List of works - Paul Denny

"Like a Nesting Doll": Analyzing Recursion Analogies Generated by CS Students Using Large Language Models

scientific article published on 03 July 2024

A Comparison of Immediate and Scheduled Feedback in Introductory Programming Projects

scientific article published on 22 February 2022

A case study of multi-institutional contributing-student pedagogy

A comparison of peer and tutor feedback

A simple framework for interactive games in CS1

Activities, affordances and attitude

Advancing Automated Assessment Tools - Opportunities for Innovations in Upper-level Computing Courses: A Position Paper

scientific article published on 07 March 2024

All syntax errors are not equal

Analyzing Students' Preferences for LLM-Generated Analogies

scientific article published on 04 July 2024

Automated Assessment: Experiences From the Trenches

scientific article published on 19 January 2023

Automatic Generation of Programming Exercises and Code Explanations Using Large Language Models

Automating Personalized Parsons Problems with Customized Contexts and Concepts

scientific article published on 03 July 2024

BEST PAPER AT SIGCSE 2019 IN THE CS EDUCATION TRACK: First things first: providing metacognitive scaffolding for interpreting problem prompts

scholarly article

Chat Overflow: Artificially Intelligent Models for Computing Education - renAIssance or apocAIypse?

scientific article published on 30 June 2023

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

scientific article published on 11 May 2024

CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes

scientific article published on 06 February 2024

CodeWrite

Common logic errors made by novice programmers

Comparing Code Explanations Created by Students and Large Language Models

scientific article published on 30 June 2023

Comparing four contemporary statistical software tools for introductory data science and statistics in the social sciences

scientific article published on 25 June 2021

Constructive evaluation: a pedagogy of student-contributed assessment

Coverage of course topics in a student generated MCQ repository

Decoding Logic Errors: A Comparative Study on Bug Detection by Students and Large Language Models

scientific article published on 02 January 2024

Desirable Characteristics for AI Teaching Assistants in Programming Education

scientific article published on 03 July 2024

Discussing the Changing Landscape of Generative AI in Computing Education

scientific article published on 15 March 2024

Educator Experiences of Low Overhead Student Project Risk Management

scientific article published on 02 January 2024

Enhancing syntax error messages appears ineffectual

Evaluating Automatically Generated Contextualised Programming Exercises

scientific article published on 07 March 2024

Evaluating LLM-generated Worked Examples in an Introductory Programming Course

scientific article published on 02 January 2024

Evaluating a new exam question

Evaluating the Performance of Code Generation Models for Solving Parsons Problems With Small Prompt Variations

scientific article published on 30 June 2023

Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book

scientific article published on 03 March 2023

Explaining Code with a Purpose: An Integrated Approach for Developing Code Comprehension and Prompting Skills

scientific article published on 03 July 2024

Exploring How Novice Programming Students Have Experienced Digital Technology

scientific article published on 20 December 2023

Exploring the Difficulty of Faded Parsons Problems for Programming Education

scientific article published on 19 January 2023

Exploring the Effects of Contextualized Problem Descriptions on Problem Solving

scientific article published on 2 February 2021

First Steps Towards Predicting the Readability of Programming Error Messages

scientific article published on 03 March 2023

Getting By With Help From My Friends: Group Study in Introductory Programming Understood as Socially Shared Regulation

scientific article published on 3 August 2022

HandsUp: An In-Class Question Posing Tool

Improving complex task performance using a sequence of simple practice tasks

Instructor Perceptions of AI Code Generation Tools - A Multi-Institutional Interview Study

scientific article published on 07 March 2024

Ladebug: an online tool to help novice programmers improve their debugging skills

Mastery Learning in Computer Science Education

Mathematics, Computer Science and Career Inclinations — A Multi-Institutional Exploration

scientific article published on 19 November 2020

Metacognition and Self-Regulation in Programming Education: Theories and Exemplars of Use

scientific article published in 2022

More Than Meets the AI: Evaluating the performance of GPT-4 on Computer Graphics assessment questions

scientific article published on 02 January 2024

My AI Wants to Know if This Will Be on the Exam: Testing OpenAI’s Codex on CS2 Programming Exercises

scientific article published on 19 January 2023

Novice Reflections During the Transition to a New Programming Language

scientific article published on 22 February 2022

Objects Count so Count Objects!

