Khushboo Thaker

Khushboo Thaker
University of Pittsburgh | Pitt · Intelligent Systems Program - School of Computing and Information

PhD Student

About

34
Publications
5,261
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
259
Citations
Introduction
My research focuses on building user knowledge models for Adaptation and Personalization. User models rely on direct or indirect evidence from users like quiz performance in tutoring systems and item clicks in recommendation systems. However, there are scenarios when the evidence is missing. This is where I am digging in and trying to use user behaviours likes reading behavior and user reviews perform user modeling - to know more http://pitt.edu/~kmt81
Additional affiliations
May 2019 - August 2019
Meta
Position
  • Developer
Description
  • At facebook search, I worked for Search Ranking Team.
October 2012 - July 2016
Indian Institute of Science
Position
  • Research Associate
Education
September 2016 - August 2022
University of Pittsburgh
Field of study
  • Intelligent Systems

Publications

Publications (34)
Conference Paper
Massive Open Online Courses (MOOCs) often incorporate lecture-based learning along with lecture notes, textbooks, and videos to students. Moreover, MOOCs also incorporate practice activities and quizzes. Student learning in MOOCs can be tracked and improved using state-of-the-art student modeling. Currently, this means employing conventional studen...
Conference Paper
Full-text available
Adaptive textbooks use student interaction data to infer the current state of student knowledge and recommend the most relevant learning materials. A challenge of student modeling for adaptive textbooks is that conventional student models are constructed based on performance data (quiz or problem-solving). However, students' interactions with onlin...
Conference Paper
Full-text available
Assessment plays a vital role in learning, as it provides both instructors and students with feedback on the overall effectiveness of their teaching or learning. However, when a student fails to correctly answer certain questions in an assessment (such as a quiz), the student needs specific recommendations that are tailored to their learning needs...
Article
Full-text available
The advancement of computational Artificial Intelligence (AI) in the recent decade has been transformative for many domains, including AI in Education. One direction, where it has caused a noticeable increase in research activity, is application of AI technologies to enhance digital textbooks by making them more interactive, engaging, adaptive, and...
Article
This study represents our preliminary work focused on the health information seeking of caregivers of ovarian cancer (OvCa) patients and survivors. Previous research has predominantly focused on OvCa patients' needs, while neglecting caregivers' needs independently. Through the analysis of social media posts by OvCa caregivers, this study explores...
Article
Full-text available
Background Patients and caregivers widely use online health communities (OHCs) to acquire knowledge from peers. Questions posed in OHCs reflect participants’ learning objectives and differ in their level of cognitive complexity. However, little is known about the topics and levels of participants’ learning objectives and the corresponding support t...
Preprint
BACKGROUND Patients and caregivers have been widely using Online Health Communities (OHCs) to acquire knowledge from peers. Questions posed in OHCs reflect the participant's learning objectives and are known to differ in the level of cognitive complexity. However, little is known about the topics and levels of participant learning objectives and th...
Conference Paper
Full-text available
Developing user personas has been a crucial aspect of human-centered system design for decades as it helps in understanding and segregating users based on their prominent characteristics. However, such a technique has not been applied in developing and improving systems for supporting open government data (OGD) users. Therefore, this paper explores...
Poster
Full-text available
The overarching goal of our project is to develop a recommender system that personalize online health-related materials to patients and their caregivers based on their needs and knowledge level. • The recommender system will address the knowledge discrepancy between patients and online health information, and accurately estimate the required knowle...
Preprint
BACKGROUND Online health communities (OHCs) provide ovarian cancer (OvCa) patients, survivors, and their caregivers assistance beyond their traditional support channels. OvCa OHC promotes connection and exchange information among users who had similar experiences. This exchange of information often leads to resource sharing amongst users, as web li...
Article
Full-text available
Background Online health communities (OHCs) provide patients and survivors of ovarian cancer (OvCa) and their caregivers with help beyond traditional support channels, such as health care providers and clinicians. OvCa OHCs promote connections and exchanges of information among users with similar experiences. Users often exchange information, which...
