@article{monahan_vandenberg_gupta_smith_elsayed_fox_cheuoua_ringstaff_minogue_oliver_et al._2023, title={Multimodal CS Education Using a Scaffolded CSCL Environment}, url={https://doi.org/10.1145/3587103.3594181}, DOI={10.1145/3587103.3594181}, abstractNote={There is a growing need for 21st-century workers to be digitally literate and to possess computational thinking and collaborative problem-solving skills. Computer-supported collaborative learning (CSCL) focused on computational thinking can guide students toward the co-development of these skills. In this work, we present our approach to integrating virtual and physical learning modalities into InfuseCS, a CSCL environment. InfuseCS uses problem-based learning scenarios to situate upper elementary school students (ages 8 to 11) in a CSCL setting to foster their computational thinking and science knowledge construction as they collaborate to create digital narratives.}, journal={PROCEEDINGS OF THE 2023 CONFERENCE ON INNOVATION AND TECHNOLOGY IN COMPUTER SCIENCE EDUCATION, ITICSE 2023, VOL. 2}, author={Monahan, Robert and Vandenberg, Jessica and Gupta, Anisha and Smith, Andy and Elsayed, Rasha and Fox, Kimkinyona and Cheuoua, Aleata Hubbard and Ringstaff, Cathy and Minogue, James and Oliver, Kevin and et al.}, year={2023}, pages={645–645} }
 @article{spain_rowe_smith_goldberg_pokorny_mott_lester_2021, title={A reinforcement learning approach to adaptive remediation in online training}, volume={7}, ISSN={["1557-380X"]}, DOI={10.1177/15485129211028317}, abstractNote={ Advances in artificial intelligence (AI) and machine learning can be leveraged to tailor training based on the goals, learning needs, and preferences of learners. A key component of adaptive training systems is tutorial planning, which controls how scaffolding is structured and delivered to learners to create dynamically personalized learning experiences. The goal of this study was to induce data-driven policies for tutorial planning using reinforcement learning (RL) to provide adaptive scaffolding based on the Interactive, Constructive, Active, Passive framework for cognitive engagement. We describe a dataset that was collected to induce RL-based scaffolding policies, and we present the results of our policy analyses. Results showed that the best performing policies optimized learning gains by inducing an adaptive fading approach in which learners received less cognitively engaging forms of remediation as they advanced through the training course. This policy was consistent with preliminary analyses that showed constructive remediation became less effective as learners progressed through the training session. Results also showed that learners’ prior knowledge impacted the type of scaffold that was recommended, thus showing evidence of an aptitude–treatment interaction. We conclude with a discussion of how AI-based training can be leveraged to enhance training effectiveness as well as directions for future research. }, journal={JOURNAL OF DEFENSE MODELING AND SIMULATION-APPLICATIONS METHODOLOGY TECHNOLOGY-JDMS}, author={Spain, Randall and Rowe, Jonathan and Smith, Andy and Goldberg, Benjamin and Pokorny, Robert and Mott, Bradford and Lester, James}, year={2021}, month={Jul} }
 @article{tian_wiggins_fahid_emerson_bounajim_smith_boyer_wiebe_mott_lester_2021, title={Modeling Frustration Trajectories and Problem-Solving Behaviors in Adaptive Learning Environments for Introductory Computer Science}, volume={12749}, ISBN={["978-3-030-78269-6"]}, ISSN={["1611-3349"]}, DOI={10.1007/978-3-030-78270-2_63}, abstractNote={Modeling a learner’s frustration in adaptive environments can inform scaffolding. While much work has explored momentary frustration, there is limited research investigating the dynamics of frustration over time and its relationship with problem-solving behaviors. In this paper, we clustered 86 undergraduate students into four frustration trajectories as they worked with an adaptive learning environment for introductory computer science. The results indicate that students who initially report high levels of frustration but then reported lower levels later in their problem solving were more likely to have sought help. These findings provide insight into how frustration trajectory models can guide adaptivity during extended problem-solving episodes.}, journal={ARTIFICIAL INTELLIGENCE IN EDUCATION (AIED 2021), PT II}, author={Tian, Xiaoyi and Wiggins, Joseph B. and Fahid, Fahmid Morshed and Emerson, Andrew and Bounajim, Dolly and Smith, Andy and Boyer, Kristy Elizabeth and Wiebe, Eric and Mott, Bradford and Lester, James}, year={2021}, pages={355–360} }
