arXiv subjects

Joseph Jay Williams

Publications and source records attributed to Joseph Jay Williams.

36 records · Page 2Linked to original sources

arXiv2023

Getting too personal(ized): The importance of feature choice in online adaptive algorithms

Digital educational technologies offer the potential to customize students' experiences and learn what works for which students, enhancing the technology as more students interact with it. We consider whether and when attempting to discover how to personalize has a cost, such as if the adaptation to personal information can delay the adoption of policies that benefit all students. We explore these issues in the context of using multi-armed bandit (MAB) algorithms to learn a policy for what version of an educational technology to present to each student, varying the relation between student characteristics and outcomes and also whether the algorithm is aware of these characteristics. Through simulations, we demonstrate that the inclusion of student characteristics for personalization can be beneficial when those characteristics are needed to learn the optimal action. In other scenarios, this inclusion decreases performance of the bandit algorithm. Moreover, including unneeded student characteristics can systematically disadvantage students with less common values for these characteristics. Our simulations do however suggest that real-time personalization will be helpful in particular real-world scenarios, and we illustrate this through case studies using existing experimental results in ASSISTments. Overall, our simulations show that adaptive personalization in educational technologies can be a double-edged sword: real-time adaptation improves student experiences in some contexts, but the slower adaptation and potentially discriminatory results mean that a more personalized model is not always beneficial.

cs.AI↗

arXiv2023

A Flexible Micro-Randomized Trial Design and Sample Size Considerations

Technological advancements have made it possible to deliver mobile health interventions to individuals. A novel framework that has emerged from such advancements is the just-in-time adaptive intervention (JITAI), which aims to suggest the right support to the individuals when their needs arise. The micro-randomized trial (MRT) design has been proposed recently to test the proximal effects of these JITAIs. However, the extant MRT framework only considers components with a fixed number of categories added at the beginning of the study. We propose a flexible MRT (FlexiMRT) design which allows addition of more categories to the components during the study. The proposed design is motivated by collaboration on the DIAMANTE study, which learns to deliver text messages to encourage physical activity among the patients with diabetes and depression. We developed a new test statistic and the corresponding sample size calculator for the FlexiMRT using an approach similar to the generalized estimating equation for longitudinal data. Simulation studies were conducted to evaluate the sample size calculators and an R shiny application for the calculators was developed.

stat.ME↗

arXiv2023

Student Usage of Q&A Forums: Signs of Discomfort?

Q&A forums are widely used in large classes to provide scalable support. In addition to offering students a space to ask questions, these forums aim to create a community and promote engagement. Prior literature suggests that the way students participate in Q&A forums varies and that most students do not actively post questions or engage in discussions. Students may display different participation behaviours depending on their comfort levels in the class. This paper investigates students' use of a Q&A forum in a CS1 course. We also analyze student opinions about the forum to explain the observed behaviour, focusing on students' lack of visible participation (lurking, anonymity, private posting). We analyzed forum data collected in a CS1 course across two consecutive years and invited students to complete a survey about perspectives on their forum usage. Despite a small cohort of highly engaged students, we confirmed that most students do not actively read or post on the forum. We discuss students' reasons for the low level of engagement and barriers to participating visibly. Common reasons include fearing a lack of knowledge and repercussions from being visible to the student community.

cs.CY↗

arXiv2022

Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation solicitation. The design balances two competing objectives: optimizing the outcomes for the subjects in the experiment (``cumulative regret minimization'') and gathering data that will be most useful for policy learning, that is, for learning an assignment rule that will maximize welfare if used after the experiment (``simple regret minimization''). We evaluate alternative experimental designs by collecting pilot data and then conducting a simulation study. Next, we implement our selected algorithm. Finally, we perform a second simulation study anchored to the collected data that evaluates the benefits of the algorithm we chose. Our first result is that the value of a learned policy in this setting is higher when data is collected via a uniform randomization rather than collected adaptively using standard cumulative regret minimization or policy learning algorithms. We propose a simple heuristic for adaptive experimentation that improves upon uniform randomization from the perspective of policy learning at the expense of increasing cumulative regret relative to alternative bandit algorithms. The heuristic modifies an existing contextual bandit algorithm by (i) imposing a lower bound on assignment probabilities that decay slowly so that no arm is discarded too quickly, and (ii) after adaptively collecting data, restricting policy learning to select from arms where sufficient data has been gathered.

econ.EM↗

arXiv2022

Exploring The Design of Prompts For Applying GPT-3 based Chatbots: A Mental Wellbeing Case Study on Mechanical Turk

