More Like this

1. Encouraging CS students to compute for social good through collaborative, community-engaged projects

   https://doi.org/10.1145/3447892.3447900  

   Pulimood, S. Monisha; Pearson, Kim; Bates, Diane (January 2021, ACM SIGCAS Computers and Society)

   Which pedagogical techniques better engage computer science (CS) students in computing for social good? We examine this question with students enrolled in classes using the Collaborating Across Boundaries to Engage Undergraduates in Computational Thinking (CABECT) pedagogical model, that pairs CS and non-CS courses with a community partner to propose solutions to a local problem. Pre- and post-tests of self-assessed concerns about civic responsibility, global responsibility, and local civic efficacy were administered to the students in a three-year long pedagogical experiment, which paired five CS courses with five journalism courses. While CS students were not statistically different from their journalism peers in pre-test measures of social and global responsibility, they lagged behind in local efficacy. In the posttest, CS students had significantly increased their sense of local efficacy to the extent that they were statistically indistinguishable from journalism students. Community-engaged learning projects, such as the one in the CABECT model, show great potential for attracting students to computing for social good. 

   more » « less
2. Supporting Students’ Science Content Knowledge and Motivation through Project-Based Inquiry (PBI) Global in a Cross-School Collaboration

   https://doi.org/10.3390/educsci12060412  

   Spires, Hiller A.; Himes, Marie P.; Krupa, Erin (June 2022, Education Sciences)

   Inquiry is featured prominently in the Next Generation Science Standards (NGSS) as a promising pedagogical approach. Building on current conceptions of inquiry, a mixed-methods research design was used to explore the effects of Project-Based Inquiry (PBI) Global on student science content knowledge, motivation, and perspectives related to inquiry in a cross-school collaboration. The data sources included pre-/post-tests on science content and student motivation (n = 75), transcripts from student focus groups (n = 26), and students’ multimodal learning products (n = 18 teams). The quantitative findings indicated School B students were more motivated by the project than School A students, which mirrored student performance. The student focus group findings generated three themes: constructing empathy, learning for impact, and navigating challenges. The discussion focuses on an integrated view of what students gained and did not gain from the PBI Global experience, including a nuanced explanation of how motivation and content knowledge may be influenced by student experiences and school contextual factors during PBI Global. Implications for instructional practice highlight how relationship building, mutual respect, and consensus making are essential components of constructing cross-school collaborations and the importance of integrating instructional frameworks with teachers and students. Future research will focus on investigating the effects of PBI Global on student learning in cross-school partnerships through experimental-designed studies, and the systemic and structural barriers to scaling cross-school inquiry-based learning. 

   more » « less
3. Leveraging Deep Reinforcement Learning for Pedagogical Policy Induction in an Intelligent Tutoring System

   Ausin, M. S. (January 2019, In: Proceedings of the 12th International Conference on Educational Data Mining (EDM 2019),)

   Deep Reinforcement Learning (DRL) has been shown to be a very powerful technique in recent years on a wide range of applications. Much of the prior DRL work took the online learning approach. However, given the challenges of building accurate simulations for modeling student learning, we investigated applying DRL to induce a pedagogical policy through an offiine approach. In this work, we explored the effectiveness of offiine DRL for pedagogical policy induction in an Intelligent Tutoring System. Generally speaking, when applying offiine DRL, we face two major challenges: one is limited training data and the other is the credit assignment problem caused by delayed rewards. In this work, we used Gaussian Processes to solve the credit assignment problem by estimating the inferred immediate rewards from the final delayed rewards. We then applied the DQN and Double-DQN algorithms to induce adaptive pedagogical strategies tailored to individual students. Our empirical results show that without solving the credit assignment problem, the DQN policy, although better than Double-DQN, was no better than a random policy. However, when combining DQN with the inferred rewards, our best DQN policy can outperform the random yet reasonable policy, especially for students with high pre-test scores. 

   more » « less
4. Enhancing Engagement Modeling in Game-Based Learning Environments with Student-Agent Discourse Analysis

   https://doi.org/10.1007/978-3-031-36336-8_105  

   Goslen, A; Henderson, N; Rowe, J; Zhang, J; Hutt, S; Ocumpaugh, J; Wiebe, E; Boyer, K; Mott, B; Lester, J (June 2023, Proceedings of the 24th International Conference on Artificial Intelligence in Education)

   Pedagogical agents offer significant promise for engaging students in learning. In this paper, we investigate students’ conversational interactions with a pedagogical agent in a game-based learning environment for middle school sci- ence education. We utilize word embeddings of student-agent conversations along with features distilled from students’ in-game actions to induce predictive models of student engagement. An evaluation of the models’ accuracy and early prediction performance indicates that features derived from students’ conversa- tions with the pedagogical agent yield the highest accuracy for predicting student engagement. Results also show that combining student problem-solving features and conversation features yields higher performance than a problem solving-only feature set. Overall, the findings suggest that student-agent conversations can greatly enhance student models for game-based learning environments. 

   more » « less
5. Visual Literacy Intervention for Improving Undergraduate Student Critical Thinking of Global Sustainability Issues

   https://doi.org/10.3390/su122310209  

   Krejci, Sarah E.; Ramroop-Butts, Shirma; Torres, Hector N.; Isokpehi, Raphael D. (December 2020, Sustainability)

   null (Ed.)

   The promotion of global sustainability within environmental science courses requires a paradigm switch from knowledge-based teaching to teaching that stimulates higher-order cognitive skills. Non-major undergraduate science courses, such as environmental science, promote critical thinking in students in order to improve the uptake of scientific information and develop the rational decision making used to make more informed decisions. Science, engineering, technology and mathematics (STEM) courses rely extensively on visuals in lectures, readings and homework to improve knowledge. However, undergraduate students do not automatically acquire visual literacy and a lack of intervention from instructors could be limiting academic success. In this study, a visual literacy intervention was developed and tested in the face-to-face (FTF) and online sections of an undergraduate non-major Introduction to Environmental Science course. The intervention was designed to test and improve visual literacy at three levels: (1) elementary—identifying values; (2) intermediate—identifying trends; and (3) advanced—using the data to make projections or conclusions. Students demonstrated a significant difference in their ability to answer elementary and advanced visual literacy questions in both course sections in the pre-test and post-test. Students in the face-to-face course had significantly higher exam scores and higher median assessment scores compared to sections without a visual literacy intervention. The online section did not show significant improvements in visual literacy or academic success due to a lack of reinforcement of visual literacy following the initial intervention. The visual literacy intervention shows promising results in improving student academic success and should be considered for implementation in other general education STEM courses. 

   more » « less