On Using Gamification to Effectively Influence Student Activity in Online Learning Environments ⬇️

2017 doctoral thesis by Paul Denny at University of Auckland

On the comprehensibility of functional decomposition: An empirical study

scientific article published on 13 June 2024

On the differences between correct student solutions

Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge

scientific article published on 03 July 2024

Patterns of Student Help-Seeking When Using a Large Language Model-Powered Programming Assistant

scientific article published on 02 January 2024

PeerWise

Programming Is Hard - Or at Least It Used to Be

scientific article published on 03 March 2023

Promoting Early Engagement with Programming Assignments Using Scheduled Automated Feedback

scientific article published on 2 February 2021

Prompt Problems: A New Programming Exercise for the Generative AI Era

scientific article published on 07 March 2024

Prompting for Comprehension: Exploring the Intersection of Explain in Plain English Questions and Prompt Writing

scientific article published on 15 July 2024

Quality of peer assessment in CS1

Resources and Support for the Implementation of Digital Technologies in New Zealand Schools

Scientific Collaboration Network Analysis for Computing Education Conferences

scientific article published on 26 June 2021

Self-Regulation, Self-Efficacy, and Fear of Failure Interactions with How Novices Use LLMs to Solve Programming Problems

scientific article published on 03 July 2024

Self-predicted and actual performance in an introductory programming course

Solving Proof Block Problems Using Large Language Models

scientific article published on 07 March 2024

Student use of the PeerWise system

Supporting student-generated free-response questions

The Impact of Multiple Choice Question Design on Predictions of Performance

scientific article published on 2 February 2021

The Implications of Large Language Models for CS Teachers and Students

scientific article published on 07 March 2023

The Robots Are Here: Navigating the Generative AI Revolution in Computing Education

scientific article published on 28 December 2023

The impact of question generation activities on performance

Towards a Framework for Teaching Debugging

Transformed by Transformers: Navigating the AI Coding Revolution for Computing Education: An ITiCSE Working Group Conducted by Humans

scientific article published on 29 June 2023

Transitioning from Block-Based to Text-Based Programming Languages

Understanding the syntax barrier for novices

Using Large Language Models to Enhance Programming Error Messages

scientific article published on 03 March 2023

Using Sensor-Based Programming to Improve Self-Efficacy and Outcome Expectancy for Students from Underrepresented Groups

scientific article published on 30 June 2023

“It’s Weird That it Knows What I Want”: Usability and Interactions with Copilot for Novice Programmers

scientific article published on 23 August 2023

List of works by Paul Denny

"Like a Nesting Doll": Analyzing Recursion Analogies Generated by CS Students Using Large Language Models

A Comparison of Immediate and Scheduled Feedback in Introductory Programming Projects

A case study of multi-institutional contributing-student pedagogy

A comparison of peer and tutor feedback

A simple framework for interactive games in CS1

A simple framework for interactive games in CS1

Activities, affordances and attitude

Advancing Automated Assessment Tools - Opportunities for Innovations in Upper-level Computing Courses: A Position Paper

All syntax errors are not equal

Analyzing Students' Preferences for LLM-Generated Analogies

Automated Assessment: Experiences From the Trenches

Automatic Generation of Programming Exercises and Code Explanations Using Large Language Models

Automating Personalized Parsons Problems with Customized Contexts and Concepts

BEST PAPER AT SIGCSE 2019 IN THE CS EDUCATION TRACK: First things first: providing metacognitive scaffolding for interpreting problem prompts

Chat Overflow: Artificially Intelligent Models for Computing Education - renAIssance or apocAIypse?

