skip to main content

This content will become publicly available on September 24, 2022

Title: Measuring and Analyzing Students’ Strategic Learning Behaviors in Open-Ended Learning Environments
Strategies are an important component of self-regulated learning frameworks. However, the characterization of strategies in these frameworks is often incomplete: (1) they lack an operational definition of strategies; (2) there is limited understanding of how students develop and apply strategies; and (3) there is a dearth of systematic and generalizable approaches to measure and evaluate strategies when students’ work in open-ended learning environments (OELEs). This paper develops systematic methods for detecting, interpreting, and analyzing students’ use of strategies in OELEs, and demonstrates how students’ strategies evolve across tasks. We apply this framework in the context of tasks that students perform as they learn science topics by building conceptual and computational models in an OELE. Data from a classroom study, where sixth-grade students (N = 52) worked on science model-building activities in our Computational Thinking using Simulation and Modeling (CTSiM) environment demonstrates how we interpret students’ strategy use, and how strategy use relates to their learning performance. We also demonstrate how students’ strategies evolve as they work on multiple model-building tasks. The results demonstrate the effectiveness of our strategy framework in analyzing students’ behaviors and performance in CTSiM.
; ;
Award ID(s):
Publication Date:
Journal Name:
International Journal of Artificial Intelligence in Education
Sponsoring Org:
National Science Foundation
More Like this
  1. Xu, Jinbo (Ed.)
    Abstract Motivation Cryo-Electron Tomography (cryo-ET) is a 3D bioimaging tool that visualizes the structural and spatial organization of macromolecules at a near-native state in single cells, which has broad applications in life science. However, the systematic structural recognition and recovery of macromolecules captured by cryo-ET are difficult due to high structural complexity and imaging limits. Deep learning-based subtomogram classification has played critical roles for such tasks. As supervised approaches, however, their performance relies on sufficient and laborious annotation on a large training dataset. Results To alleviate this major labeling burden, we proposed a Hybrid Active Learning (HAL) framework for queryingmore »subtomograms for labeling from a large unlabeled subtomogram pool. Firstly, HAL adopts uncertainty sampling to select the subtomograms that have the most uncertain predictions. This strategy enforces the model to be aware of the inductive bias during classification and subtomogram selection, which satisfies the discriminativeness principle in AL literature. Moreover, to mitigate the sampling bias caused by such strategy, a discriminator is introduced to judge if a certain subtomogram is labeled or unlabeled and subsequently the model queries the subtomogram that have higher probabilities to be unlabeled. Such query strategy encourages to match the data distribution between the labeled and unlabeled subtomogram samples, which essentially encodes the representativeness criterion into the subtomogram selection process. Additionally, HAL introduces a subset sampling strategy to improve the diversity of the query set, so that the information overlap is decreased between the queried batches and the algorithmic efficiency is improved. Our experiments on subtomogram classification tasks using both simulated and real data demonstrate that we can achieve comparable testing performance (on average only 3% accuracy drop) by using less than 30% of the labeled subtomograms, which shows a very promising result for subtomogram classification task with limited labeling resources. Availability and implementation Supplementary information Supplementary data are available at Bioinformatics online.« less
  2. Translating information between the domains of systematics and conservation requires novel information management designs. Such designs should improve interactions across the trading zone between the domains, herein understood as the model according to which knowledge and uncertainty are productively translated in both directions (cf. Collins et al. 2019). Two commonly held attitudes stand in the way of designing a well-functioning systematics-to-conservation trading zone. On one side, there are calls to unify the knowledge signal produced by systematics, underpinned by the argument that such unification is a necessary precondition for conservation policy to be reliably expressed and enacted (e.g., Garnett etmore »al. 2020). As a matter of legal scholarship, the argument for systematic unity by legislative necessity is principally false (Weiss 2003, MacNeil 2009, Chromá 2011), but perhaps effective enough as a strategy to win over audiences unsure about robust law-making practices in light of variable and uncertain knowledge. On the other side, there is an attitude that conservation cannot ever restrict the academic freedom of systematics as a scientific discipline (e.g., Raposo et al. 2017). This otherwise sound argument misses the mark in the context of designing a productive trading zone with conservation. The central interactional challenge is not whether the systematic knowledge can vary at a given time and/or evolve over time, but whether these signal dynamics are tractable in ways that actors can translate into robust maxims for conservation. Redesigning the trading zone should rest on the (historically validated) projection that systematics will continue to attract generations of inspired, productive researchers and broad-based societal support, frequently leading to protracted conflicts and dramatic shifts in how practioners in the field organize and identify organismal lineages subject to conservation. This confident outlook for systematics' future, in turn, should refocus the challenge of designing the trading zone as one of building better information services to model the concurrent conflicts and longer-term evolution of systematic knowledge. It would seem unreasonable to expect the International Union for Conservation of Nature (IUCN) Red List Index to develop better data science models for the dynamics of systematic knowledge (cf. Hoffmann et al. 2011) than are operational in the most reputable information systems designed and used by domain experts (Burgin et al. 2018). The reasonable challenge from conservation to systematics is not to stop being a science but to be a better data science. In this paper, we will review advances in biodiversity data science in relation to representing and reasoning over changes in systematic knowledge with computational logic, i.e., modeling systematic intelligence (Franz et al. 2016). We stress-test this