 @inproceedings{fahid_tian_emerson_wiggins_bounajim_smith_wiebe_mott_boyer_lester_2021, title={Progression Trajectory-Based Student Modeling for Novice Block-Based Programming}, url={http://dx.doi.org/10.1145/3450613.3456833}, DOI={10.1145/3450613.3456833}, abstractNote={Block-based programming environments are widely used in computer science education. However, these environments pose significant challenges for student modeling. Given a series of problem-solving actions taken by students in block-based programming environments, student models need to accurately infer problem-solving students’ programming abilities in real time to enable adaptive feedback and hints that are tailored to students’ abilities. While student models for block-based programming offer the potential to support student-adaptivity, creating student models for these environments is challenging because students can develop a broad range of solutions to a given programming activity. To address these challenges, we introduce a progression trajectory-based student modeling framework for modeling novice student block-based programming across multiple learning activities. Student trajectories utilize a time series representation that employs code analysis to incrementally compare student programs to expert solutions as students undertake block-based programming activities. This paper reports on a study in which progression trajectories were collected from more than 100 undergraduate students engaging in a series of block-based programming activities in an introductory computer science course. Using progression trajectory-based student modeling, we identified three distinct trajectory classes: Early Quitting, High Persistence, and Efficient Completion. Analysis of these trajectories revealed that they exhibit significantly different characteristics with respect to students’ actions and can be used to accurately predict students’ programming behaviors on future programming activities compared to competing baseline models. The findings suggest that progression trajectory-based student models can accurately model students’ block-based programming problem solving and hold potential for informing adaptive support in block-based programming environments.}, booktitle={Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization}, publisher={ACM}, author={Fahid, Fahmid Morshed and Tian, Xiaoyi and Emerson, Andrew and Wiggins, Joseph B. and Bounajim, Dolly and Smith, Andy and Wiebe, Eric and Mott, Bradford and Boyer, Kristy Elizabeth and Lester, James}, year={2021}, month={Jun} }
 @inproceedings{cluster-based analysis of novice coding misconceptions in block-based programming_2020, url={http://dx.doi.org/10.1145/3328778.3366924}, DOI={10.1145/3328778.3366924}, abstractNote={Recent years have seen an increasing interest in identifying common student misconceptions during introductory programming. In a parallel development, block-based programming environments for novice programmers have grown in popularity, especially in introductory courses. While these environments eliminate many syntax-related errors faced by novice programmers, there has been limited work that investigates the types of misconceptions students might exhibit in these environments. Developing a better understanding of these misconceptions will enable these programming environments and instructors to more effectively tailor feedback to students, such as prompts and hints, when they face challenges. In this paper, we present results from a cluster analysis of student programs from interactions with programming activities in a block-based programming environment for introductory computer science education. Using the interaction data from students' programming activities, we identify three families of student misconceptions and discuss their implications for refinement of the activities as well as design of future activities. We then examine the value of block counts, block sequence counts, and system interaction counts as programming features for clustering block-based programs. These clusters can help researchers identify which students would benefit from feedback or interventions and what kind of feedback provides the most benefit to that particular student.}, booktitle={Proceedings of the 51st ACM Technical Symposium on Computer Science Education}, year={2020}, month={Feb} }
 @inproceedings{designing block-based programming language features to support upper elementary students in creating interactive science narratives_2020, url={http://dx.doi.org/10.1145/3328778.3372653}, DOI={10.1145/3328778.3372653}, abstractNote={Recent years have seen a growing recognition of the importance of enabling K-12 students to engage in computational thinking, particularly in elementary grades where students' dispositions toward STEM are developing. Block-based programming has emerged as an effective tool for engaging these novice learners in computational thinking. At the same time, digital storytelling has emerged as a promising avenue for creating motivating problem-solving scenarios that engage students in science investigations. Although block-based programming and digital storytelling are in many ways synergistic, there is a lingering question of how to design block-based languages at an age-appropriate level to enable effective and engaging storytelling. In this work, we review design principles from prior block-based and digital storytelling systems as well as propose the design of block-based programming language features to enable the creation of rich, interactive science narratives by upper elementary students.}, booktitle={Proceedings of the 51st ACM Technical Symposium on Computer Science Education}, year={2020}, month={Feb} }