CodeAid: Evaluating a Classroom Deployment of an LLM-based Programming Assistant that Balances Student and Educator Needs

CodeHelp: Using Large Language Models with Guardrails for Scalable Support in Programming Classes

CodeWrite

Common logic errors made by novice programmers

Comparing Code Explanations Created by Students and Large Language Models

Comparing four contemporary statistical software tools for introductory data science and statistics in the social sciences

Constructive evaluation: a pedagogy of student-contributed assessment

Coverage of course topics in a student generated MCQ repository

Decoding Logic Errors: A Comparative Study on Bug Detection by Students and Large Language Models

Desirable Characteristics for AI Teaching Assistants in Programming Education

Discussing the Changing Landscape of Generative AI in Computing Education

Educator Experiences of Low Overhead Student Project Risk Management

Enhancing syntax error messages appears ineffectual

Evaluating Automatically Generated Contextualised Programming Exercises

Evaluating LLM-generated Worked Examples in an Introductory Programming Course

Evaluating a new exam question

Evaluating the Performance of Code Generation Models for Solving Parsons Problems With Small Prompt Variations

Experiences from Using Code Explanations Generated by Large Language Models in a Web Software Development E-Book

Explaining Code with a Purpose: An Integrated Approach for Developing Code Comprehension and Prompting Skills

Exploring How Novice Programming Students Have Experienced Digital Technology

Exploring the Difficulty of Faded Parsons Problems for Programming Education

Exploring the Effects of Contextualized Problem Descriptions on Problem Solving

First Steps Towards Predicting the Readability of Programming Error Messages

Getting By With Help From My Friends: Group Study in Introductory Programming Understood as Socially Shared Regulation

HandsUp: An In-Class Question Posing Tool

Improving complex task performance using a sequence of simple practice tasks

Instructor Perceptions of AI Code Generation Tools - A Multi-Institutional Interview Study

Ladebug: an online tool to help novice programmers improve their debugging skills

Mastery Learning in Computer Science Education

Mathematics, Computer Science and Career Inclinations — A Multi-Institutional Exploration

Metacognition and Self-Regulation in Programming Education: Theories and Exemplars of Use

More Than Meets the AI: Evaluating the performance of GPT-4 on Computer Graphics assessment questions

My AI Wants to Know if This Will Be on the Exam: Testing OpenAI’s Codex on CS2 Programming Exercises

Novice Reflections During the Transition to a New Programming Language

Objects Count so Count Objects!

On Using Gamification to Effectively Influence Student Activity in Online Learning Environments ⬇️

On the comprehensibility of functional decomposition: An empirical study

On the differences between correct student solutions

Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge

Patterns of Student Help-Seeking When Using a Large Language Model-Powered Programming Assistant

PeerWise

PeerWise

Programming Is Hard - Or at Least It Used to Be

Promoting Early Engagement with Programming Assignments Using Scheduled Automated Feedback

Prompt Problems: A New Programming Exercise for the Generative AI Era

Prompting for Comprehension: Exploring the Intersection of Explain in Plain English Questions and Prompt Writing

Quality of peer assessment in CS1

Resources and Support for the Implementation of Digital Technologies in New Zealand Schools

Scientific Collaboration Network Analysis for Computing Education Conferences

Self-Regulation, Self-Efficacy, and Fear of Failure Interactions with How Novices Use LLMs to Solve Programming Problems

Self-predicted and actual performance in an introductory programming course

Solving Proof Block Problems Using Large Language Models

Student use of the PeerWise system

Supporting student-generated free-response questions

The Impact of Multiple Choice Question Design on Predictions of Performance

The Implications of Large Language Models for CS Teachers and Students

The Robots Are Here: Navigating the Generative AI Revolution in Computing Education

The impact of question generation activities on performance

Towards a Framework for Teaching Debugging

Transformed by Transformers: Navigating the AI Coding Revolution for Computing Education: An ITiCSE Working Group Conducted by Humans

Transitioning from Block-Based to Text-Based Programming Languages

Understanding the syntax barrier for novices

Using Large Language Models to Enhance Programming Error Messages

Using Sensor-Based Programming to Improve Self-Efficacy and Outcome Expectancy for Students from Underrepresented Groups