arXiv subjects

Tiffany Barnes

Publications and source records attributed to Tiffany Barnes.

At least 37 records · Page 2Linked to original sources

arXiv2025

LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters

Large language models (LLMs) are rapidly reshaping software development, but their impact across the software development lifecycle is underexplored. Existing work focuses on isolated activities such as code generation or testing, leaving open questions about how LLMs affect developers, processes, products, and the software ecosystem. We address this gap through semi-structured interviews with sixteen early-adopter software professionals who integrated LLM-based tools into their day-to-day work in early to mid-2023. We treat these interviews as early empirical evidence and compare participants' accounts with recent work on LLMs in software engineering, noting which early patterns persist or shift. Using thematic analysis, we organize findings around four dimensions: people, process, product, and society. Developers reported substantial productivity gains from reducing routine tasks, streamlining search, and accelerating debugging, but also described a productivity-quality paradox: they often discarded generated code and shifted effort from writing to critically evaluating and integrating it. LLM use was highly phase-dependent, with strong uptake in implementation and debugging but limited influence on requirements gathering and other collaborative work. Participants developed new competencies to use LLMs effectively, including prompt engineering strategies, layered verification, and secure integration to protect proprietary data. They anticipated changes in hiring expectations, team practices, and computing education, while emphasizing that human judgment and foundational software engineering skills remain essential. Our findings, later echoed in large-scale quantitative studies, offer actionable implications for developers, organizations, educators, and tool designers seeking to integrate LLMs responsibly into software practice today.

cs.SE↗

arXiv2025

The promise and limits of LLMs in constructing proofs and hints for logic problems in intelligent tutoring systems

Intelligent tutoring systems have demonstrated effectiveness in teaching formal propositional logic proofs, but their reliance on template-based explanations limits their ability to provide personalized student feedback. While large language models (LLMs) offer promising capabilities for dynamic feedback generation, they risk producing hallucinations or pedagogically unsound explanations. We evaluated the stepwise accuracy of LLMs in constructing multi-step symbolic logic proofs, comparing six prompting techniques across four state-of-the-art LLMs on 358 propositional logic problems. Results show that DeepSeek-V3 achieved superior performance up to 86.7% accuracy on stepwise proof construction and excelled particularly in simpler rules. We further used the best-performing LLM to generate explanatory hints for 1,050 unique student problem-solving states from a logic ITS and evaluated them on 4 criteria with both an LLM grader and human expert ratings on a 20% sample. Our analysis finds that LLM-generated hints were 75% accurate and rated highly by human evaluators on consistency and clarity, but did not perform as well explaining why the hint was provided or its larger context. Our results demonstrate that LLMs may be used to augment tutoring systems with logic tutoring hints, but require additional modifications to ensure accuracy and pedagogical appropriateness.

cs.AI↗

arXiv2025

Investigating the Impact and Student Perceptions of Guided Parsons Problems for Learning Logic with Subgoals

Parsons problems (PPs) have shown promise in structured problem solving by providing scaffolding that decomposes the problem and requires learners to reconstruct the solution. However, some students face difficulties when first learning with PPs or solving more complex Parsons problems. This study introduces Guided Parsons problems (GPPs) designed to provide step-specific hints and improve learning outcomes in an intelligent logic tutor. In a controlled experiment with 76 participants, GPP students achieved significantly higher accuracy of rule application in both level-end tests and post-tests, with the strongest gains among students with lower prior knowledge. GPP students initially spent more time in training (1.52 vs. 0.81 hours) but required less time for post-tests, indicating improved problem solving efficiency. Our thematic analysis of GPP student self-explanations revealed task decomposition, better rule understanding, and reduced difficulty as key themes, while some students felt the structured nature of GPPs restricted their own way of reasoning. These findings reinforce that GPPs can effectively combine the benefits of worked examples and problem solving practice, but could be further improved by individual adaptation.

