Purpose: In this project, researchers proposed to iteratively develop and test an intervention to support  reading comprehension for university students and students in third through sixth grade. This intervention was to include a web-based search engine and intelligent tutoring system. The students were to use the search engine to select passages on the Internet on topics of interest that also met specific standards of reading difficulty. As students used the search engine, the search engine would analyze their behavior and develop a profile each individual student's level of acquisition and fluency for each word, producing an individualized framework for selecting reading materials that strengthened that student's reading comprehension. The intelligent tutoring system, called REAP, aimed to provide reader-specific lexical practice for improved reading comprehension by selecting authentic reading materials from the Internet that were matched to students' needs.

Structured Abstract

THE FOLLOWING CONTENT DESCRIBES THE PROJECT AT THE TIME OF FUNDING

The researchers are carrying out three studies in the process of developing the search engine, two of which involve university students and one of which involves students in the third through sixth grades. The first study involves adults reading texts in three different topic areas (business, arts and leisure, and sports) and three levels of different percentages of unfamiliar words. This is to measure the effects of these differences on reading times, comprehension, and readers' ability to infer word meanings, assessments of difficulty, and degree of interest. The second study involves students reading texts chosen according to the search engine's criteria for gauging their reading difficulty and taking into account the individual readers' degree of familiarity with the vocabulary, to evaluate the feasibility of individualized text selection using materials drawn from the web. In the third study, the researchers are having students in grades 3 through 6 use the search engine to select and practice reading with materials selected from the web that reflect increasing levels of difficulty in the vocabulary words included in the texts and measuring the development of their reading comprehension.

Products AND Publications

ERIC Citations: Find available citations in ERIC for this award here.

Select Publications:

Journal articles

Collins-Thompson, K., and Callan, J. (2005). Predicting Reading Difficulty With Statistical Language Models. Journal of the American Society for Information Science and Technology, 56(13): 1448–1462.

Proceedings

Brown, J. Frishkoff, G., and Eskenazi, M. (2005). Automatic Question Generation for Vocabulary Assessment. In Proceedings of HLT/EMNLP 2005 (pp. 819–826). Vancouver, Canada: Association for Computational Linguistics.

Brown, J., and Eskenazi, M. (2004). Retrieval of Authentic Documents for Reader-Specific Lexical Practice. In Proceedings of Instil/ICALL Symposium 2004 (pp. 1–4). Venice, Italy: International Speech Communication Association.

Brown, J., and Eskenazi, M. (2005). Student, Text and Curriculum Modeling for Reader-Specific Document Retrieval. In Proceedings of the IASTED International Conference on Human-Computer Interaction 2005. Phoenix, AZ: International Association of Science and Technology for Development.

Collins-Thompson, K., and Callan, J. (2004). A Language Modeling Approach to Predicting Reading Difficulty. In Proceedings of the HLT/NAACL 2004 Conference (pp. 193–200). Boston: North American Chapter of the Association for Computational Linguistics.

Collins-Thompson, K., and Callan, J. (2004). Information Retrieval for Language Tutoring: An Overview of the REAP Project. In Proceedings of the Twenty Seventh Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 544–545). New York: ACM.

Collins-Thompson, K., and Callan, J. (2005). Query Expansion Using Random Walk Models. In Proceedings of the 14th ACM International Conference on Information and Knowledge Management (pp. 704–711). New York: ACM Press.