 @inproceedings{predictive student modeling in block-based programming environments with bayesian hierarchical models_2020, url={http://dx.doi.org/10.1145/3340631.3394853}, DOI={10.1145/3340631.3394853}, abstractNote={Recent years have seen a growing interest in block-based programming environments for computer science education. Although block-based programming offers a gentle introduction to coding for novice programmers, introductory computer science still presents significant challenges, so there is a great need for block-based programming environments to provide students with adaptive support. Predictive student modeling holds significant potential for adaptive support in block-based programming environments because it can identify early on when a student is struggling. However, predictive student models often make a number of simplifying assumptions, such as assuming a normal response distribution or homogeneous student characteristics, which can limit the predictive performance of models. These assumptions, when invalid, can significantly reduce the predictive accuracy of student models. To address these issues, we introduce an approach to predictive student modeling that utilizes Bayesian hierarchical linear models. This approach explicitly accounts for individual student differences and programming activity differences by analyzing block-based programs created by students in a series of introductory programming activities. Evaluation results reveal that predictive student models that account for both the distributional and hierarchical factors outperform baseline models. These findings suggest that predictive student models based on Bayesian hierarchical modeling and representing individual differences in students can substantially improve models' accuracy for predicting student performance on post-tests. By improving the predictive performance of student models, this work holds substantial potential for improving adaptive support in block-based programming environments.}, booktitle={Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization}, year={2020}, month={Jul} }
 @article{taub_sawyer_smith_rowe_azevedo_lester_2020, title={The agency effect: The impact of student agency on learning, emotions, and problem-solving behaviors in a game-based learning environment}, volume={147}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85076323543&partnerID=MN8TOARS}, DOI={10.1016/j.compedu.2019.103781}, abstractNote={Game-based learning environments are designed to foster high levels of student engagement and motivation during learning of complex topics. Game-based learning environments allow students freedom to navigate a space to interact with game elements that foster learning, i.e., agency. Agency has been studied in learning, and it has been demonstrated that increased student agency results in greater learning outcomes. However, it is unclear what is the level of agency that is required to demonstrate this effect, and whether this effect applies only to learning or to problem solving and affect during game-based learning as well. To investigate how the level of student agency impacts learning, problem solving, and affect, a study was conducted with 138 college students interacting with a game-based learning environment for microbiology, Crystal Island. This study is an extension of a previous study that examined the impact of agency on learning and problem-solving behaviors during game-based learning with Crystal Island. Students were randomly assigned to either a High Agency condition, a Low Agency condition, or a No Agency condition. It was found that students in the Low Agency condition achieved significantly higher normalized learning gain scores than students in the No Agency condition, and marginally higher normalized learning gains than the High Agency condition. Post-surveys of interest and presence indicated that students in the No Agency condition were less interested, and perceived themselves as less present in the virtual environment, than students in the other conditions. Students in the No Agency condition also experienced less frustration, confusion, and joy than the other agency conditions, indicating a less cognitively stimulating experience. Overall the results indicate that a moderate degree of agency provided to students in game-based learning environments leads to better learning outcomes without sacrificing interest and without yielding a negative emotional experience, demonstrating how even low levels of agency can positively impact learning, problem solving, and affect during game-based learning.}, journal={Computers and Education}, author={Taub, M. and Sawyer, R. and Smith, A. and Rowe, J. and Azevedo, R. and Lester, J.}, year={2020} }
 @inproceedings{smith_mott_taylor_hubbard-cheuoua_minogue_oliver_ringstaff_2020, title={Toward a Block-Based Programming Approach to Interactive Storytelling for Upper Elementary Students}, url={http://dx.doi.org/10.1007/978-3-030-62516-0_10}, DOI={10.1007/978-3-030-62516-0_10}, abstractNote={Developing narrative and computational thinking skills is crucial for K-12 student learning. A growing number of K-12 teachers are utilizing digital storytelling, where students create short narratives around a topic, as a means of creating motivating problem-solving activities for a variety of domains, including history and science. At the same time, there is increasing awareness of the need to engage K-12 students in computational thinking, including elementary school students. Given the challenges that the syntax of text-based programming languages poses for even