Large-Language Models like GPT-3 have the potential to enable HCI designers and researchers to create more human-like and helpful chatbots for specific applications. But evaluating the feasibility of these chatbots and designing prompts that optimize GPT-3 for a specific task is challenging. We present a case study in tackling these questions, applying GPT-3 to a brief 5-minute chatbot that anyone can talk to better manage their mood. We report a randomized factorial experiment with 945 participants on Mechanical Turk that tests three dimensions of prompt design to initialize the chatbot (identity, intent, and behaviour), and present both quantitative and qualitative analyses of conversations and user perceptions of the chatbot. We hope other HCI designers and researchers can build on this case study, for other applications of GPT-3 based chatbots to specific tasks, and build on and extend the methods we use for prompt design, and evaluation of the prompt design.

cs.HC↗

arXiv2022

Increasing Students' Engagement to Reminder Emails Through Multi-Armed Bandits

Conducting randomized experiments in education settings raises the question of how we can use machine learning techniques to improve educational interventions. Using Multi-Armed Bandits (MAB) algorithms like Thompson Sampling (TS) in adaptive experiments can increase students' chances of obtaining better outcomes by increasing the probability of assignment to the most optimal condition (arm), even before an intervention completes. This is an advantage over traditional A/B testing, which may allocate an equal number of students to both optimal and non-optimal conditions. The problem is the exploration-exploitation trade-off. Even though adaptive policies aim to collect enough information to allocate more students to better arms reliably, past work shows that this may not be enough exploration to draw reliable conclusions about whether arms differ. Hence, it is of interest to provide additional uniform random (UR) exploration throughout the experiment. This paper shows a real-world adaptive experiment on how students engage with instructors' weekly email reminders to build their time management habits. Our metric of interest is open email rates which tracks the arms represented by different subject lines. These are delivered following different allocation algorithms: UR, TS, and what we identified as TS† - which combines both TS and UR rewards to update its priors. We highlight problems with these adaptive algorithms - such as possible exploitation of an arm when there is no significant difference - and address their causes and consequences. Future directions includes studying situations where the early choice of the optimal arm is not ideal and how adaptive algorithms can address them.

cs.LG↗

arXiv2022

Using Adaptive Experiments to Rapidly Help Students

Adaptive experiments can increase the chance that current students obtain better outcomes from a field experiment of an instructional intervention. In such experiments, the probability of assigning students to conditions changes while more data is being collected, so students can be assigned to interventions that are likely to perform better. Digital educational environments lower the barrier to conducting such adaptive experiments, but they are rarely applied in education. One reason might be that researchers have access to few real-world case studies that illustrate the advantages and disadvantages of these experiments in a specific context. We evaluate the effect of homework email reminders in students by conducting an adaptive experiment using the Thompson Sampling algorithm and compare it to a traditional uniform random experiment. We present this as a case study on how to conduct such experiments, and we raise a range of open questions about the conditions under which adaptive randomized experiments may be more or less useful.

cs.LG↗

arXiv2022

How can Email Interventions Increase Students' Completion of Online Homework? A Case Study Using A/B Comparisons

Email communication between instructors and students is ubiquitous, and it could be valuable to explore ways of testing out how to make email messages more impactful. This paper explores the design space of using emails to get students to plan and reflect on starting weekly homework earlier. We deployed a series of email reminders using randomized A/B comparisons to test alternative factors in the design of these emails, providing examples of an experimental paradigm and metrics for a broader range of interventions. We also surveyed and interviewed instructors and students to compare their predictions about the effectiveness of the reminders with their actual impact. We present our results on which seemingly obvious predictions about effective emails are not borne out, despite there being evidence for further exploring these interventions, as they can sometimes motivate students to attempt their homework more often. We also present qualitative evidence about student opinions and behaviours after receiving the emails, to guide further interventions. These findings provide insight into how to use randomized A/B comparisons in everyday channels such as emails, to provide empirical evidence to test our beliefs about the effectiveness of alternative design choices.

cs.HC↗

arXiv2022

Experimenting with Experimentation: Rethinking The Role of Experimentation in Educational Design

What if we take a broader view of what it means to run an education experiment? In this paper, we explore opportunities that arise when we think beyond the commonly-held notion that the purpose of an experiment is to either accept or reject a pre-defined hypothesis and instead, reconsider experimentation as a means to explore the complex design space of creating and improving instructional content. This is an approach we call experiment-inspired design. Then, to operationalize these ideas in a real-world experimentation venue, we investigate the implications of running a sequence of interventions teaching first-year students "meta-skills": transferable skills applicable to multiple areas of their lives, such as planning, and managing stress. Finally, using two examples as case studies for meta-skills interventions (stress-reappraisal and mental contrasting with implementation intentions), we reflect on our experiences with experiment-inspired design and share six preliminary lessons on how to use experimentation for design.

