Blending Machine and Human Learning Processes

Citizen science projects face a dilemma in relying on contributions from volunteers to achieve their scientific goals: providing volunteers with explicit training might increase the quality of contributions, but at the cost of losing the work done by newcomers during the training period, which for many is the only work they will contribute to the project. Based on research in cognitive science on how humans learn to classify images, we have designed an approach to use machine learning to guide the presentation of tasks to newcomers that help them more quickly learn how to do the image classification task while still contributing to the work of the project. A Bayesian model for tracking volunteer learning is presented.

[1]  W. T. Maddox,et al.  Stimulus Generalization in Category Learning , 2005 .

[2]  Brett van de Sande,et al.  Properties of the Bayesian Knowledge Tracing Model , 2013, EDM 2013.

[3]  Nicolas Ducheneaut,et al.  Socialization in an Open Source Software Community: A Socio-Technical Analysis , 2005, Computer Supported Cooperative Work (CSCW).

[4]  John R. Anderson,et al.  Knowledge tracing: Modeling the acquisition of procedural knowledge , 2005, User Modeling and User-Adapted Interaction.

[5]  Joshua B. Tenenbaum,et al.  Bayesian Modeling of Human Concept Learning , 1998, NIPS.

[6]  Michael C. Mozer,et al.  Improving Human-Machine Cooperative Classification Via Cognitive Theories of Similarity , 2017, Cogn. Sci..

[7]  R. Moreno,et al.  Cognitive load and learning effects of having students organize pictures and words in multimedia environments: The role of student interactivity and feedback , 2005 .

[8]  Yun-En Liu,et al.  Designing Engaging Games Using Bayesian Optimization , 2016, CHI.

[9]  Carsten S. Østerlund,et al.  Planet hunters and seafloor explorers: legitimate peripheral participation through practice proxies in online citizen science , 2014, CSCW.

[10]  G. Murphy,et al.  Ideals and category typicality. , 2011, Journal of experimental psychology. Learning, memory, and cognition.

[11]  Sanna Malinen,et al.  Understanding user participation in online communities: A systematic literature review of empirical studies , 2015, Comput. Hum. Behav..

[12]  Mausam,et al.  Re-Active Learning: Active Learning with Relabeling , 2016, AAAI.

[13]  R. Shepard,et al.  Toward a universal law of generalization for psychological science. , 1987, Science.

[14]  Liesbeth Kester,et al.  Dynamic task selection: Effects of feedback and learner control on efficiency and motivation , 2009 .

[15]  Vincent Aleven,et al.  More Accurate Student Modeling through Contextual Estimation of Slip and Guess Probabilities in Bayesian Knowledge Tracing , 2008, Intelligent Tutoring Systems.

[16]  Kenneth R. Koedinger,et al.  Individualized Bayesian Knowledge Tracing Models , 2013, AIED.

[17]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Pawan Sinha,et al.  A Perceptually Based Comparison of Image Similarity Metrics , 2011, Perception.

[19]  Amy Bruckman,et al.  Becoming Wikipedian: transformation of participation in a collaborative online encyclopedia , 2005, GROUP.

[20]  R. Nosofsky.  Attention, similarity, and the identification-categorization relationship. , 1986, Journal of experimental psychology. General.

[21]  C. Lintott,et al.  Galaxy Zoo: Exploring the Motivations of Citizen Science Volunteers. , 2009, 0909.2925.

[22]  Sarah Kendrew,et al.  THE MILKY WAY PROJECT: LEVERAGING CITIZEN SCIENCE AND MACHINE LEARNING TO DETECT INTERSTELLAR BUBBLES , 2014, 1406.2692.

[23]  D. Leutner.  Guided discovery learning with computer-based simulation games: Effects of adaptive and non-adaptive instructional support , 1993 .

[24]  Geoffrey R Norman,et al.  Teaching posttraining: influencing diagnostic strategy with instructions at test. , 2011, Journal of experimental psychology. Applied.

[25]  Steven Bamford,et al.  The Moon Zoo citizen science project: Preliminary results for the Apollo 17 landing site , 2016, 1602.01664.

[26]  David Richard Moore,et al.  E-Learning and the Science of Instruction: Proven Guidelines for Consumers and Designers of Multimedia Learning , 2006 .