novice university-level learners, block-based programming languages have emerged as an effective tool for introducing computational thinking to elementary-level students. Leveraging the unique affordances of narrative and computational thinking offers significant potential for student learning; however, integrating them presents significant challenges. In this paper, we describe initial work toward solving this problem by introducing an approach to block-based programming for interactive storytelling to engage upper elementary students (ages 9 to 11) in computational thinking and narrative skill development. Leveraging design principles and best practices from prior research on elementary-grade block-based programming and digital storytelling, we propose a set of custom blocks enabling learners to create interactive narratives. We describe both the process used to derive the custom blocks, including their alignment with elements of interactive narrative and with specific computational thinking curricular goals, as well as lessons learned from students interacting with a prototype learning environment utilizing the block-based programming approach.}, booktitle={Interactive Storytelling}, publisher={Springer International Publishing}, author={Smith, Andy and Mott, Bradford and Taylor, Sandra and Hubbard-Cheuoua, Aleata and Minogue, James and Oliver, Kevin and Ringstaff, Cathy}, year={2020}, month={Nov}, pages={111–119} }
 @article{smith_leeman-munk_shelton_mott_wiebe_lester_2019, title={A Multimodal Assessment Framework for Integrating Student Writing and Drawing in Elementary Science Learning}, volume={12}, ISSN={1939-1382 2372-0050}, url={http://dx.doi.org/10.1109/TLT.2018.2799871}, DOI={10.1109/TLT.2018.2799871}, abstractNote={Science learning is inherently multimodal, with students utilizing both drawings and writings to explain observations of physical phenomena. As such assessments in science should accommodate the many ways students express their understanding, especially given evidence that understanding is distributed across both drawing and writing. In recent years advanced automated assessment techniques that evaluate expressive student artifacts have emerged. However, these techniques have largely operated individually, each considering only a single mode. We propose a framework for the multimodal automated assessment of students’ writing and drawing to leverage the synergies inherent across modalities and create a more complete and accurate picture of a student's knowledge. We introduce a multimodal assessment framework as well as two computational techniques for automatically analyzing student writings and drawings: a convolutional neural network-based model for assessing student writing, and a topology-based model for assessing student drawing. Evaluations with elementary students’ writings and drawings collected with a tablet-based digital science notebook demonstrate that 1) each of the framework's two modalities provide an independent and complementary measure of student science learning, and 2) the computational methods are capable of accurately assessing student work from both modalities and offer the potential for integration in technology-rich learning environments for real-time formative assessment.}, number={1}, journal={IEEE Transactions on Learning Technologies}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Smith, Andy and Leeman-Munk, Samuel and Shelton, Angi and Mott, Bradford and Wiebe, Eric and Lester, James}, year={2019}, month={Jan}, pages={3–15} }
 @article{geden_smith_campbell_spain_amos-binks_mott_feng_lester_2019, title={Construction and Validation of an Anticipatory Thinking Assessment}, volume={10}, ISSN={["1664-1078"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85077306542&partnerID=MN8TOARS}, DOI={10.3389/fpsyg.2019.02749}, abstractNote={Anticipatory thinking is a critical cognitive skill for successfully navigating complex, ambiguous systems in which individuals must analyze system states, anticipate outcomes, and forecast future events. For example, in military planning, intelligence analysis, business, medicine, and social services, individuals must use information to identify warnings, anticipate a spectrum of possible outcomes, and forecast likely futures in order to avoid tactical and strategic surprise. Existing methods for examining anticipatory thinking skill have relied upon task-specific behavioral measures or are resource-intensive, both of which are challenging to scale. Given the increasing importance of anticipatory thinking in many domains, developing a generic assessment of this skill and identifying the underlying cognitive mechanisms supporting it are paramount. The work reported here focuses on the development and validation of the anticipatory thinking assessment (ANTA) for measuring the divergent generative process of anticipatory thinking. Two-hundred and ten participants completed the ANTA, which required them to anticipate possible risks, opportunities, trends, or other uncertainties associated with a focal topic. Responses to the anticipatory thinking and divergent thinking tasks were rated by trained raters on a five-point scale according to the uniqueness, specificity, and remoteness of responses. Results supported the ANTA’s construct validity, convergent validity, and discriminant validity. We also explored the relationship between the ANTA scores and certain psychological traits and cognitive measures (need for cognition, need for closure, and mindfulness). Our findings suggest that the ANTA is a psychometrically valid instrument that may help researchers investigate anticipatory thinking in new contexts.}, journal={FRONTIERS IN PSYCHOLOGY}, author={Geden, Michael and Smith, Andy and Campbell, James and Spain, Randall and Amos-Binks, Adam and Mott, Bradford W. and Feng, Jing and Lester, James}, year={2019}, month={Dec} }
