2012","venue":"Cognitive science","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Maclellan et al., 2016] Christopher J Maclellan, Erik Harp- stead, Rony Patel, and Kenneth R Koedinger. The appren- tice learner architecture: Closing the loop between learn- ing theory and educational data. International Educational Data Mining Society, 2016.","title":"The apprentice learner architecture: Closing the loop between learning theory and educational data","authors":"Erik Christopher J Maclellan, Rony Harpstead, Kenneth R Patel, Koedinger","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Pavlik and Anderson, 2008] Philip I Pavlik and John R An- derson. Using a model to compute the optimal schedule of practice. Journal of Experimental Psychology: Applied, 14(2):101, 2008.","title":"Philip I Pavlik and John R Anderson. Using a model to compute the optimal schedule of practice","authors":"Anderson Pavlik","year":"2008","venue":"Journal of Experimental Psychology: Applied","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Rachatasumrit et al., 2023] Napol Rachatasumrit, Paulo F Carvalho, Sophie Li, and Kenneth R Koedinger. Content matters: A computational investigation into the effective- ness of retrieval practice and worked examples. In Interna- tional Conference on Artificial Intelligence in Education, pages 54-65. Springer, 2023.","title":"Content matters: A computational investigation into the effectiveness of retrieval practice and worked examples","authors":"Napol Rachatasumrit, Paulo F Carvalho, Sophie Li, Kenneth R Koedinger","year":"2023","venue":"International Conference on Artificial Intelligence in Education","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Renkl, 2005] Alexander Renkl. The worked-out-example principle in multimedia learning. The Cambridge hand- book of multimedia learning, pages 229-245, 2005.","title":"The worked-out-example principle in multimedia learning","authors":"Alexander Renkl","year":"2005","venue":"The Cambridge handbook of multimedia learning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Roediger III and Karpicke, 2006] Henry L Roediger III and Jeffrey D Karpicke. Test-enhanced learning: Taking mem- ory tests improves long-term retention. Psychological sci- ence, 17(3):249-255, 2006.","title":"Test-enhanced learning: Taking memory tests improves long-term retention","authors":"L Henry, Iii Roediger, Jeffrey D Karpicke","year":"2006","venue":"Psychological science","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Roediger III et al., 2011] Henry L Roediger III, Pooja K Agarwal, Mark A McDaniel, and Kathleen B McDermott. Test-enhanced learning in the classroom: long-term im- provements from quizzing. Journal of Experimental Psy- chology: Applied, 17(4):382, 2011.","title":"Test-enhanced learning in the classroom: long-term improvements from quizzing","authors":"Iii Henry L Roediger, K Pooja, Mark A Agarwal, Kathleen B Mcdaniel, Mcdermott","year":"2011","venue":"Journal of Experimental Psychology: Applied","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Salden et al., 2010] Ron JCM Salden, Kenneth R Koedinger, Alexander Renkl, Vincent Aleven, and Bruce M McLaren. Accounting for beneficial effects of worked examples in tutored problem solving. Educational Psychology Review, 22(4):379-392, 2010.","title":"Accounting for beneficial effects of worked examples in tutored problem solving","authors":"Ron Jcm Salden, Alexander Kenneth R Koedinger, Renkl, Bruce M Vincent Aleven, Mclaren","year":"2010","venue":"Educational Psychology Review","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Van Gog et al., 2006] Tamara Van Gog, Fred Paas, and Jeroen JG Van Merriënboer. Effects of process-oriented worked examples on troubleshooting transfer perfor- mance. Learning and Instruction, 16(2):154-164, 2006.","title":"Effects of process-oriented worked examples on troubleshooting transfer performance","authors":"Tamara Van Gog, Fred Paas, Jeroen Jg Van Merriënboer","year":"2006","venue":"Learning and Instruction","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Weitekamp et al., 2021] Daniel Weitekamp, Christopher MacLellan, Erik Harpstead, and Kenneth Koedinger. De- composed inductive procedure learning, 2021.","title":"Decomposed inductive procedure learning","authors":"Daniel Weitekamp, Christopher Maclellan, Erik Harpstead, Kenneth Koedinger","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Weitekamp III et al., ] Daniel Weitekamp III, Erik Harp- stead, Christopher J MacLellan, Napol Rachatasumrit, and Kenneth R Koedinger. Toward near zero-parameter predic- tion using a computational model of student learning. Ann Arbor, 1001:48105.","title":"Toward near zero-parameter prediction using a computational model of student learning","authors":"Iii Weitekamp","year":"1001","venue":"Ann Arbor","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}