Search for: All records

Background and Context: Professional development (PD) programs for K-12 computer science teachers use surveys to measure teachers’ knowledge and attitudes while recognizing daily sentiment and emotion changes can be crucial for providing timely teacher support. Objective: We investigate approaches to compute sentiment and emotion scores automatically and identify associations between the scores and teachers’ performance. Method: We compute the scores from teachers’ assignments using a machine-assisted tool and measure score changes with standard deviation and linear regression slopes. Further, we compare the scores to teachers’ performance and post-PD qualitative survey results. Findings: We find significant associations between teachers’ sentiment and emotion scores and their performance across demographics. Additionally, we find significant associations that are not captured by post-PD qualitative surveys. Implications: The sentiment and emotion scores can viably reflect teachers’ performance and enrich our understanding of teachers’ learning behaviors. Further, the sentiment and emotion scores can complement conventional surveys with additional insights related to teachers’ learning performance. 

In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent's optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios. 

In open multiagent systems, the set of agents operating in the environment changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. Because an agent’s optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other’s presence, which can be enhanced through agents communicating about their presence in the environment. At the same time, communicative acts can also incur costs (e.g., consuming limited bandwidth), and thus an agent must tradeoff the benefits of enhanced coordination with the costs of communication. We present a new principled, decision-theoretic method in the context provided by the recent communicative interactive POMDP framework for planning in open agent settings that balances this tradeoff. Simulations of multiagent wildfire suppression problems demonstrate how communication can improve planning in open agent environments, as well as how agents tradeoff the benefits and costs of communication under different scenarios. 

Broadening participation in computer science (CS) for primary/elementary students is a growing movement, spurred by computing workforce demands and the need for younger students to develop skills in problem solving and critical/computational thinking. However, offering computer science instruction at this level is directly related to the availability of teachers prepared to teach the subject. Unfortunately, there are relatively few primary/elementary school teachers who have received formal training in computer science, and they often self-report a lack of CS subject matter expertise. Teacher development is a key factor to address these issues, and this paper describes professional development strategies and empirical impacts of a summer institute that included two graduate courses and a series of Saturday workshops during the subsequent academic year. Key elements included teaching a high-level programing language (Python and JavaScript), integrating CS content and pedagogy instruction, and involving both experienced K-12 CS teachers and University faculty as instructors. Empirical results showed that this carefully structured PD that incorporated evidence-based elements of sufficient duration, teacher active learning and collaboration, modeling, practice, and feedback can successfully impact teacher outcomes. Results showed significant gains in teacher CS knowledge (both pedagogy and content), self-efficacy, and perception of CS value. Moderating results - examining possible differential effects depending on teacher gender, years of teaching CS, and geographic locale - showed that the PD was successful with experienced and less experienced teachers, with teachers from both rural and urban locales, and with both males and females. 

Increasingly professional development (PD) programs have been designed and implemented for pre-service and in-service teachers to acquire CS content knowledge and CS pedagogy and instructional strategies for K-12 students. This paper reports on our adaptation, implementation and research program for K-8 CS teachers across a Midwestern state. More specifically, its PD program for K-8 CS teachers consists of a summer institute with two graduate courses and a series of Saturday workshops during the subsequent academic year. This paper focuses on the two summer courses: one on CS knowledge content including computational thinking, variables, conditionals, loops, arrays, functions, and algorithms, and one instructional strategies, student pedagogy, computer-aided education resources, and community building. We report our SWOT (Strengths, Weaknesses, Opportunities, Threats) analysis of the two summer institutes involving the two courses to identify what went well and what needed improvement. This paper also reviews best practices for summer PD. 