cs.HC↗

arXiv2023

Bridging Declarative, Procedural, and Conditional Metacognitive Knowledge Gap Using Deep Reinforcement Learning

In deductive domains, three metacognitive knowledge types in ascending order are declarative, procedural, and conditional learning. This work leverages Deep Reinforcement Learning (DRL) in providing adaptive metacognitive interventions to bridge the gap between the three knowledge types and prepare students for future learning across Intelligent Tutoring Systems (ITSs). Students received these interventions that taught how and when to use a backward-chaining (BC) strategy on a logic tutor that supports a default forward-chaining strategy. Six weeks later, we trained students on a probability tutor that only supports BC without interventions. Our results show that on both ITSs, DRL bridged the metacognitive knowledge gap between students and significantly improved their learning performance over their control peers. Furthermore, the DRL policy adapted to the metacognitive development on the logic tutor across declarative, procedural, and conditional students, causing their strategic decisions to be more autonomous.

cs.CY↗

arXiv2023

Leveraging Deep Reinforcement Learning for Metacognitive Interventions across Intelligent Tutoring Systems

This work compares two approaches to provide metacognitive interventions and their impact on preparing students for future learning across Intelligent Tutoring Systems (ITSs). In two consecutive semesters, we conducted two classroom experiments: Exp. 1 used a classic artificial intelligence approach to classify students into different metacognitive groups and provide static interventions based on their classified groups. In Exp. 2, we leveraged Deep Reinforcement Learning (DRL) to provide adaptive interventions that consider the dynamic changes in the student's metacognitive levels. In both experiments, students received these interventions that taught how and when to use a backward-chaining (BC) strategy on a logic tutor that supports a default forward-chaining strategy. Six weeks later, we trained students on a probability tutor that only supports BC without interventions. Our results show that adaptive DRL-based interventions closed the metacognitive skills gap between students. In contrast, static classifier-based interventions only benefited a subset of students who knew how to use BC in advance. Additionally, our DRL agent prepared the experimental students for future learning by significantly surpassing their control peers on both ITSs.

cs.CY↗

arXiv2023

Preparing Unprepared Students For Future Learning

Based on strategy-awareness (knowing which problem-solving strategy to use) and time-awareness (knowing when to use it), students are categorized into Rote (neither type of awareness), Dabbler (strategy-aware only) or Selective (both types of awareness). It was shown that Selective is often significantly more prepared for future learning than Rote and Dabbler (Abdelshiheed et al., 2020). In this work, we explore the impact of explicit strategy instruction on Rote and Dabbler students across two domains: logic and probability. During the logic instruction, our logic tutor handles both Forward-Chaining (FC) and Backward-Chaining (BC) strategies, with FC being the default; the Experimental condition is taught how to use BC via worked examples and when to use it via prompts. Six weeks later, all students are trained on a probability tutor that supports BC only. Our results show that Experimental significantly outperforms Control in both domains, and Experimental Rote catches up with Selective.

cs.HC↗

arXiv2023

The Power of Nudging: Exploring Three Interventions for Metacognitive Skills Instruction across Intelligent Tutoring Systems

Deductive domains are typical of many cognitive skills in that no single problem-solving strategy is always optimal for solving all problems. It was shown that students who know how and when to use each strategy (StrTime) outperformed those who know neither and stick to the default strategy (Default). In this work, students were trained on a logic tutor that supports a default forward-chaining and a backward-chaining (BC) strategy, then a probability tutor that only supports BC. We investigated three types of interventions on teaching the Default students how and when to use which strategy on the logic tutor: Example, Nudge and Presented. Meanwhile, StrTime students received no interventions. Overall, our results show that Nudge outperformed their Default peers and caught up with StrTime on both tutors.

cs.HC↗

arXiv2023

Mixing Backward- with Forward-Chaining for Metacognitive Skill Acquisition and Transfer

Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy-and time-aware (StrTime) outperformed their nonStrTime peers across deductive domains. In this work, students were trained on a logic tutor that supports a default forward-chaining (FC) and a backward-chaining (BC) strategy. We investigated the impact of mixing BC with FC on teaching strategy- and time-awareness for nonStrTime students. During the logic instruction, the experimental students (Exp) were provided with two BC worked examples and some problems in BC to practice how and when to use BC. Meanwhile, their control (Ctrl) and StrTime peers received no such intervention. Six weeks later, all students went through a probability tutor that only supports BC to evaluate whether the acquired metacognitive skills are transferred from logic. Our results show that on both tutors, Exp outperformed Ctrl and caught up with StrTime.

cs.HC↗

arXiv2023

Metacognition and Motivation: The Role of Time-Awareness in Preparation for Future Learning

In this work, we investigate how two factors, metacognitive skills and motivation, would impact student learning across domains. More specifically, our primary goal is to identify the critical, yet robust, interaction patterns of these two factors that would contribute to students' performance in learning logic first and then their performance on a subsequent new domain, probability. We are concerned with two types of metacognitive skills: strategy-awareness and time-awareness, that is, which problem-solving strategy to use and when to use it. Our data were collected from 495 participants across three consecutive semesters, and our results show that the only students who consistently outperform their peers across both domains are those who are not only highly motivated but also strategy-aware and time-aware.

cs.HC↗

arXiv2023

Assessing Competency Using Metacognition and Motivation: The Role of Time-Awareness in Preparation for Future Learning

One fundamental goal of learning is preparation for future learning (PFL) and being able to extend acquired skills and problem-solving strategies to different domains and environments. While substantial research has shown that PFL can be accelerated by obtaining metacognitive skills or influenced by the individual's motivation, no prior work investigated whether the interaction of the two factors could assess students' competency for PFL. In this chapter, we tackle this research question in one type of highly interactive e-learning environment, intelligent tutoring systems. More specifically, we investigate whether the combination of metacognitive skills and motivation would assess students' learning abilities in logic, and their competence to extend these abilities to a subsequent domain, probability.

cs.HC↗

arXiv2022

Investigating the Impact of Backward Strategy Learning in a Logic Tutor: Aiding Subgoal Learning towards Improved Problem Solving

Learning to derive subgoals reduces the gap between experts and students and makes students prepared for future problem solving. Researchers have explored subgoal labeled instructional materials with explanations in traditional problem solving and within tutoring systems to help novices learn to subgoal. However, only a little research is found on problem-solving strategies in relationship with subgoal learning. Also, these strategies are under-explored within computer-based tutors and learning environments. Backward problem-solving strategy is closely related to the process of subgoaling, where problem solving iteratively refines the goal into a new subgoal to reduce difficulty. In this paper, we explore a training strategy for backward strategy learning within an intelligent logic tutor that teaches logic proof construction. The training session involved backward worked examples (BWE) and problem-solving (BPS) to help students learn backward strategy towards improving their subgoaling and problem-solving skills. To evaluate the training strategy, we analyzed students' 1) experience with and engagement in learning backward strategy, 2) performance, and 3) proof construction approaches in new problems that they solved independently without tutor help after each level of training and in post-test. Our results showed that, when new problems were given to solve without any tutor help, students who were trained with both BWE and BPS outperformed students who received none of the treatment or only BWE during training. Additionally, students trained with both BWE and BPS derived subgoals during proof construction with significantly higher efficiency than the other two groups.

cs.CY↗

arXiv2022

A Multicriteria Evaluation for Data-Driven Programming Feedback Systems: Accuracy, Effectiveness, Fallibility, and Students' Response

