Coordinating visualizations of polysemous action: values added for grounding proportion

Abrahamson, Dor; Lee, Rosa G.; Negrete, Andrea G.; Gutiérrez, J.F.

doi:10.1007/s11858-013-0521-7

Cited by 54 publications

(47 citation statements)

References 34 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Students devise a broad variety of sensorimotor schemes for enacting a target movement [2,7,8,12]. Knowing what schemes students are employing is critical for supporting their learning, and yet determining these schemes has been a challenging engineering task.…”

Section: Discussionmentioning

confidence: 99%

“…It remains an open challenge to enable automatic assessment at the strategy level and to provide subsequent appropriate instruction, valorization, providing of correction hints, asking of questions that provoke reflection, and introduction of new artifacts. The nature of strategies exhibited during interaction with MITp have been deduced through manual analysis of data streams collected during tutoring in previous work and were determined to be helpful states to transition through while learning [7]. Three distinct strategies were identified in past work as most important and are described below.…”

Section: The Proportionality Tutor Appmentioning

confidence: 99%

See 1 more Smart Citation

Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks

Pardos

Meng

et al. 2018

Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization

Self Cite

View full text Add to dashboard Cite

Sensor stream data, particularly those collected at the millisecond of granularity, have been notoriously difficult to leverage classifiable signal out of. Adding to the challenge is the limited domain knowledge that exists at these biological sensor levels of interaction that prohibits a comprehensive manual feature engineering approach to classification of those streams. In this paper, we attempt to enhance the assessment capability of a touchscreen based ratio tutoring system by using Recurrent Neural Networks (RNNs) to predict the strategy being demonstrated by students from their 60hz data streams. We hypothesize that the ability of neural networks to learn representations automatically, instead of relying on human feature engineering, may benefit this classification task. Our RNN and baseline models were trained and cross-validated at several levels on historical data which had been human coded with the task strategy believed to be exhibited by the learner. Our RNN approach to this historically difficult high frequency data classification task moderately advances performance above baselines and we discuss what implication this level of assessment performance has on enabling greater adaptive supports in the tutoring system.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: The Proportionality Tutor Appmentioning

confidence: 99%

Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks

Pardos

Meng

et al. 2018

Adjunct Publication of the 26th Conference on User Modeling, Adaptation and Personalization

Self Cite

View full text Add to dashboard Cite

show abstract

“…One could also argue that proportion is both discrete-think of all discrete instances (4:8, 5:10, etc. )-and continuous: Put your hands on the table and move them up in such a way that the right hand is moving twice as fast as the left one; your hands then move proportionally in a continuous way (Abrahamson et al 2014). I propose to use this concept of Aufhebung to lift the tension between guidance and discovery, and lift up the discussion about discovery learning to a higher level.…”

Section: Sublationmentioning

confidence: 99%

Discovery learning: zombie, phoenix, or elephant?

Bakker

2018

Instr Sci

View full text Add to dashboard Cite

Discovery learning continues to be a topic of heated debate. It has been called a zombie, and this special issue raises the question whether it may be a phoenix arising from the ashes to which the topic was burnt. However, in this commentary I propose it is more like an elephant-a huge topic approached by many people who address different aspects. What is needed in the discussion about discovery learning and related approaches, I argue, is sublation: the kind of lifting up from the one-dimensional discussion between two extremes (minimal guidance vs. instruction) that puts an end to the everlasting tug of war by integrating justified concerns from both opposite positions. I evaluate how the different contributions to the special issue help to sublate the discussion about discovery learning to a higher level. In particular, the case study presented by Trninic illustrates how strong guidance and repetition may be needed for the discovery of something that cannot be told. I further suggest scaffolding, inferentialism, and design research as potential theoretical and methodological ways forward.

show abstract

“…In this paper, we leverage intensive, qualitative micro-analyses of multimodal behaviors (e.g., Abrahamson, Lee, Negrete, & Gutiérrez, 2014;Nathan, Wolfgram, Srisurichan, Walkington, & Alibali, 2017;Nemirovsky, 2011;Schoenfeld, Smith, & Arcavi, 1991) to investigate how relational equity is manifested and how strategies for solving equivalence problems emerge during and after peer collaboration. This analysis brings together traditions and research methods from psychology and mathematics education to paint a richer, more complete picture of collaborative learning than that offered by either discipline alone.…”

Section: The Current Studymentioning

confidence: 99%

Relational equity and mathematics learning: Mutual construction during collaborative problem solving

2018

Self Cite

View full text Add to dashboard Cite

We present an emerging interdisciplinary approach to the study of mathematics learning, which brings together strands from psychology and mathematics education. Our aim was to examine how students navigate the cognitive and social aspects of peer collaboration as they generate and adopt new strategies. We analyzed video data from a laboratory study involving pairs of elementary students working collaboratively to solve mathematical equivalence problems (e.g., 8 + 5 + 4 = 4 + ___). We adopted a qualitative micro-analytic approach that focused on multimodal action (i.e., verbal utterance, gesture, inscription production, body positioning, and eye gaze) to examine three cases. These cases illustrate the complex ways that students interacted in this particular context and, in some instances, attempted to teach one another. Our findings show how "relational equity" (Boaler, 2008) and mathematics knowledge were co-constructed differently in each case. We argue that a micro-analytic approach, complemented by a blending of theory from these two fields, reveals hidden aspects of the interaction that may help explain, for example, why some students generate or adopt correct strategies and others do not. As such, this interdisciplinary approach offers a rich account of the learning processes that occur in peer collaboration.

show abstract

Coordinating visualizations of polysemous action: values added for grounding proportion

Cited by 54 publications

References 34 publications

Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks

Classifying Learner Behavior from High Frequency Touchscreen Data Using Recurrent Neural Networks

Discovery learning: zombie, phoenix, or elephant?

Relational equity and mathematics learning: Mutual construction during collaborative problem solving

Contact Info

Product

Resources

About