A5034009839- Online Learning and Analytics
- Intelligent Tutoring Systems and Adaptive Learning
- Topic Modeling
- Technology and Data Analysis
- Education and Learning Interventions
- Education, Safety, and Science Studies
- Neural Networks and Applications
- Advanced Data Processing Techniques
- Mobile Crowdsensing and Crowdsourcing
- Diet, Metabolism, and Disease
- Video Analysis and Summarization
- Digital Games and Media
- Mental Health Research Topics
- Advanced Text Analysis Techniques
- Text Readability and Simplification
- Business Process Modeling and Analysis
- Advanced Bandit Algorithms Research
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Service-Oriented Architecture and Web Services
- Teaching and Learning Programming
- Educational Games and Gamification
- Innovative Teaching and Learning Methods
- Sentiment Analysis and Opinion Mining
- Hepatocellular Carcinoma Treatment and Prognosis
PnP Innovations (United States)
2021-2022
Thomas Jefferson University
2020
Lankenau Medical Center
2020
Carnegie Mellon University
2016-2018
Many game designers aim to optimize difficulty make games that are "not too hard, not easy." However, recent experiments have shown even moderate can reduce player engagement. The present work investigates other design factors may account for the purported benefits of difficulty, such as choice, novelty and suspense. These were manipulated in three involving over 20,000 play sessions an online educational game.
"Multi-armed bandits" offer a new paradigm for the AI-assisted design of user interfaces. To help designers understand potential, we present results two experimental comparisons between bandit algorithms and random assignment. Our studies are intended to show how bandits able rapidly explore an space automatically select optimal configuration. focus is on optimization game space. The our experiments that can make data-driven more efficient accessible interface designers, but human...
Abstract Background Readability metrics provide us with an objective and efficient way to assess the quality of educational texts. We can use readability measures for finding assessment items that are difficult read a given grade level. Hard‐to‐read math word problems put some students at disadvantage if they behind in their literacy learning. Despite abilities, these perform poorly on difficult‐to‐read because poor reading skills. Less readable tests create equity issues who relatively new...
Abstract:
Generative AI systems are increasingly capable of expressing emotions via text and imagery. Effective emotional expression will likely play a major role in the efficacy -- particularly those designed to support human mental health wellbeing. This motivates our present research better understand alignment expressed with perception emotions. When tries express particular emotion, how might we assess whether they successful? To answer this question, survey measure between by generative...
In this paper, we describe our Knowledge Tracing model for the 2020 NeurIPS Education Challenge. We used a combination of 22 models to predict whether students will answer given question correctly or not. Our different approaches allowed us get an accuracy higher than any individual models, and variation types gave solution better explainability, more alignment with learning science theories, high predictive power.
Process Analysis is an emerging approach to discover meaningful knowledge from temporal educational data. The study presented in this paper shows how we used methods on the National Assessment of Educational Progress (NAEP) test data for modeling and predicting student test-taking behavior. Our process-oriented exploration gave us insightful findings students were interacting with digital assessment system over time. To what processes following during NAEP Digital Assessment, first developed...