 @article{min_frankosky_mott_rowe_smith_wiebe_boyer_lester_2019, title={DeepStealth: Game-Based Learning Stealth Assessment with Deep Neural Networks}, volume={13}, ISSN={1939-1382 2372-0050}, url={http://dx.doi.org/10.1109/TLT.2019.2922356}, DOI={10.1109/tlt.2019.2922356}, abstractNote={A distinctive feature of game-based learning environments is their capacity for enabling stealth assessment. Stealth assessment analyzes a stream of fine-grained student interaction data from a game-based learning environment to dynamically draw inferences about students’ competencies through evidence-centered design. In evidence-centered design, evidence models have been traditionally designed using statistical rules authored by domain experts that are encoded using Bayesian networks. This article presents DeepStealth, a deep learning-based stealth assessment framework, that yields significant reductions in the feature engineering labor that has previously been required to create stealth assessments. DeepStealth utilizes end-to-end trainable deep neural network-based evidence models. Using this framework, evidence models are devised using a set of predictive features captured from raw, low-level interaction data to infer evidence for competencies. We investigate two deep learning-based evidence models, long short-term memory networks (LSTMs) and n-gram encoded feedforward neural networks (FFNNs). We compare these models’ predictive performance for inferring students’ knowledge to linear-chain conditional random fields (CRFs) and naïve Bayes models. We perform feature set-level analyses of game trace logs and external pre-learning measures, and we examine the models’ early prediction capacity. The framework is evaluated using data collected from 182 middle school students interacting with a game-based learning environment for middle grade computational thinking. Results indicate that LSTM-based stealth assessors outperform competitive baseline approaches with respect to predictive accuracy and early prediction capacity. We find that LSTMs, FFNNs, and CRFs all benefit from combined feature sets derived from both game trace logs and external pre-learning measures.}, number={2}, journal={IEEE Transactions on Learning Technologies}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Min, Wookhee and Frankosky, Megan and Mott, Bradford W. and Rowe, Jonathan and Smith, Peter Andrew Miller and Wiebe, Eric and Boyer, Kristy and Lester, James}, year={2019}, pages={1–1} }
 @inproceedings{taylor_min_mott_emerson_smith_wiebe_lester_2019, title={Position: IntelliBlox: A Toolkit for Integrating Block-Based Programming into Game-Based Learning Environments}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85078082955&partnerID=MN8TOARS}, DOI={10.1109/BB48857.2019.8941222}, abstractNote={Block-based programming languages reduce the need to learn low-level programming syntax while enabling novice learners to focus on computational thinking skills. Game-based learning environments have been shown to create effective and engaging learning experiences for students in a broad range of educational domains. The fusion of block-based programming with game-based learning offers significant potential to motivate learners to develop computational thinking skills. A key challenge educational game developers face in creating rich, interactive learning experiences that integrate computational thinking activities is the lack of an embeddable block-based programming toolkit. Current block-based programming languages, such as Blockly and Scratch, cannot be easily embedded into industry-standard 3D game engines. This paper presents IntelliBlox, a Blockly-inspired toolkit for the Unity cross-platform game engine that enables learners to create block-based programs within immersive game-based learning environments. Our experience using IntelliBlox suggests that it is an effective toolkit for integrating block-based programming challenges into game-based learning environments.}, booktitle={Proceedings - 2019 IEEE Blocks and Beyond Workshop, B and B 2019}, author={Taylor, S. and Min, W. and Mott, B. and Emerson, A. and Smith, A. and Wiebe, E. and Lester, J.}, year={2019}, pages={55–58} }
 @inproceedings{lester_boyer_wiebe_mott_smith_2019, title={Prime: Engaging STEM undergraduates in computer science with intelligent tutoring systems}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85078800967&partnerID=MN8TOARS}, booktitle={ASEE Annual Conference and Exposition, Conference Proceedings}, author={Lester, J.C. and Boyer, K.E. and Wiebe, E.N. and Mott, B. and Smith, A.}, year={2019} }