Data-driven programming feedback systems can help novices to program in the absence of a human tutor. Prior evaluations showed that these systems improve learning in terms of test scores, or task completion efficiency. However, crucial aspects which can impact learning or reveal insights important for future improvement of such systems are ignored in these evaluations. These aspects include inherent fallibility of current state-of-the-art, students' programming behavior in response to correct/incorrect feedback, and effective/ineffective system components. Consequently, a great deal of knowledge is yet to be discovered about such systems. In this paper, we apply a multi-criteria evaluation with 5 criteria on a data-driven feedback system integrated within a block-based novice programming environment. Each criterion in the evaluation reveals a unique pivotal aspect of the system: 1) How accurate the feedback system is; 2) How it guides students throughout programming tasks; 3) How it helps students in task completion; 4) What happens when it goes wrong; and 5) How students respond generally to the system. Our evaluation results showed that the system was helpful to students due to its effective design and feedback representation despite being fallible. However, novices can be negatively impacted by this fallibility due to high reliance and lack of self-evaluation. The negative impacts include increased working time, implementation, or submission of incorrect/partially correct solutions. The evaluation results reinforced the necessity of multi-criteria system evaluations while revealing important insights helpful to ensuring proper usage of data-driven feedback systems, designing fallibility mitigation steps, and driving research for future improvement.

cs.CY↗

arXiv2022

Enhancing a Student Productivity Model for Adaptive Problem-Solving Assistance

Research on intelligent tutoring systems has been exploring data-driven methods to deliver effective adaptive assistance. While much work has been done to provide adaptive assistance when students seek help, they may not seek help optimally. This had led to the growing interest in proactive adaptive assistance, where the tutor provides unsolicited assistance upon predictions of struggle or unproductivity. Determining when and whether to provide personalized support is a well-known challenge called the assistance dilemma. Addressing this dilemma is particularly challenging in open-ended domains, where there can be several ways to solve problems. Researchers have explored methods to determine when to proactively help students, but few of these methods have taken prior hint usage into account. In this paper, we present a novel data-driven approach to incorporate students' hint usage in predicting their need for help. We explore its impact in an intelligent tutor that deals with the open-ended and well-structured domain of logic proofs. We present a controlled study to investigate the impact of an adaptive hint policy based on predictions of HelpNeed that incorporate students' hint usage. We show empirical evidence to support that such a policy can save students a significant amount of time in training, and lead to improved posttest results, when compared to a control without proactive interventions. We also show that incorporating students' hint usage significantly improves the adaptive hint policy's efficacy in predicting students' HelpNeed, thereby reducing training unproductivity, reducing possible help avoidance, and increasing possible help appropriateness (a higher chance of receiving help when it was likely to be needed). We conclude with suggestions on the domains that can benefit from this approach as well as the requirements for adoption.

cs.AI↗

arXiv2022

Code-DKT: A Code-based Knowledge Tracing Model for Programming Tasks

Knowledge tracing (KT) models are a popular approach for predicting students' future performance at practice problems using their prior attempts. Though many innovations have been made in KT, most models including the state-of-the-art Deep KT (DKT) mainly leverage each student's response either as correct or incorrect, ignoring its content. In this work, we propose Code-based Deep Knowledge Tracing (Code-DKT), a model that uses an attention mechanism to automatically extract and select domain-specific code features to extend DKT. We compared the effectiveness of Code-DKT against Bayesian and Deep Knowledge Tracing (BKT and DKT) on a dataset from a class of 50 students attempting to solve 5 introductory programming assignments. Our results show that Code-DKT consistently outperforms DKT by 3.07-4.00% AUC across the 5 assignments, a comparable improvement to other state-of-the-art domain-general KT models over DKT. Finally, we analyze problem-specific performance through a set of case studies for one assignment to demonstrate when and how code features improve Code-DKT's predictions.

cs.SE↗

arXiv2021

Designing a Dashboard for Student Teamwork Analysis

Classroom dashboards are designed to help instructors effectively orchestrate classrooms by providing summary statistics, activity tracking, and other information. Existing dashboards are generally specific to an LMS or platform and they generally summarize individual work, not group behaviors. However, CS courses typically involve constellations of tools and mix on- and offline collaboration. Thus, cross-platform monitoring of individuals and teams is important to develop a full picture of the class. In this work, we describe our work on Concert, a data integration platform that collects data about student activities from several sources such as Piazza, My Digital Hand, and GitHub and uses it to support classroom monitoring through analysis and visualizations. We discuss team visualizations that we have developed to support effective group management and to help instructors identify teams in need of intervention.

