Difference between revisions of "Projects"
(→HELPeR - Health e-Librarian with Personalized Recommender) |
(→Past Projects) |
||
(8 intermediate revisions by the same user not shown) | |||
Line 4: | Line 4: | ||
Mohammad https://arxiv.org/abs/2312.02105 | Mohammad https://arxiv.org/abs/2312.02105 | ||
Rully Hendrawan [LLM for domain modeling](https://docs.google.com/presentation/d/1EjlC0MUKzbWKfOMHJffrVXJ31cbjJFcxIv5F9HBjULU/edit?usp=sharing) --> | Rully Hendrawan [LLM for domain modeling](https://docs.google.com/presentation/d/1EjlC0MUKzbWKfOMHJffrVXJ31cbjJFcxIv5F9HBjULU/edit?usp=sharing) --> | ||
− | == Current Projects == | + | == Current Funded Projects == |
===[[An Interactive Electronic Textbook for Python Programming and Data Science Courses]] === | ===[[An Interactive Electronic Textbook for Python Programming and Data Science Courses]] === | ||
Line 10: | Line 10: | ||
Peter Brusilovsky proposes to develop AdaPT, an interactive and adaptive system for learning and practicing Python programming and Data Science skills, which fuses a well-tested electronic textbook with a large volume of “smart” interactive learning content: worked code examples, code animations, and several types of automatically assessed practice problems. The system uses advanced learner modeling to trace the growth of learner’s knowledge and skills and to identify misunderstood concepts. Adapting dynamically to the current state of knowledge, it suggests most appropriate interactive content to practice at every step of learning. | Peter Brusilovsky proposes to develop AdaPT, an interactive and adaptive system for learning and practicing Python programming and Data Science skills, which fuses a well-tested electronic textbook with a large volume of “smart” interactive learning content: worked code examples, code animations, and several types of automatically assessed practice problems. The system uses advanced learner modeling to trace the growth of learner’s knowledge and skills and to identify misunderstood concepts. Adapting dynamically to the current state of knowledge, it suggests most appropriate interactive content to practice at every step of learning. | ||
− | Supported by Innovation in Education Award, University of Pittsburgh (2023-2024). [[An Interactive Electronic Textbook for Python Programming and Data Science Courses|==> more]] | + | Supported by [https://www.provost.pitt.edu/acie/awards/funded-projects Innovation in Education Award], University of Pittsburgh (2023-2024). [[An Interactive Electronic Textbook for Python Programming and Data Science Courses|==> more]] |
===[[Investigating and Evaluating Exploratory Recommender Systems]]=== | ===[[Investigating and Evaluating Exploratory Recommender Systems]]=== | ||
+ | Exploratory recommender systems bring together the power of Human and Artificial Intelligence through human-AI collaboration and user-controlled recommendation. In this project, we develop and evaluate exploratory recommender systems in several domains. The focus of the project are carousel-based interfaces and novel recommender algorithms that can better adapt to user actions in the human-AI collaboration process. | ||
+ | |||
+ | Supported by Amazon Research Award to Peter Brusilovsky (2022-2024) [[Investigating and Evaluating Exploratory Recommender Systems|==> more]] | ||
===[[An Infrastructure for Sustainable Innovation and Research in Computer Science Education]]=== | ===[[An Infrastructure for Sustainable Innovation and Research in Computer Science Education]]=== | ||
+ | Researchers from the University of Pittsburgh, Carnegie Mellon University, North Carolina State University, and Virginia Tech collaborate to support the Computer Science Education Hub, social and technical infrastructure to accelerate research on teaching and learning of computing disciplines. The Hub will host community events and provide a web repository for computing education datasets, tools, and common analysis methods. The Hub facilitates creation and adoption of new tools to support computing educators and students, and new standards to support data collection and data-enabled research. Hub community events help researchers and educators from many learning contexts to develop and improve computing education resources. | ||
+ | |||
+ | Supported by NSF grant [https://www.nsf.gov/awardsearch/showAward?AWD_ID=2213789&HistoricalAwards=false CNS 2213789 (2017-2021)]. [[An Infrastructure for Sustainable Innovation and Research in Computer Science Education|==> more]] | ||
===[[Integrating Complementary Learning Principles in Aphasia Rehabilitation via Adaptive Modeling]]=== | ===[[Integrating Complementary Learning Principles in Aphasia Rehabilitation via Adaptive Modeling]]=== | ||
Line 23: | Line 29: | ||
===[[HELPeR - Health e-Librarian with Personalized Recommender]]=== | ===[[HELPeR - Health e-Librarian with Personalized Recommender]]=== | ||