 @inproceedings{rodriguez_smith_smith_boyer_wiebe_mott_lester_2019, title={Toward a Responsive Interface to Support Novices in Block-Based Programming}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85078105153&partnerID=MN8TOARS}, DOI={10.1109/BB48857.2019.8941205}, abstractNote={Block-based programming environments are often used for teaching novice students, including at the undergraduate level. Despite the simplification these tools offer, undergraduates still require additional support, often learning programming by themselves or in large section courses with little instructional support. Programming environments that provide adaptive support hold great promise for meeting this need. This paper presents the early design and piloting of Prime, a learning environment under development that provides scaffolded support for novices in block-based programming. A pilot study with Prime compared two implementations of the functionality for moving between programming subtasks: one with a static “Next Step” button for advancing through subtasks at any time, and one with a responsive button that only appeared once the current subtask was completed. Analysis of students’ code quality showed that students in the responsive condition achieved higher quality code in later programming tasks. The results highlight design considerations and opportunities for adaptively supporting novices in block-based programming.}, booktitle={Proceedings - 2019 IEEE Blocks and Beyond Workshop, B and B 2019}, author={Rodriguez, F.J. and Smith, C.R. and Smith, A. and Boyer, K.E. and Wiebe, E.N. and Mott, B.W. and Lester, J.C.}, year={2019}, pages={9–13} }
 @inproceedings{psaradellis_muis_smith_lajoie_2018, title={Enhancing complex mathematics problem solving through learning by teaching with a teachable agent}, volume={2}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85056509594&partnerID=MN8TOARS}, booktitle={IMSCI 2018 - 12th International Multi-Conference on Society, Cybernetics and Informatics, Proceedings}, author={Psaradellis, C. and Muis, K.R. and Smith, A. and Lajoie, S.P.}, year={2018}, pages={31–36} }
 @article{geden_smith_campbell_amos-binks_mott_feng_lester_2018, title={Towards Adaptive Support for Anticipatory Thinking}, DOI={10.1145/3183654.3183665}, abstractNote={Adaptive training and support technologies have been used to improve training and performance in a number of domains. However, limited work on adaptive training has examined anticipatory thinking, which is the deliberate, divergent exploration and analysis of relevant futures to avoid surprise. Anticipatory thinking engages the process of imagining how uncertainties impact the future, helps identify leading indicators and causal dependencies of future scenarios, and complements forecasting, which focuses on assessing the likelihood of outcomes. It is particularly important for intelligence analysis, mission planning, and strategic forecasting, wherein practitioners apply prospective sense-making, scenario planning, and other methodologies to identify possible options and their effects during decision making processes. However, there is currently no underlying cognitive theory supporting specific anticipatory thinking methodologies, no adaptive technologies to support their training, and no existing measures to assess their efficacy. We are engaged in an ongoing effort to design adaptive technologies to support the acquisition and measurement of anticipatory thinking. As a first step toward adaptive environments that support the acquisition and application of anticipatory thinking competencies, we have developed a task to measure anticipatory thinking in which participants explore uncertainties and the impacts on the future given a particular topic. We present preliminary results from a study to examine the validity of this measure and discuss multiple factors that affect anticipatory thinking including attention, inhibitory control, need for cognition, need for closure, convergent thinking, and divergent thinking. We then introduce design principles for supporting training, application, and assessment of anticipatory thinking.}, journal={PROCEEDINGS OF THE TECHNOLOGY, MIND, AND SOCIETY CONFERENCE (TECHMINDSOCIETY'18)}, author={Geden, Michael and Smith, Andy and Campbell, James and Amos-Binks, Adam and Mott, Bradford and Feng, Jing and Lester, James}, year={2018} }
 @inproceedings{sawyer_smith_rowe_azevedo_lester_2017, title={Enhancing student models in game-based learning with facial expression recognition}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-85026767763&partnerID=MN8TOARS}, DOI={10.1145/3079628.3079686}, abstractNote={Recent years have seen a growing recognition of the role that affect plays in learning. Because game-based learning environments elicit a wide range of student affective states, affect-enhanced student modeling for game-based learning holds considerable promise. This paper introduces an affect-enhanced student modeling framework that leverages facial expression tracking for game-based learning. The affect-enhanced student modeling framework was used to generate predictive models of student learning and student engagement for students who interacted with CRYSTAL ISLAND, a game-based learning environment for microbiology education. Findings from the study reveal that the affect-enhanced student models significantly outperform baseline predictive student models that utilize the same gameplay traces but do not use facial expression tracking. The study also found that models based on individual facial action coding units are more effective than composite emotion models. The findings suggest that introducing facial expression tracking can improve the accuracy of student models, both for predicting student learning gains and also for predicting student engagement.}, booktitle={UMAP 2017 - Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization}, author={Sawyer, R. and Smith, A. and Rowe, J. and Azevedo, R. and Lester, J.}, year={2017}, pages={192–201} }
