Active Learning for Technology Enhanced Learning

详细信息    查看全文

• 作者：Artus Krohn-Grimberghe (1) artus@ismll.uni-hildesheim.de
  Andre Busche (1) busche@ismll.uni-hildesheim.de
  Alexandros Nanopoulos (1) nanopoulos@ismll.uni-hildesheim.de
  Lars Schmidt-Thieme (1) schmidt-thieme@ismll.uni-hildesheim.de
• 关键词：Active learning – ; recommender systems – ; student performance prediction – ; optimal learning – ; intelligent tutoring systems
• 刊名：Lecture Notes in Computer Science
• 出版年：2011
• 出版时间：2011
• 年：2011
• 卷：6964
• 期：1
• 页码：512-518
• 全文大小：220.9 KB
• 参考文献：1. Golbandi, N., Koren, Y., Lempel, R.: Adaptive bootstr. of recommender systems using decision trees. In: Proc. of the 4th ACM Intl. Conf. on Web Search and Data Mining (2011)
  2. Lewis, D., Catlett, J.: Heterogeneous uncertainty sampling for supervised learning. In: Proceedings of the International Conference on Machine Learning, ICML (1994)
  3. Manouselis, N., Drachsler, H., Vuorikari, R., Hummel, H., Koper, R.: Recommender systems in technology enhanced learning. In: Recommender Systems Handbook: A Complete Guide for Research Scientists & Practitioners (2010)
  4. Murray, T., Arroyo, I.: Toward measuring and maintaining the zone of proximal development in adaptive instructional systems. In: Cerri, S.A., Gouard茅res, G., Paragua莽u, F. (eds.) ITS 2002. LNCS, vol. 2363, pp. 749–758. Springer, Heidelberg (2002)
  5. Rish, I., Tesauro, G.: Active Collaborative Prediction with Maximum Margin Matrix Factorization. In: Inform. Theory and App. Workshop (2007)
  6. Thai-Nghe, N., Drumond, L., Horv谩th, T., Krohn-Grimberghe, A., Nanopoulos, A., Schmidt-Thieme, L.: Factorization techniques for predicting student performance. In: Educational Recommender Systems and Technologies: Practices and Challenges (2011)
  7. Vygotsky, L.S.: Mind in Society: The Development of Higher Psychological Processes. Harvard University Press, Cambridge (1978)
• 作者单位：1. Information Systems and Machine Learning Lab, University of Hildesheim, Germany
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349

文摘

Suggesting tasks and learning resources of appropriate difficulty to learners is challenging. Neither should they be too difficult and nor too easy. Well-chosen tasks would enable a quick assessment of the learner, well-chosen learning resources would speed up the learning curve most. We connect active learning to classical pedagogical theory and propose the uncertainty sampling framework as a means to the challenge of selecting optimal tasks and learning resources to learners. To assess the efficiency of this strategy, we compared different exercise selection strategies and evaluated their effect on different datasets. We consistently find that uncertainty sampling significantly outperforms several alternative exercise selection approaches and thus leads to a faster convergence to the true assessment. These findings demonstrate that active (machine) learning is consistent with classic learning theory. It is a valuable instrument for choosing appropriate exercises as well as learning resources both from a teacher’s and from a learner’s perspective.