− | As the Internet has become a prominent source of health information to guide patients’ decision-making and self-management activities, patients strongly indicate they need navigational support to locate appropriate information on the Internet. The overall goal of this project is to build and implement a “Health E-Librarian with Personalized Recommendations (HELPeR)” - a personalized information access system with a hybrid recommender engine that adapts to different aspects of the patient: information needs based on the user’s profile, the user’s uniquely expressed information interests, and the level of user’s disease-related knowledge | + | As the Internet has become a prominent source of health information to guide patients’ decision-making and self-management activities, patients strongly indicate they need navigational support to locate appropriate information on the Internet. The overall goal of this project is to build and implement a “Health E-Librarian with Personalized Recommendations (HELPeR)” - a personalized information access system with a hybrid recommender engine that adapts to different aspects of the patient: information needs based on the user’s profile, the user’s uniquely expressed information interests, and the level of user’s disease-related knowledge. |
Supported by NIH grant [https://www.grantome.com/grant/NIH/R01-LM013038-02 R01-LM013038-02] (2019 - 2023). | Supported by NIH grant [https://www.grantome.com/grant/NIH/R01-LM013038-02 R01-LM013038-02] (2019 - 2023). | ||
Line 32: | Line 38: | ||
Supported by the University of Pittsburgh through the Personalized Education program (2018-2020). [[The Pitt Grapevine|==> more]] | Supported by the University of Pittsburgh through the Personalized Education program (2018-2020). [[The Pitt Grapevine|==> more]] | ||
− | == Past Projects == | + | == Past Funded Projects == |
===[[Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education]]=== | ===[[Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education]]=== |
Latest revision as of 19:09, 21 April 2024
This page presents a list of funded projects performed by PAWS Lab. The most recent projects are shown at the top of the list.
Contents
- 1 Current Funded Projects
- 1.1 An Interactive Electronic Textbook for Python Programming and Data Science Courses
- 1.2 Investigating and Evaluating Exploratory Recommender Systems
- 1.3 An Infrastructure for Sustainable Innovation and Research in Computer Science Education
- 1.4 Integrating Complementary Learning Principles in Aphasia Rehabilitation via Adaptive Modeling
- 1.5 HELPeR - Health e-Librarian with Personalized Recommender
- 1.6 The Pitt Grapevine: An Academic Recommender System
- 2 Past Funded Projects
- 2.1 Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education
- 2.2 CSEdPad: Investigating and Scaffolding Students' Mental Models during Computer Programming Tasks to Improve Learning, Engagement, and Retention
- 2.3 Open Corpus Personalized Learning
- 2.4 Adaptive Navigation Support and Open Social Learner Modeling for PAL
- 2.5 Ensemble: Enriching Communities and Collections to Support Education in Computing
- 2.6 Engaging Students in Online Reading Through Social Progress Visualization
- 2.7 Personalized Social Systems for Local Communities
- 2.8 Personalization and Social Networking for Short-Term Communities
- 2.9 Modeling and Visualization of Latent Communities
- 2.10 Personalized Exploratorium for Database Courses
- 2.11 GALE: Distillation with Utility-Optimized Transcription and Translation
- 2.12 Personalized Access to Open Corpus Educational Resources through Adaptive Navigation Support and Adaptive Visualization
- 2.13 Adaptive Explanatory Visualization for Learning Programming Concepts
- 2.14 Individualized Exercises for Assessment and Self-Assessment of Programming Knowledge
- 2.15 Educational Software for Teaching and Learning Information Retrieval
- 2.16 Supporting Learning from Examples in a Programming Course
- 2.17 Adaptive Electronic Textbooks for World Wide Web
Current Funded Projects
An Interactive Electronic Textbook for Python Programming and Data Science Courses
Peter Brusilovsky proposes to develop AdaPT, an interactive and adaptive system for learning and practicing Python programming and Data Science skills, which fuses a well-tested electronic textbook with a large volume of “smart” interactive learning content: worked code examples, code animations, and several types of automatically assessed practice problems. The system uses advanced learner modeling to trace the growth of learner’s knowledge and skills and to identify misunderstood concepts. Adapting dynamically to the current state of knowledge, it suggests most appropriate interactive content to practice at every step of learning.