 @inbook{sawyer_smith_rowe_azevedo_lester_2017, title={Is More Agency Better? The Impact of Student Agency on Game-Based Learning}, volume={10331 LNAI}, ISBN={9783319614243 9783319614250}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-319-61425-0_28}, DOI={10.1007/978-3-319-61425-0_28}, abstractNote={Student agency has long been viewed as a critical element in game-based learning. Agency refers to the degree of freedom and control that a student has to perform meaningful actions in a learning environment. While long postulated to be central to student self-regulation, there is limited evidence on the design of game-based learning environments that promote student agency and its effect on learning. This paper reports on an experiment to investigate the impact of student agency on learning and problem-solving behavior in a game-based learning environment for microbiology. Students interacted with one of three versions of the system. In the High Agency condition, students could freely navigate the game's 3D open-world environment and perform problem-solving actions in any order they chose. In the Low Agency condition, students were required to traverse the environment and solve the mystery in a prescribed partially ordered sequence. In the No Agency condition, students watched a video of an expert playing the game by following an "ideal path" for solving the problem scenario. Results indicate that students in the Low Agency condition achieved greater learning gains than students in both the High Agency and No Agency conditions, but exhibited more unproductive behaviors, suggesting that artfully striking a balance between high and low agency best supports learning.}, booktitle={Lecture Notes in Computer Science}, publisher={Springer International Publishing}, author={Sawyer, Robert and Smith, Andy and Rowe, Jonathan and Azevedo, Roger and Lester, James}, year={2017}, pages={335–346} }
 @article{shelton_smith_wiebe_behrle_sirkin_lester_2016, title={Drawing and Writing in Digital Science Notebooks: Sources of Formative Assessment Data}, volume={25}, ISSN={1059-0145 1573-1839}, url={http://dx.doi.org/10.1007/S10956-016-9607-7}, DOI={10.1007/s10956-016-9607-7}, number={3}, journal={Journal of Science Education and Technology}, publisher={Springer Science and Business Media LLC}, author={Shelton, Angi and Smith, Andrew and Wiebe, Eric and Behrle, Courtney and Sirkin, Ruth and Lester, James}, year={2016}, month={Feb}, pages={474–488} }
 @inbook{smith_aksit_min_wiebe_mott_lester_2016, place={Cham, Switzerland}, title={Integrating Real-Time Drawing and Writing Diagnostic Models: An Evidence-Centered Design Framework for Multimodal Science Assessment}, volume={9684}, ISBN={9783319395821 9783319395838}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-319-39583-8_16}, DOI={10.1007/978-3-319-39583-8_16}, abstractNote={Interactively modeling science phenomena enables students to develop rich conceptual understanding of science. While this understanding is often assessed through summative, multiple-choice instruments, science notebooks have been used extensively in elementary and secondary grades as a mechanism to promote and reveal reflection through both drawing and writing. Although each modality has been studied individually, obtaining a comprehensive view of a student’s conceptual understanding requires analyses of knowledge represented across both modalities. Evidence-centered design (ECD) provides a framework for diagnostic measurement of data collected from student interactions with complex learning environments. This work utilizes ECD to analyze a corpus of elementary student writings and drawings collected with a digital science notebook. First, a competency model representing the core concepts of each exercise, as well as the curricular unit as a whole, was constructed. Then, evidence models were created to map between student written and drawn artifacts and the shared competency model. Finally, the scores obtained using the evidence models were used to train a deep-learning based model for automated writing assessment, as well as to develop an automated drawing assessment model using topological abstraction. The findings reveal that ECD provides an expressive unified framework for multimodal assessment of science learning with accurate predictions of student learning.}, booktitle={Intelligent Tutoring Systems}, publisher={Springer International Publishing}, author={Smith, Andy and Aksit, Osman and Min, Wookhee and Wiebe, Eric and Mott, Bradford W. and Lester, James C.}, editor={Micarelli, A. and Stamper, J. and Panourgia, K.Editors}, year={2016}, pages={165–175} }
