arXiv subjects

Kobi Gal

Publications and source records attributed to Kobi Gal.

27 records · Page 2Linked to original sources

arXiv2020

Personalization in Human-AI Teams: Improving the Compatibility-Accuracy Tradeoff

AI systems that model and interact with users can update their models over time to reflect new information and changes in the environment. Although these updates may improve the overall performance of the AI system, they may actually hurt the performance with respect to individual users. Prior work has studied the trade-off between improving the system's accuracy following an update and the compatibility of the updated system with prior user experience. The more the model is forced to be compatible with a prior version, the higher loss in accuracy it will incur. In this paper, we show that by personalizing the loss function to specific users, in some cases it is possible to improve the compatibility-accuracy trade-off with respect to these users (increase the compatibility of the model while sacrificing less accuracy). We present experimental results indicating that this approach provides moderate improvements on average (around 20%) but large improvements for certain users (up to 300%).

cs.LG↗

arXiv2020

One Size Does Not Fit All: A Study of Badge Behavior in Stack Overflow

Badges are endemic to online interaction sites, from Question and Answer (Q&A) websites to ride sharing, as systems for rewarding participants for their contributions. This paper studies how badge design affects people's contributions and behavior over time. Past work has shown that badges "steer" people's behavior toward substantially increasing the amount of contributions before obtaining the badge, and immediately decreasing their contributions thereafter, returning to their baseline contribution levels. In contrast, we find that the steering effect depends on the type of user, as modeled by the rate and intensity of the user's contributions. We use these measures to distinguish between different groups of user activity, including users who are not affected by the badge system despite being significant contributors to the site. We provide a predictive model of how users change their activity group over the course of their lifetime in the system. We demonstrate our approach empirically in three different Q\&A sites on Stack Exchange with hundreds of thousands of users, for two types of activities (editing and voting on posts).

cs.SI↗

arXiv2020

Interpretable Models for Understanding Immersive Simulations

This paper describes methods for comparative evaluation of the interpretability of models of high dimensional time series data inferred by unsupervised machine learning algorithms. The time series data used in this investigation were logs from an immersive simulation like those commonly used in education and healthcare training. The structures learnt by the models provide representations of participants' activities in the simulation which are intended to be meaningful to people's interpretation. To choose the model that induces the best representation, we designed two interpretability tests, each of which evaluates the extent to which a model's output aligns with people's expectations or intuitions of what has occurred in the simulation. We compared the performance of the models on these interpretability tests to their performance on statistical information criteria. We show that the models that optimize interpretability quality differ from those that optimize (statistical) information theoretic criteria. Furthermore, we found that a model using a fully Bayesian approach performed well on both the statistical and human-interpretability measures. The Bayesian approach is a good candidate for fully automated model selection, i.e., when direct empirical investigations of interpretability are costly or infeasible.

cs.AI↗

arXiv2020

In the Eye of the Beholder? Detecting Creativity in Visual Programming Environments

Visual programming environments are increasingly part of the curriculum in schools. Their potential for promoting creative thinking of students is an important factor in their adoption. However, there does not exist a standard approach for detecting creativity in students' programming behavior, and analyzing programs manually requires human expertise and is time consuming. This work provides a computational tool for measuring creativity in visual programming that combines theory from the literature with data mining approaches. It adapts the classical dimensions of creative processes to our setting, as well as considering new aspects such as visual elements of the projects. We apply this approach to the Scratch programming environment, measuring the creativity score of hundreds of projects. We show that current metrics of computational thinking in Scratch fail to capture important aspects of creativity, such as the visual artifacts of projects. Interviews conducted with Scratch teachers validate our approach.

cs.HC↗

arXiv2019

EduBERT: Pretrained Deep Language Models for Learning Analytics

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to domain-specific NLP tasks such as re-hospitalization prediction from clinical notes. This paper demonstrates that using large pretrained models produces excellent results on common learning analytics tasks. Pre-training deep language models using student forum data from a wide array of online courses improves performance beyond the state of the art on three text classification tasks. We also show that a smaller, distilled version of our model produces the best results on two of the three tasks while limiting computational cost. We make both models available to the research community at large.

cs.CY↗

arXiv2019

Modeling Peoples Voting Behavior with Poll Information

Despite the prevalence of voting systems in the real world there is no consensus among researchers of how people vote strategically, even in simple voting settings. This paper addresses this gap by comparing different approaches that have been used to model strategic voting, including expected utility maximization, heuristic decisionmaking, and bounded rationality models. The models are applied to data collected from hundreds of people in controlled voting experiments, where people vote after observing non-binding poll information. We introduce a new voting model, the Attainability- Utility (AU) heuristic, which weighs the popularity of a candidate according to the poll, with the utility of the candidate to the voter. We argue that the AU model is cognitively plausible, and show that it is able to predict peoples voting behavior significantly better than other models from the literature. It was almost at par with (and sometimes better than) a machine learning algorithm that uses substantially more information. Our results provide new insights into the strategic considerations of voters, that undermine the prevalent assumptions of much theoretical work in social choice.

cs.GT↗

arXiv2019

A difficulty ranking approach to personalization in E-learning

The prevalence of e-learning systems and on-line courses has made educational material widely accessible to students of varying abilities and backgrounds. There is thus a growing need to accommodate for individual differences in e-learning systems. This paper presents an algorithm called EduRank for personalizing educational content to students that combines a collaborative filtering algorithm with voting methods. EduRank constructs a difficulty ranking for each student by aggregating the rankings of similar students using different aspects of their performance on common questions. These aspects include grades, number of retries, and time spent solving questions. It infers a difficulty ranking directly over the questions for each student, rather than ordering them according to the student's predicted score. The EduRank algorithm was tested on two data sets containing thousands of students and a million records. It was able to outperform the state-of-the-art ranking approaches as well as a domain expert. EduRank was used by students in a classroom activity, where a prior model was incorporated to predict the difficulty rankings of students with no prior history in the system. It was shown to lead students to solve more difficult questions than an ordering by a domain expert, without reducing their performance.

cs.AI↗

arXiv2018

Predicting Strategic Voting Behavior with Poll Information

The question of how people vote strategically under uncertainty has attracted much attention in several disciplines. Theoretical decision models have been proposed which vary in their assumptions on the sophistication of the voters and on the information made available to them about others' preferences and their voting behavior. This work focuses on modeling strategic voting behavior under poll information. It proposes a new heuristic for voting behavior that weighs the success of each candidate according to the poll score with the utility of the candidate given the voters' preferences. The model weights can be tuned individually for each voter. We compared this model with other relevant voting models from the literature on data obtained from a recently released large scale study. We show that the new heuristic outperforms all other tested models. The prediction errors of the model can be partly explained due to inconsistent voters that vote for (weakly) dominated candidates.

cs.GT↗

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↗