Publication Date
| In 2026 | 0 |
| Since 2025 | 1 |
| Since 2022 (last 5 years) | 2 |
| Since 2017 (last 10 years) | 3 |
| Since 2007 (last 20 years) | 3 |
Descriptor
Source
| Grantee Submission | 3 |
Author
| Danielle S. McNamara | 2 |
| Linh Huynh | 2 |
| Bailing Lyu | 1 |
| Dongwon Lee | 1 |
| Ethan Prihar | 1 |
| Jia Tracy Shen | 1 |
| Jonna M. Kulikowich | 1 |
| Matthew T. McCrudden | 1 |
| Michiharu Yamashita | 1 |
| Neil Heffernan | 1 |
| Sean McGrew | 1 |
| More ▼ | |
Publication Type
| Reports - Research | 3 |
| Journal Articles | 2 |
| Speeches/Meeting Papers | 1 |
Education Level
| Higher Education | 1 |
| Postsecondary Education | 1 |
Audience
Location
Laws, Policies, & Programs
Assessments and Surveys
What Works Clearinghouse Rating
Peer reviewed
Direct linkMatthew T. McCrudden; Linh Huynh; Bailing Lyu; Jonna M. Kulikowich; Danielle S. McNamara – Grantee Submission, 2024
Readers build a mental representation of text during reading. The coherence building processes readers use to build a mental representation during reading is key to comprehension. We examined the effects of self- explanation on coherence building processes as undergraduates (n =51) read five complementary texts about natural selection and…
Descriptors: Reading Processes, Reading Comprehension, Undergraduate Students, Evolution
Linh Huynh; Danielle S. McNamara – Grantee Submission, 2025
Four versions of science and history texts were tailored to diverse hypothetical reader profiles (high and low reading skills and domain knowledge), generated by four Large Language Models (i.e., Claude, Llama, ChatGPT, and Gemini). The Natural Language Processing (NLP) technique was applied to examine variations in Large Language Model (LLM) text…
Descriptors: Artificial Intelligence, Natural Language Processing, Textbook Evaluation, Individualized Instruction
Download full textJia Tracy Shen; Michiharu Yamashita; Ethan Prihar; Neil Heffernan; Xintao Wu; Sean McGrew; Dongwon Lee – Grantee Submission, 2021
Educational content labeled with proper knowledge components (KCs) are particularly useful to teachers or content organizers. However, manually labeling educational content is labor intensive and error-prone. To address this challenge, prior research proposed machine learning based solutions to auto-label educational content with limited success.…
Descriptors: Mathematics Education, Knowledge Level, Video Technology, Educational Technology