 @inproceedings{smith_aksit_min_wiebe_mott_lester_2016, title={Integrating real-time drawing and writing diagnostic models: An evidence-centered design framework for multimodal science assessment}, volume={0684}, booktitle={Intelligent tutoring systems, its 2016}, author={Smith, A. and Aksit, O. and Min, W. and Wiebe, E. and Mott, B. W. and Lester, J. C.}, year={2016}, pages={165–175} }
 @inbook{smith_min_mott_lester_2015, title={Diagrammatic Student Models: Modeling Student Drawing Performance with Deep Learning}, volume={9146}, ISBN={9783319202662 9783319202679}, ISSN={0302-9743 1611-3349}, url={http://dx.doi.org/10.1007/978-3-319-20267-9_18}, DOI={10.1007/978-3-319-20267-9_18}, abstractNote={Recent years have seen a growing interest in the role that student drawing can play in learning. Because drawing has been shown to contribute to students’ learning and increase their engagement, developing student models to dynamically support drawing holds significant promise. To this end, we introduce diagrammatic student models, which reason about students’ drawing trajectories to generate a series of predictions about their conceptual knowledge based on their evolving sketches. The diagrammatic student modeling framework utilizes deep learning, a family of machine learning methods based on a deep neural network architecture, to reason about sequences of student drawing actions encoded with temporal and topological features. An evaluation of the deep-learning-based diagrammatic student models suggests that it can predict student performance more accurately and earlier than competitive baseline approaches.}, booktitle={Lecture Notes in Computer Science}, publisher={Springer International Publishing}, author={Smith, Andy and Min, Wookhee and Mott, Bradford W. and Lester, James C.}, year={2015}, pages={216–227} }
 @article{leeman-munk_smith_mott_wiebe_lester_2015, title={Two Modes Are Better Than One: A Multimodal Assessment Framework Integrating Student Writing and Drawing}, volume={9112}, ISBN={["978-3-319-19772-2"]}, ISSN={["1611-3349"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84948972893&partnerID=MN8TOARS}, DOI={10.1007/978-3-319-19773-9_21}, abstractNote={We are beginning to see the emergence of advanced automated assessment techniques that evaluate expressive student artifacts such as free-form written responses and sketches. These approaches have largely operated individually, each considering only a single mode. We hypothesize that there are synergies to be leveraged in multimodal assessments that can integrate multiple modalities of student responses to create a more complete and accurate picture of a student’s knowledge. In this paper, we introduce a novel multimodal assessment framework that integrates two techniques for automatically analyzing student artifacts: a deep learning-based model for assessing student writing, and a topology-based model for assessing student drawing. An evaluation of the framework with elementary students’ writing and drawing assessments demonstrate that 1) each of the framework’s two modalities provides an independent and complementary measure of student science learning, and 2) together, the multimodal framework significantly outperforms either uni-modal approach individually, demonstrating the potential synergistic benefits of multimodal assessment.}, journal={ARTIFICIAL INTELLIGENCE IN EDUCATION, AIED 2015}, author={Leeman-Munk, Samuel and Smith, Andy and Mott, Bradford and Wiebe, Eric and Lester, James}, year={2015}, pages={205–215} }
 @inproceedings{miller_smith_bahram_st. amant_2012, title={A glove for tapping and discrete 1D/2D input}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-84859938560&partnerID=MN8TOARS}, DOI={10.1145/2166966.2166986}, abstractNote={This paper describes a glove with which users enter input by tapping fingertips with the thumb or by rubbing the thumb over the palmar surfaces of the middle and index fingers. The glove has been informally tested as the controller for two semi-autonomous robots in a a 3D simulation environment. A preliminary evaluation of the glove's performance is presented.}, booktitle={International Conference on Intelligent User Interfaces, Proceedings IUI}, author={Miller, S.A. and Smith, A. and Bahram, S. and St. Amant, R.}, year={2012}, pages={101–104} }
 @article{smith_spontak_1999, title={P-methylstyrene}, journal={Polymer data handbook}, publisher={New York: Oxford University Press}, author={Smith, A. P. and Spontak, R. J.}, year={1999}, pages={688–695} }
 @article{smith_evans_davidian_1998, title={Statistical properties of fitted estimates of apparent in vivo metabolic constants obtained from gas uptake data. I. Lipophilic and slowly metabolized VOCs}, volume={10}, number={5}, journal={Inhalation Toxicology}, author={Smith, A. E. and Evans, M. V. and Davidian, M.}, year={1998}, pages={383–409} }
 @inproceedings{smith_min_mott_lester, title={Diagrammatic student models: Modeling student drawing performance with deep learning}, volume={9146}, booktitle={User modeling, adaptation and personalization}, author={Smith, A. and Min, W. and Mott, B. W. and Lester, J. C.}, pages={216–227} }
 @inproceedings{sawyer_smith_rowe_azevedo_lester, title={Is more agency better? The impact of student agency on game-based learning}, volume={10331}, booktitle={Artificial intelligence in education, aied 2017}, author={Sawyer, R. and Smith, A. and Rowe, J. and Azevedo, R. and Lester, J.}, pages={335–346} }