Article
Full-text available
With the increased popularity of electronic textbooks, there is a growing interest in developing a new generation of “intelligent textbooks,” which have the ability to guide readers according to their learning goals and current knowledge. Intelligent textbooks extend regular textbooks by integrating machine-manipulable knowledge, and the most popul...
Preprint
Full-text available
Faceted summarization provides briefings of a document from different perspectives. Readers can quickly comprehend the main points of a long document with the help of a structured outline. However, little research has been conducted on this subject, partially due to the lack of large-scale faceted summarization datasets. In this study, we present F...
Poster
Full-text available
Ovarian cancer (OvCa) can be a deadly gynecological cancer affecting about 22k women per year in the United States with a significant recurrence rate [1]. Women with OvCa and their caregivers often seek support from online health communities (OHCs) [2]. These OHCs allow for the exchange of information and resources with other individuals who have h...
Chapter
In this paper, we introduce an approach that combines automatic domain knowledge modeling, student modeling, and content recommendation approaches to recommend relevant Wikipedia articles for students working with online electronic textbooks.
Conference Paper
Full-text available
This paper presents our attempt to create an exploratory search system CovEx for a collection of academic papers related to COVID-19. CovEx uses concept extraction, knowledge graphs, and user-controlled recommendation to assist users with various levels of domain expertise in their information needs. CCS CONCEPTS • Information systems → Graph-based...
Article
The increasing popularity of digital textbooks as a new learning media has resulted in a growing interest in developing a new generation of adaptive textbooks that can help readers to learn better through adapting to the readers’ learning goals and the current state of knowledge. These adaptive textbooks are most frequently powered by internal know...
Article
Full-text available
Academic collections, such as COVID-19 Open Research Dataset (CORD-19), contain a large number of scholarly articles regarding COVID-19 and other related viruses. These articles represent the latest development in combating COVID-19 pandemic in various disciplines. However, it is difficult for laypeople to access these articles due to the term mism...
Conference Paper
Full-text available
Over the last 10 years, the world experienced a rapid increase in volume and diversity of digital learning resources. The abundance of digital resources could support a range of powerful educational scenarios, which were not available before. In this paper, we introduce a novel approach that combines fully automatic knowledge modeling, student mode...
Preprint
Full-text available
This paper presents our attempt to create an exploratory search system CovEx for a collection of academic papers related to COVID-19. CovEx uses concept extraction, knowledge graphs, and user-controlled recommendation to assist users with various levels of domain expertise in their information needs. CCS CONCEPTS • Information systems → Graph-based...
Conference Paper
Full-text available
Behnam Rahdari [0000−0001−6514−912X] , Peter Brusilovsky [0000−0002−1902−1464] , Khushboo Thaker [0000−0003−3619−9376] , and Jordan Barria-Pineda [0000−0002−4961−4818] Abstract. In this paper, we introduce an approach that combines automatic domain knowledge modeling, student modeling, and content recommendation approaches to recommend relevant Wik...
Preprint
Full-text available
With the increased popularity of electronic textbooks, there is a growing interests in developing a new generation of "intelligent textbooks", which have the ability to guide the readers according to their learning goals and current knowledge. The intelligent textbooks extend regular textbooks by integrating machine-manipulatable knowledge such as...
Presentation
Full-text available
In this work, we described methods used to predict student success on a given programming task and reported our evaluation results.
Preprint
Existing keyphrase generation studies suffer from the problems of generating duplicate phrases and deficient evaluation based on a fixed number of predicted phrases. We propose a recurrent generative model that generates multiple keyphrases sequentially from a text, with specific modules that promote generation diversity. We further propose two new...
Conference Paper
Full-text available
Adaptive textbooks use student interaction data to infer the current state of student knowledge and recommend most relevant learning materials. A challenge of student modeling for adaptive textbooks is that conventional student models are constructed based on performance data (quiz or problem-solving), however, students’ interactions with online te...

Network

Cited By