cs.HC↗

arXiv2021

Understanding User Perspectives on Prompts for Brief Reflection on Troubling Emotions

We investigate users' perspectives on an online reflective question activity (RQA) that prompts people to externalize their underlying emotions on a troubling situation. Inspired by principles of cognitive behavioral therapy, our 15-minute activity encourages self-reflection without a human or automated conversational partner. A deployment of our RQA on Amazon Mechanical Turk suggests that people perceive several benefits from our RQA, including structured awareness of their thoughts and problem-solving around managing their emotions. Quantitative evidence from a randomized experiment suggests people find that our RQA makes them feel less worried by their selected situation and worth the minimal time investment. A further two-week technology probe deployment with 11 participants indicates that people see benefits to doing this activity repeatedly, although the activity may get monotonous over time. In summary, this work demonstrates the promise of online reflection activities that carefully leverage principles of psychology in their design.

cs.HC↗

arXiv2021

Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments

Multi-armed bandit algorithms have been argued for decades as useful for adaptively randomized experiments. In such experiments, an algorithm varies which arms (e.g. alternative interventions to help students learn) are assigned to participants, with the goal of assigning higher-reward arms to as many participants as possible. We applied the bandit algorithm Thompson Sampling (TS) to run adaptive experiments in three university classes. Instructors saw great value in trying to rapidly use data to give their students in the experiments better arms (e.g. better explanations of a concept). Our deployment, however, illustrated a major barrier for scientists and practitioners to use such adaptive experiments: a lack of quantifiable insight into how much statistical analysis of specific real-world experiments is impacted (Pallmann et al, 2018; FDA, 2019), compared to traditional uniform random assignment. We therefore use our case study of the ubiquitous two-arm binary reward setting to empirically investigate the impact of using Thompson Sampling instead of uniform random assignment. In this setting, using common statistical hypothesis tests, we show that collecting data with TS can as much as double the False Positive Rate (FPR; incorrectly reporting differences when none exist) and the False Negative Rate (FNR; failing to report differences when they exist)...

cs.LG↗

arXiv2020

Multi-Level Micro-Randomized Trial: Detecting the Proximal Effect of Messages on Physical Activity

Technological advancements in mobile devices have made it possible to deliver mobile health interventions to individuals. A novel intervention framework that emerges from such advancements is the just-in-time adaptive intervention (JITAI), where it aims to suggest the right support to the individual "just in time", when their needs arise, thus having proximal, near future effects. The micro-randomized trial (MRT) design was proposed recently to test the proximal effects of these JITAIs. In an MRT, participants are repeatedly randomized to one of the intervention options of various in the intervention components, at a scale of hundreds or thousands of decision time points over the course of the study. However, the extant MRT framework only tests the proximal effect of two-level intervention components (e.g. control vs intervention). In this paper, we propose a novel version of MRT design with multiple levels per intervention component, which we call "multi-level micro-randomized trial" (MLMRT) design. The MLMRT extends the existing MRT design by allowing multi-level intervention components, and the addition of more levels to the components during the study period. We apply generalized estimating equation type methodology on the longitudinal data arising from an MLMRT to develop the novel test statistics for assessing the proximal effects and deriving the associated sample size calculators. We conduct simulation studies to evaluate the sample size calculators based on both power and precision. We have developed an R shiny application of the sample size calculators. This proposed design is motivated by our involvement in the Diabetes and Mental Health Adaptive Notification Tracking and Evaluation (DIAMANTE) study. This study uses a novel mobile application, also called "DIAMANTE", which delivers adaptive text messages to encourage physical activity.

stat.ME↗

arXiv2020

Sequential Explanations with Mental Model-Based Policies

The act of explaining across two parties is a feedback loop, where one provides information on what needs to be explained and the other provides an explanation relevant to this information. We apply a reinforcement learning framework which emulates this format by providing explanations based on the explainee's current mental model. We conduct novel online human experiments where explanations generated by various explanation methods are selected and presented to participants, using policies which observe participants' mental models, in order to optimize an interpretability proxy. Our results suggest that mental model-based policies (anchored in our proposed state representation) may increase interpretability over multiple sequential explanations, when compared to a random selection baseline. This work provides insight into how to select explanations which increase relevant information for users, and into conducting human-grounded experimentation to understand interpretability.

cs.LG↗

arXiv2019

RiPPLE: A Crowdsourced Adaptive Platform for Recommendation of Learning Activities

