Skip to feedback

Award Abstract # 1917625
Collaborative Research: Parent-EMBRACE: An Embodied ITS for Improving Comprehension during fParent-Child Shared Reading

NSF Org: IIS
Division of Information & Intelligent Systems
Recipient: UNIVERSITY OF PITTSBURGH - OF THE COMMONWEALTH SYSTEM OF HIGHER EDUCATION
Initial Amendment Date: July 11, 2019
Latest Amendment Date: July 11, 2019
Award Number: 1917625
Award Instrument: Standard Grant
Program Manager: Tatiana Korelsky
IIS
 Division of Information & Intelligent Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: July 15, 2019
End Date: June 30, 2023 (Estimated)
Total Intended Award Amount: $226,036.00
Total Awarded Amount to Date: $226,036.00
Funds Obligated to Date: FY 2019 = $226,036.00
History of Investigator:
  • Erin Walker (Principal Investigator)
    eawalker@pitt.edu
Recipient Sponsored Research Office: University of Pittsburgh
4200 FIFTH AVENUE
PITTSBURGH
PA  US  15260-0001
(412)624-7400
Sponsor Congressional District: 12
Primary Place of Performance: University of Pittsburgh
5000 Forbes Ave
Pittsburgh
PA  US  15213-3815
Primary Place of Performance
Congressional District:
12
Unique Entity Identifier (UEI): MKAGLD59JRL1
Parent UEI:
NSF Program(s): S-STEM-Schlr Sci Tech Eng&Math
Primary Program Source: 1300XXXXDB H-1B FUND, EDU, NSF
Program Reference Code(s): 8045
Program Element Code(s): 153600
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

Young Latino dual language learners are a growing segment of our society. Unfortunately, many of these children struggle with reading comprehension, and their parents do not always have the tools to support them. That is, the parents are often recent immigrants who are also poor readers in both Spanish and English, and thus read infrequently with their children. When these parents do engage in shared reading, they do not ask the sorts of questions that promote comprehension. This project will build upon the already-developed iPad application, EMBRACE, which helps dual language learners become successful readers of English. EMBRACE will be modified to encourage parent/child shared reading; to train the parents on how to ask questions that enhance comprehension; and to promote reading in both languages since reading skill transfers between languages. Thus, the work will potentially impact society by improving reading skills and educational achievement of both parents and children.

The project will contribute to three areas of science. The first contribution is to the study of human-computer interaction. EMBRACE will be modified with the first intelligent tutoring system designed specifically for parent-child use, thus uncovering design principles for the creation of intelligent learning environments that are sensitive to how they are being used and by whom. Second, experimental testing of the new EMBRACE system with families will contribute to understanding the processes that enhance bilingual education and how interventions can positively influence these processes. Third, a component of the testing includes the use of electroencephalography to trace changes in brain activity produced by the intervention. Thus, the research contributes to the cognitive psychology and neuroscience of reading comprehension by using a combination of process data, outcome data, and neurocognitive data from both the children and their parents.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Lekshmi Narayanan, Arun B and Lim, Ju Eun and Nguyen, Tri and Gomez, Ligia E. and Restrepo, Maria A. and Blais, Chris and Glenberg, Arthur M. and Walker, E. "Parent-EMBRACE: An Adaptive Dialogic Reading Intervention" International Conference of Artificial Intelligence in Education , 2021 https://doi.org/10.1007/978-3-030-78270-2_43 Citation Details

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

EMBRACE (Enhance Moved by Reading to Accelerate Comprehension in English) is an iPad application designed to be used in conjunction by children and caregivers. A major goal is to help children whose native language is Spanish develop greater competency in English reading comprehension.

EMBRACE, and a version created for this project, Parent-EMBRACE, are designed around several principles. First, it incorporates principles of embodied cognition, namely that reading comprehension requires a simulation of the content of the sentences using motor, perceptual, and emotional cortices. To accomplish this simulation, children manipulate images that accompany the text. That is, they move the images to illustrate sentence content (see Figure 1). A second principle is based on the notion of dialogic reading when engaged in shared book reading. That is, when a parent and a child read together, the child's comprehension of the text is improved when the parent asks questions intended to engage the child in dialog about the text. A third principle is related to bilingual literacy. The application is designed specifically for Latine families, and there are multiple places where users can engage in either Spanish or English.

The primary purpose of Parent-EMBRACE was to scaffold parents (using an intelligent tutoring system) in asking dialogic questions of three kinds: Questions about concrete components of the text (C) such as questions about specific facts or pictures; questions about abstract components of the text (A) such as what might happen next; and relational questions that relate the text to experiences that the child has had (R).

We conducted a study with 21 dyads examining use of the system and outcomes for parents and children. We are still in the process of data analysis for much of the research including a) simultaneous EEG of parents and children while reading, b) online recordings of dyad conversations, c) story retells as an index of story comprehension. Nonetheless, we have completed analysis and manuscript preparation for one important component of the research. Each dyad was video recorded while engaging in shared book reading of a hard-copy book (printed in Spanish and English). A video was made both before and after the 8-week training in Parent-EMBRACE and a control condition that involved reading the same texts but without the intelligent tutoring system that supported parents in question-asking during shared book reading. After using Parent-EMBRACE, the parents asked many more dialogic (CAR) questions than before the intervention, and parents asked a greater variety of dialogic questions.

We continue to work on the analyses of other components of the project, including automated speech processing of parent-child talk to provide Parent-EMBRACE with real-time input on how parents and children are engaging with the system. We are additionally in the process of porting the Parent-EMBRACE system into a web-based application that will be accessible from smartphones, tablets, and computers, enabling Parent-EMBRACE to reach a broader audience.

 


Last Modified: 02/09/2024
Modified by: Erin Walker

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page