cs.CY↗

arXiv2021

Novices' Learning Barriers When Using Code Examples in Open-Ended Programming

Open-ended programming increases students' motivation by allowing them to solve authentic problems and connect programming to their own interests. However, such open-ended projects are also challenging, as they often encourage students to explore new programming features and attempt tasks that they have not learned before. Code examples are effective learning materials for students and are well-suited to supporting open-ended programming. However, there is little work to understand how novices learn with examples during open-ended programming, and few real-world deployments of such tools. In this paper, we explore novices' learning barriers when interacting with code examples during open-ended programming. We deployed Example Helper, a tool that offers galleries of code examples to search and use, with 44 novice students in an introductory programming classroom, working on an open-ended project in Snap. We found three high-level barriers that novices encountered when using examples: decision, search and integration barriers. We discuss how these barriers arise and design opportunities to address them.

cs.HC↗

arXiv2021

The Impact of Looking Further Ahead: A Comparison of Two Data-driven Unsolicited Hint Types on Performance in an Intelligent Data-driven Logic Tutor

Research has shown assistance can provide many benefits to novices lacking the mental models needed for problem solving in a new domain. However, varying approaches to assistance, such as subgoals and next-step hints, have been implemented with mixed results. Next-Step hints are common in data-driven tutors due to their straightforward generation from historical student data, as well as research showing positive impacts on student learning. However, there is a lack of research exploring the possibility of extending data-driven methods to provide higher-level assistance. Therefore, we modified our data-driven Next-Step hint generator to provide Waypoints, hints that are a few steps ahead, representing problem-solving subgoals. We hypothesized that Waypoints would benefit students with high prior knowledge, and that Next-Step hints would most benefit students with lower prior knowledge. In this study, we investigated the influence of data-driven hint type, Waypoints versus Next-Step hints, on student learning in a logic proof tutoring system, Deep Thought, in a discrete mathematics course. We found that Next-Step hints were more beneficial for the majority of students in terms of time, efficiency, and accuracy on the posttest. However, higher totals of successfully used Waypoints were correlated with improvements in efficiency and time in the posttest. These results suggest that Waypoint hints could be beneficial, but more scaffolding may be needed to help students follow them.

cs.HC↗

arXiv2020

Avoiding Help Avoidance: Using Interface Design Changes to Promote Unsolicited Hint Usage in an Intelligent Tutor

Within intelligent tutoring systems, considerable research has investigated hints, including how to generate data-driven hints, what hint content to present, and when to provide hints for optimal learning outcomes. However, less attention has been paid to how hints are presented. In this paper, we propose a new hint delivery mechanism called "Assertions" for providing unsolicited hints in a data-driven intelligent tutor. Assertions are partially-worked example steps designed to appear within a student workspace, and in the same format as student-derived steps, to show students a possible subgoal leading to the solution. We hypothesized that Assertions can help address the well-known hint avoidance problem. In systems that only provide hints upon request, hint avoidance results in students not receiving hints when they are needed. Our unsolicited Assertions do not seek to improve student help-seeking, but rather seek to ensure students receive the help they need. We contrast Assertions with Messages, text-based, unsolicited hints that appear after student inactivity. Our results show that Assertions significantly increase unsolicited hint usage compared to Messages. Further, they show a significant aptitude-treatment interaction between Assertions and prior proficiency, with Assertions leading students with low prior proficiency to generate shorter (more efficient) posttest solutions faster. We also present a clustering analysis that shows patterns of productive persistence among students with low prior knowledge when the tutor provides unsolicited help in the form of Assertions. Overall, this work provides encouraging evidence that hint presentation can significantly impact how students use them and using Assertions can be an effective way to address help avoidance.

cs.AI↗