Supported by Innovation in Education Award, University of Pittsburgh (2023-2024). ==> more
Investigating and Evaluating Exploratory Recommender Systems
Exploratory recommender systems bring together the power of Human and Artificial Intelligence through human-AI collaboration and user-controlled recommendation. In this project, we develop and evaluate exploratory recommender systems in several domains. The focus of the project are carousel-based interfaces and novel recommender algorithms that can better adapt to user actions in the human-AI collaboration process.
Supported by Amazon Research Award to Peter Brusilovsky (2022-2024) ==> more
An Infrastructure for Sustainable Innovation and Research in Computer Science Education
Researchers from the University of Pittsburgh, Carnegie Mellon University, North Carolina State University, and Virginia Tech collaborate to support the Computer Science Education Hub, social and technical infrastructure to accelerate research on teaching and learning of computing disciplines. The Hub will host community events and provide a web repository for computing education datasets, tools, and common analysis methods. The Hub facilitates creation and adoption of new tools to support computing educators and students, and new standards to support data collection and data-enabled research. Hub community events help researchers and educators from many learning contexts to develop and improve computing education resources.
Supported by NSF grant CNS 2213789 (2017-2021). ==> more
Integrating Complementary Learning Principles in Aphasia Rehabilitation via Adaptive Modeling
Aphasia, commonly caused by stroke or other acquired brain injuries, can have a negative effect on an individual’s quality of life, often leading to depression and feelings of isolation. A primary frustration for people with aphasia is anomia, or word-finding difficulty. In this NIH-funded project, an interdisciplinary team of researchers will work on developing and evaluating novel adaptive computer-based aphasia treatments to help improve the efficiency and long-term impact of language treatment.
Supported by NIH grant 1R01DC019325-01A1 (2021 - 2026).
HELPeR - Health e-Librarian with Personalized Recommender
As the Internet has become a prominent source of health information to guide patients’ decision-making and self-management activities, patients strongly indicate they need navigational support to locate appropriate information on the Internet. The overall goal of this project is to build and implement a “Health E-Librarian with Personalized Recommendations (HELPeR)” - a personalized information access system with a hybrid recommender engine that adapts to different aspects of the patient: information needs based on the user’s profile, the user’s uniquely expressed information interests, and the level of user’s disease-related knowledge.
Supported by NIH grant R01-LM013038-02 (2019 - 2023).
The Pitt Grapevine: An Academic Recommender System
The goal of the project is to connect students with research advisors at the University of Pittsburgh through an interactive recommender system.
Supported by the University of Pittsburgh through the Personalized Education program (2018-2020). ==> more
Past Funded Projects
Community-Building and Infrastructure Design for Data-Intensive Research in Computer Science Education
The mission of this collaborative project is to support the CS Education community by supplying documentation and infrastructure to help with adopting shared standards, protocols, and tools. In this way we hope to promote
- development and broader re-use of innovative learning content that is instrumented for rich data collection;
- formats and tools for analysis of learner data; and
- best practices to make large collections of learner data and associated analytics available to researchers in the CSE, data science, and learner science communities.