approach with a use case where rapid systematic signal change and high stakes for conservation action intersect, i.e., the Malagasy mouse lemurs ( Microcebus É. Geoffroy, 1834 sec. Schüßler et al. 2020), where the number of recognized species-level concepts has risen from 2 to 25 in the span of 38 years (1982–2020). As much as scientifically defensible, we extend our modeling approach to the level of individual published occurrence records, where the inability to do so sometimes reflects substandard practice but more importantly reveals systemic inadequacies in biodiversity data science or informational modeling. In the absence of shared, sound theoretical foundations to assess taxonomic congruence or incongruence across treatments, and in the absence of biodiversity data platforms capable of propagating logic-enabled, scalable occurrence-to-concept identification events to produce alternative and succeeding distribution maps, there is no robust way to provide a knowledge signal from systematics to conservation that is both consistent in its syntax and acccurate in its semantics, in the sense of accurately reflecting the variation and uncertainty that exists across multiple systematic perspectives. Translating this diagnosis into new designs for the trading zone is only one "half" of the solution, i.e., a technical advancement that then would need to be socially endorsed and incentivized by systematic and conservation communities motivated to elevate their collaborative interactions and trade robustly in inherently variable and uncertain information.« less
  3. Today’s classrooms are remarkably different from those of yesteryear. In place of individual students responding to the teacher from neat rows of desks, one more typically finds students working in groups on projects, with a teacher circulating among groups. AI applications in learning have been slow to catch up, with most available technologies focusing on personalizing or adapting instruction to learners as isolated individuals. Meanwhile, an established science of Computer Supported Collaborative Learning has come to prominence, with clear implications for how collaborative learning could best be supported. In this contribution, I will consider how intelligence augmentation could evolve tomore »support collaborative learning as well as three signature challenges of this work that could drive AI forward. In conceptualizing collaborative learning, Kirschner and Erkens (2013) provide a useful 3x3 framework in which there are three aspects of learning (cognitive, social and motivational), three levels (community, group/team, and individual) and three kinds of pedagogical supports (discourse-oriented, representation-oriented, and process-oriented). As they engage in this multiply complex space, teachers and learners are both learning to collaborate and collaborating to learn. Further, questions of equity arise as we consider who is able to participate and in which ways. Overall, this analysis helps us see the complexity of today’s classrooms and within this complexity, the opportunities for augmentation or “assistance to become important and even essential. An overarching design concept has emerged in the past 5 years in response to this complexity, the idea of intelligent augmentation for “orchestrating” classrooms (Dillenbourg, et al, 2013). As a metaphor, orchestration can suggest the need for a coordinated performance among many agents who are each playing different roles or voicing different ideas. Practically speaking, orchestration suggests that “intelligence augmentation” could help many smaller things go well, and in doing so, could enable the overall intention of the learning experience to succeed. Those smaller things could include helping the teacher stay aware of students or groups who need attention, supporting formation of groups or transitions from one activity to the next, facilitating productive social interactions in groups, suggesting learning resources that would support teamwork, and more. A recent panel of AI experts identified orchestration as an overarching concept that is an important focus for near-term research and development for intelligence augmentation (Roschelle, Lester & Fusco, 2020). Tackling this challenging area of collaborative learning could also be beneficial for advancing AI technologies overall. Building AI agents that better understand the social context of human activities has broad importance, as does designing AI agents that can appropriately interact within teamwork. Collaborative learning has trajectory over time, and designing AI systems that support teams not just with a short term recommendation or suggestion but in long-term developmental processes is important. Further, classrooms that are engaged in collaborative learning could become very interesting hybrid environments, with multiple human and AI agents present at once and addressing dual outcome goals of learning to collaborate and collaborating to learn; addressing a hybrid environment like this could lead to developing AI systems that more robustly help many types of realistic human activity. In conclusion, the opportunity to make a societal impact by attending to collaborative learning, the availability of growing science of computer-supported collaborative learning and the need to push new boundaries in AI together suggest collaborative learning as a challenge worth tackling in coming years.« less
  4. Educational process data, i.e., logs of detailed student activities in computerized or online learning platforms, has the potential to offer deep insights into how students learn. One can use process data for many downstream tasks such as learning outcome prediction and automatically delivering personalized intervention. However, analyzing process data is challenging since the specific format of process data varies a lot depending on different learning/testing scenarios. In this paper, we propose a framework for learning representations of educational process data that is applicable across many different learning scenarios. Our framework consists of a pre-training step that uses BERT-type objectives tomore »learn representations from sequential process data and a fine-tuning step that further adjusts these representations on downstream prediction tasks. We apply our framework to the 2019 nation’s report card data mining competition dataset that consists of student problem-solving process data and detail the specific models we use in this scenario. We conduct both quantitative and qualitative experiments to show that our framework results in process data representations that are both predictive and informative.1« less
  5. Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)
    The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3]more »as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.« less