This paper presents a platform called RiPPLE (Recommendation in Personalised Peer-Learning Environments) that recommends personalized learning activities to students based on their knowledge state from a pool of crowdsourced learning activities that are generated by educators and the students themselves. RiPPLE integrates insights from crowdsourcing, learning sciences, and adaptive learning, aiming to narrow the gap between these large bodies of research while providing a practical platform-based implementation that instructors can easily use in their courses. This paper provides a design overview of RiPPLE, which can be employed as a standalone tool or embedded into any learning management system (LMS) or online platform that supports the Learning Tools Interoperability (LTI) standard. The platform has been evaluated based on a pilot in an introductory course with 453 students at The University of Queensland. Initial results suggest that the use of the \name platform led to measurable learning gains and that students perceived the platform as beneficially supporting their learning.

cs.HC↗

arXiv2018

Combining Difficulty Ranking with Multi-Armed Bandits to Sequence Educational Content

As e-learning systems become more prevalent, there is a growing need for them to accommodate individual differences between students. This paper addresses the problem of how to personalize educational content to students in order to maximize their learning gains over time. We present a new computational approach to this problem called MAPLE (Multi-Armed Bandits based Personalization for Learning Environments) that combines difficulty ranking with multi-armed bandits. Given a set of target questions MAPLE estimates the expected learning gains for each question and uses an exploration-exploitation strategy to choose the next question to pose to the student. It maintains a personalized ranking over the difficulties of question in the target set which is used in two ways: First, to obtain initial estimates over the learning gains for the set of questions. Second, to update the estimates over time based on the students responses. We show in simulations that MAPLE was able to improve students' learning gains compared to approaches that sequence questions in increasing level of difficulty, or rely on content experts. When implemented in a live e-learning system in the wild, MAPLE showed promising results. This work demonstrates the efficacy of using stochastic approaches to the sequencing problem when augmented with information about question difficulty.

cs.AI↗

arXiv2015

A Methodology for Discovering how to Adaptively Personalize to Users using Experimental Comparisons

We explain and provide examples of a formalism that supports the methodology of discovering how to adapt and personalize technology by combining randomized experiments with variables associated with user models. We characterize a formal relationship between the use of technology to conduct A/B experiments and use of technology for adaptive personalization. The MOOClet Formalism [11] captures the equivalence between experimentation and personalization in its conceptualization of modular components of a technology. This motivates a unified software design pattern that enables technology components that can be compared in an experiment to also be adapted based on contextual data, or personalized based on user characteristics. With the aid of a concrete use case, we illustrate the potential of the MOOClet formalism for a methodology that uses randomized experiments of alternative micro-designs to discover how to adapt technology based on user characteristics, and then dynamically implements these personalized improvements in real time.

cs.HC↗

arXiv2015

Using and Designing Platforms for In Vivo Education Experiments

In contrast to typical laboratory experiments, the everyday use of online educational resources by large populations and the prevalence of software infrastructure for A/B testing leads us to consider how platforms can embed in vivo experiments that do not merely support research, but ensure practical improvements to their educational components. Examples are presented of randomized experimental comparisons conducted by subsets of the authors in three widely used online educational platforms Khan Academy, edX, and ASSISTments. We suggest design principles for platform technology to support randomized experiments that lead to practical improvements enabling Iterative Improvement and Collaborative Work and explain the benefit of their implementation by WPI co-authors in the ASSISTments platform.

cs.HC↗

arXiv2015

Supporting Instructors in Collaborating with Researchers using MOOClets

Most education and workplace learning takes place in classroom contexts far removed from laboratories or field sites with special arrangements for scientific research. But digital online resources provide a novel opportunity for large scale efforts to bridge the real world and laboratory settings which support data collection and randomized A/B experiments comparing different versions of content or interactions [2]. However, there are substantial technological and practical barriers in aligning instructors and researchers to use learning technologies like blended lessons/exercises & MOOCs as both a service for students and a realistic context to conduct research. This paper explains how the concept of a MOOClet can facilitate research-practitioner collaborations. MOOClets [3] are defined as modular components of a digital resource that can be implemented in technology to: (1) allow modification to create multiple versions, (2) allow experimental comparison and personalization of different versions, (3) reliably specify what data are collected. We suggest a framework in which instructors specify what kinds of changes to lessons, exercises, and emails they would be willing to adopt, and what data they will collect and make available. Researchers can then: (1) specify or design experiments that compare the effects of different versions on quantifiable outcomes. (2) Explore algorithms for maximizing particular outcomes by choosing alternative versions of a MOOClet based on the input variables available. We present a prototype survey tool for instructors intended to facilitate practitioner researcher matches and successful collaborations.

cs.CY↗