For a more complete description of our vision and goals, see the [home page of the project https://cssplice.github.io/]
Supported by NSF grant EHR 1740775 (2017-2021). ==> more
CSEdPad: Investigating and Scaffolding Students' Mental Models during Computer Programming Tasks to Improve Learning, Engagement, and Retention
This project is a joint effort of research teams at the University of Memphis and the University of Pittsburgh to explore the process of code comprehension by students and build AI-based tools to support the practice and assessment of code comprehension. In the course of the project, we developed and evaluated open-learned modeling approaches, code-tracing tools to practice code comprehension, and an intelligent tutor for assessing code comprehension through explanations.
Supported by the National Science Foundation Award IIS 1822752 (2018-2023). ==> more
Open Corpus Personalized Learning
This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces the carefully-crafted domain model with automatically-created domain models, lowering the cost of developing such systems while also providing a wider range of instructional paths through the content.
Supported by NSF grant IIS 1525186 (2015-2018). ==> more
The goal of this project is to leverage the power of open social learner modeling and adaptive navigation support in the context of the envisioned Personalized Assistant for Learning (PAL).
Supported by the Distributed Learning Initiative contract W911QY13C0032 (2013-2016). ==> more
Ensemble: Enriching Communities and Collections to Support Education in Computing
Ensemble is a cross-university collaborative effort that aims to bring together the global community of computing educators around a growing set of content collections with high-quality educational resources.
Supported by NSF (2008-2014). ==> more
Engaging Students in Online Reading Through Social Progress Visualization
This project explores an alternative approach to encourage student online textbook reading using a social progress visualization interface.
Supported by Innovation in Education Award, University of Pittsburgh (2012-2013). ==> more
Personalized Social Systems for Local Communities
The project explored the use of personalization and mobile computing to increase user engagement in location-bound social systems.
Supported by Google (2010-2012). ==> more
Personalization and Social Networking for Short-Term Communities
The project explored a range of approaches, which can enable reliable social networking and personalization in communities, which exist for short period of time, like researchers attending a specific conference.
Supported by NSF (2010-2011). In collaboration with Jung Sun Oh. ==> more
Modeling and Visualization of Latent Communities
The project focused on the problem of discovering latent communities from Social Web data and presenting this data in visual form.
Supported by the Institute for Defense Analysis and NSF (2010-2012). ==> more
Personalized Exploratorium for Database Courses
The project focused on developing and evaluating of a personalized educational environment for teaching Database courses.
Supported by NSF (2007-2008). In collaboration with Vladimir Zadorozhny. ==> more
GALE: Distillation with Utility-Optimized Transcription and Translation
Supported by DARPA (2005-2007) In collaboration with Carnegie Mellon University and IBM ==> more
The project focused on developing technologies for personalized access to information based on adaptive navigation support, collaborative filtering, and information visualization.
Supported by NSF (2005-2010). ==> more
Adaptive Explanatory Visualization for Learning Programming Concepts
The project focused on developing and studying adaptive explanatory visualization technologies for C and Java programming languages.
Supported by NSF (2004-2007). In collaboration with Michael Spring. ==> more
Individualized Exercises for Assessment and Self-Assessment of Programming Knowledge
The project focused on developing and evaluating a personalized assessment technology for programming courses.
Supported by NSF (2003-2005). ==> more
Educational Software for Teaching and Learning Information Retrieval
Supported by Innovation in Education Award, University of Pittsburgh (2003-2004). ==> more
Supporting Learning from Examples in a Programming Course
Supported by Innovation in Education Award, University of Pittsburgh (2001-2002). ==> more
Adaptive Electronic Textbooks for World Wide Web
Supported by Alexander von Humboldt Foundation (1995-1996) and NSF (1997-1998). In collaboration with Gerhard Weber and John Anderson ==> more