More Like this

1. ConflLlama: Domain-specific adaptation of large language models for conflict event classification

   https://doi.org/10.1177/20531680251356282  

   Meher, Shreyas; Brandt, Patrick_T (July 2025, Research & Politics)

   We present ConflLlama, demonstrating how efficient fine-tuning of large language models can advance automated classification tasks in political science research. While classification of political events has traditionally relied on manual coding or rigid rule-based systems, modern language models offer the potential for more nuanced, context-aware analysis. However, deploying these models requires overcoming significant technical and resource barriers. We demonstrate how to adapt open-source language models to specialized political science tasks, using conflict event classification as our proof of concept. Through quantization and efficient fine-tuning techniques, we show state-of-the-art performance while minimizing computational requirements. Our approach achieves a macro-averaged AUC of 0.791 and a weighted F1-score of 0.753, representing a 37.6% improvement over the base model, with accuracy gains of up to 1463% in challenging classifications. We offer a roadmap for political scientists to adapt these methods to their own research domains, democratizing access to advanced NLP capabilities across the discipline. This work bridges the gap between cutting-edge AI developments and practical political science research needs, enabling broader adoption of these powerful analytical tools. 

   more » « less
2. How to Support Career Technical Instructors to Develop Students' Professional Skills: Research Brief

   Lundh, P; Yarnall, L; Smith, E; Krishnamachari, A; Griffiths, R (July 2024, NA)

   NA (Ed.)

   Project GOALS (Greater Opportunities to Advance Lifelong Success), an NSF Advanced Technological Education targeted research project, brought together researchers and community college educators from 2020 through 2024 to co-develop, test, package, and distribute resources for developing technicians' professional skills. Through this work, the team discovered the barriers that hinder both instructors and students from connecting around professional skills development. To address these barriers, the Project GOALS team developed an instructional framework grounded in research that integrates focused low-stakes activities into classes as students work toward their technical certificates. Based on our research, we believe Project GOALS provides ways for students to students' career readiness. In this research brief, the team describes how the Project GOALS co-development collaboration revealed the supports that technical instructors need to build students' professional awareness and reflection habits. Through qualitative analysis, Project GOALS researchers discovered the challenges that prevent many instructors from sharing their honest assessments of students' professional skills. The brief describes findings and recommends ways that community colleges can provide the assistance and resources that instructors need to develop students' professional skills. 

   more » « less
3. Understanding Student Conceptualizations of the Market Context in Engineering Design

   https://doi.org/10.18260/1-2--35426  

   Hoffenson, Steven; Pitterson, Nicole; Driscoll, Jessica (June 2020, American Society of Engineering Education 2020)

   Research has shown that engineering students are graduating without all of the skills that they need to succeed in professional engineering practice. While undergraduate engineering programs emphasize technical design and analysis, they generally do not adequately teach or discuss marketability, and evidence suggests that engineering students are graduating without a sufficient grasp of the bigger picture of design. This is reinforced by the available tools for use in engineering education, which are highly focused on ensuring technical feasibility, and a corresponding lack of tools for engineers to explore other design needs. At the same time, research in engineering design has resulted in new market-driven design techniques, which provide guidance for design practitioners regarding how to develop products that are both technically sound and marketable. However, this concept of market-driven design has not yet been widely integrated into engineering curricula. By exploring how current students conceptualize design, this study seeks to contribute to a more balanced perspective on design in undergraduate engineers that accounts for both technical feasibility and market needs. In this paper, we examine third-year Engineering Management students’ mental models of design prior to and after a project-based design course that emphasizes market-driven design concepts and tools. The fundamental research questions are: (1) To what extent do undergraduate engineering students' initial conceptions of design account for the market context, such as competition and consumer considerations? (2) In what ways do these design conceptions change after introducing market-driven design techniques and tools in a design course? Using concept mapping exercises (pre- and post-course), open-ended reflection assignments, surveys, and an assessment of project performance, we reveal how students conceive of and learn about the market context as an integral part of the design process. This contributes to insights regarding how students conceptually balance the technical and non-technical elements of design, as well as evidence regarding the value of a constructivism-based educational approach to advancing student understanding of market-driven design. The results provide a foundational understanding and recommendations regarding holistic design education for engineers in order to reduce the school to work transition gap. 

   more » « less
4. Student use of three registers for representing set relationships to reason about logic in undergraduate transition to proof courses

   Dawkins, PC; Roh, KH; Bruner, O; Gonzalez, M (November 2024, Psychology in Mathematics Education - North America)

   In transition to proof courses for undergraduates, we conducted teaching experiments supporting students to learn logic and proofs rooted in set-based meanings. We invited students to reason about sets using three representational systems: set notation (including symbolic expressions and set-builder notation), mathematical statements (largely in English), and Euler diagrams. In this report, we share evidence regarding how these three representations provided students with tools for reasoning and communicating about set relationships to explore the logic of statements. By analyzing student responses to tasks that asked them to translate between the representational systems, we gain insight into the accessibility and productivity of these tools for such instruction. 

   more » « less
5. Computational musicking: music + coding as a hybrid practice

   https://doi.org/10.1080/0144929X.2024.2402533  

   Roberts, Cameron L; Horn, Michael S (March 2025, Behaviour & Information Technology)

   While there is a growing body of research that explores the integration of music and coding in learning environments, much of this work has either emphasized the technical aspects of computer language design or music as a motivational context within which to learn computer science concepts. In this paper, we report on a study in which five undergraduate students with experience in both music and coding completed two creative musical tasks: one using conventional instruments and tools and one using Python code in an online music + coding environment. Inspired by the work of Christopher Small (1998. Musicking: The Meanings of Performing and Listening. University Press of New England), we describe music + coding as a set of interlocking processes which we call computational musicking and explore how practices from both domains are reimagined in this new hybrid context. We introduce semiotic theories of translation and transcription to make sense of the computational musicking process and describe strategies that participants devised in their creative process. 

   more » « less