skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Integrating Dynamic Supports into an Equity Teaching Simulation to Promote Equity Mindsets
Implementing high-quality professional learning on diversity, equity, and inclusion (DEI) issues is a massive scaling challenge. Integrating dynamic support using natural language processing (NLP) into equity teaching simulations may allow for more responsive, personalized training in this field. In this study, we trained machine learning models on participants’ text responses in an equity teaching simulation (494 users; 988 responses) to detect certain text features related to equity. We then integrated these models into the simulation to provide dynamic supports to users during the simulation. In a pilot study (N = 13), we found users largely thought the feedback was accurate and incorporated the feedback in subsequent simulation responses. Future work will explore replicating these results with larger and more representative samples  more » « less
Award ID(s):
1917668
PAR ID:
10330903
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
L@S '22: Proceedings of the Ninth ACM Conference on Learning @ Scale
Page Range / eLocation ID:
364 to 367
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, 23rd Annual Conference on Research in Undergraduate Mathematics Education (RUME))
    Karunakaran, Shiv Smith; Reed, Zackery; Higgins, Abigail (Ed.)
    Promoting equity in undergraduate mathematics education is of vital importance, yet has received considerably less attention than equity in K-12 mathematics. The current study focuses on a pedagogical training program for graduate teaching assistants’ (GTAs), which emphasizes equity in their teaching of undergraduates. The study examines GTAs’ journals and open-ended survey responses, including their definitions of equity and the ways they promote equity in their classrooms. The research will foster discourse about ways of promoting equity in undergraduate mathematics and about professional development for undergraduate mathematics instructors. 
    more » « less
  2. ; ; (, Gender, Work & Organization)
    Abstract In this paper, we theorize the intersectional gendered impacts of COVID‐19 on faculty labor, with a particular focus on how institutions of higher education in the United States evaluate faculty labor amidst the COVID‐19 transition and beyond. The pandemic has disrupted faculty research, teaching, and service in differential ways, having larger impacts on women faculty, faculty of color, and caregiving faculty in ways that further reflect the intersections of these groups. Universities have had to reconsider how evaluation occurs, given the impact of these disruptions on faculty careers. Through a case study of university pandemic responses in the United States, we summarize key components of how colleges and universities shifted evaluations of faculty labor in response to COVID‐19, including suspending teaching evaluations, implementing tenure delays, and allowing for impact statements in faculty reviews. While most institutional responses recenter neoliberal principles of the ideal academic worker that is both gendered and racialized, a few universities have taken more innovative approaches to better attend to equity concerns. We conclude by suggesting arecalibrationof the faculty evaluation system – one that maintains systematic faculty reviews and allows for academic freedom, but requires universities to take a more contextualized approach to evaluation in ways that center equity and inclusion for women faculty and faculty of color for the long term. 
    more » « less
  3. ; (, TRB)
    Penalty-based strategies, such as congestion pricing, have been employed to improve traffic network efficiency, but they face criticism for their negative impact on users and equity concerns. Collaborative routing, which allows users to negotiate route choices, offers a solution that considers individual heterogeneity. Personalized incentives can encourage such collaboration and are more politically acceptable than penalties. This study proposes a collaborative routing strategy that uses personalized incentives to guide users towards desired traffic states while promoting multidimensional equity. Three equity dimensions are considered: accessibility equity (equal access to jobs, services, and education), inclusion equity (route suggestions and incentives that do not favor specific users), and utility equity (envy-free solutions where no user feels others have more valuable incentives). The strategy prioritizes equitable access to societal services and activities, ensuring accessibility equity in routing solutions. Inclusion equity is maintained through non-negative incentives that consider user heterogeneity without excluding anyone. An envy-free compensation mechanism achieves utility equity by eliminating envy over incentive-route bundles. A constrained traffic assignment (CTA) formulation and consensus optimization variant are then devised to break down the centralized problem into smaller, manageable parts and a decentralized algorithm is developed for scalability in large transportation networks and user populations. Numerical studies investigate the model's enhancement of equity dimensions and the impact of hyperparameters on system objective tradeoffs and demonstrate the algorithm convergence. 
    more » « less
  4. ; (, Science Education)
    In this paper, we outline how science teachers might engage in the work of creating educational equity. While acknowledging the historical inherent inequities associated with issues of access, opportunities to engage in science learning for individuals of marginalized identities (e.g., BIPOC individuals and women), and achievement, we broaden this definition to include social justice as a framework by which we can develop opportunities for the fostering of students' affinity identities with science. To this end, we draw on theorizations of equity within educational research, specifically discussed as excellence, equality, fairness, a zero-sum game, and most recently, social justice. Additionally, we utilize McKinney de Royston and Nasir's (2017) Racialized Learning Ecologies framework. This framework provides a useful lens to notice the layers of (in)equity within education. We then extend this ecological model into science education and present three lenses (i.e., layers) through which equity operates within science teaching and learning. We conclude with a discussion of the practical implications of doing the work of equity, that is, recognizing, interpreting, and redressing inequity in science classrooms. Ultimately, we provide an actionable definition of equity that has the potential to facilitate transformative and socially just science teaching and learning. 
    more » « less
  5. ; (, me: Proceedings of the Second Workshop on Bridging Human-Computer Interaction and Natural Language Processing)
    Motivated by prior literature, we provide a proof of concept simulation study for an understudied interactive machine learning method, machine teaching (MT), for the text-based emotion prediction task. We compare this method experimentally against a more well-studied technique, active learning (AL). Results show the strengths of both approaches over more resource-intensive offline supervised learning. Additionally, applying AL and MT to fine-tune a pre-trained model offers further efficiency gain. We end by recommending research directions which aim to empower users in the learning process. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email