The Adapt, Implement, and Research at Nebraska (AIR@NE) project, funded by the NSF CSforAll Researcher-Practitioner Partnership (RPP) program, examines the adaptation of a validated K-8 Computer Science (CS) curriculum in diverse school districts statewide. Our Research-Practitioner Partnership is primarily between the University of Nebraska-Lincoln, the Lincoln Public Schools, and other diverse school districts across Nebraska. Our primary goal is to study and document how different districts, including rural, predominantly minority, and Native American reservation, adopt the curriculum and broaden participation in CS. In addition, the project is developing instructional capacity for K-8 CS education with diverse learners. Our research also adapts and develops teacher and student CS assessments, and documents case studies using design-based research methodology to show how an adaptive curriculum broadens CS participation. Our Professional Development (PD) program for K-8 CS teachers is comprehensive. It consists of three summer courses for each cohort and a series of workshops during the academic year. Of the three summer courses, two are administered in the first year for a cohort: (1) an introduction to computer science course where teachers learn fundamental CS topics and programming in a high-level programming language (e.g., Python), and engage in problem solving and practice computational thinking, and (2) a course in pedagogy for teachers to learn how to teach K-8 CS, including lesson designs, use of instructional resources such as dot-and-dash robots, and assessments. Then, the following academic year after the summer, the PD program holds a series of workshops on five separate Saturdays to support teacher implementation of their lesson modules during the academic year, reflect and improve on their lessons, reinforce on CS concepts and pedagogy techniques, review and adopt alternative instructional resources, and share insights. These Saturday workshops also facilitate further community building and resource sharing. The third course occurs in the second year for a cohort, involving dissemination of research results from the team to the teachers, opportunities to discuss new resources and approaches on teaching CS concepts and computational thinking, and sharing of experiences and insights after teachers have completed one academic year of teaching CS. Unlike the first two courses that are required of teachers, this third course is an opt-in course that combines more in- depth pedagogy and elements of leadership. Thus far, we have had two cohorts and used the design methodology to revise our PD program, making our design more robust based on the lessons learned over the two years. The course materials, assessment, and survey instruments have also been improved. While the project is on-going we have data to that indicates the impact of the work so far. There were significant pre-post gains for both cohorts in teachers’ knowledge of computer science concepts and computational thinking. Scores on the computational thinking assessment were higher than those for CS concepts, which was to be expected given their CS teaching experience. Moreover, in both cohorts, the teachers’ confidence in teaching CS improved significantly. 

Intertemporal choices involve assessing options with different reward amounts available at different time delays. The similarity approach to intertemporal choice focuses on judging how similar amounts and delays are. Yet we do not fully understand the cognitive process of how these judgments are made. Here, we use machine-learning algorithms to predict similarity judgments to (1) investigate which algorithms best predict these judgments, (2) assess which predictors are most useful in predicting participants’ judgments, and (3) determine the minimum number of judgments required to accurately predict future judgments. We applied eight algorithms to similarity judgments for reward amount and time delay made by participants in two data sets. We found that neural network, random forest, and support vector machine algorithms generated the highest out-of-sample accuracy. Though neural networks and support vector machines offer little clarity in terms of a possible process for making similarity judgments, random forest algorithms generate decision trees that can mimic the cognitive computations of human judgment making. We also found that the numerical difference between amount values or delay values was the most important predictor of these judgments, replicating previous work. Finally, the best performing algorithms such as random forest can make highly accurate predictions of judgments with relatively small sample sizes (~ 15), which will help minimize the numbers of judgments required to extrapolate to new value pairs. In summary, machine-learning algorithms provide both theoretical improvements to our understanding of the cognitive computations involved in similarity judgments and intertemporal choices as well as practical improvements in designing better ways of collecting data. 

In open agent systems, the set of agents that are cooperating or competing changes over time and in ways that are nontrivial to predict. For example, if collaborative robots were tasked with fighting wildfires, they may run out of suppressants and be temporarily unavailable to assist their peers. We consider the problem of planning in these contexts with the additional challenges that the agents are unable to communicate with each other and that there are many of them. Because an agent's optimal action depends on the actions of others, each agent must not only predict the actions of its peers, but, before that, reason whether they are even present to perform an action. Addressing openness thus requires agents to model each other's presence, which becomes computationally intractable with high numbers of agents. We present a novel, principled, and scalable method in this context that enables an agent to reason about others' presence in its shared environment and their actions. Our method extrapolates models of a few peers to the overall behavior of the many-agent system, and combines it with a generalization of Monte Carlo tree search to perform individual agent reasoning in many-agent open environments. Theoretical analyses establish the number of agents to model in order to achieve acceptable worst case bounds on extrapolation error, as well as regret bounds on the agent's utility from modeling only some neighbors. Simulations of multiagent wildfire suppression problems demonstrate our approach's efficacy compared with alternative baselines.