Developmental Sentence Scoring (DSS) is a standardized language sample analysis procedure that evaluates and scores a child's use of standard American-English grammatical rules within complete sentences. Automated DSS programs have the potential to increase the efficiency and reduce the amount of time required for DSS analysis. The present study examines the accuracy of one automated DSS software program, DSSA 2.0, compared to manual DSS scoring on previously collected language samples from 30 children between the ages of 2-5 and 7-11. Additionally, this study seeks to determine the source of error in the automated score by comparing DSSA 2.0 analysis given manually versus automatedly assigned grammatical tag input. The overall accuracy of DSSA 2.0 was 86%; the accuracy of individual grammatical category-point value scores varied greatly. No statistically significant difference was found between the two DSSA 2.0 input conditions (manual vs. automated tags) suggesting that the underlying grammatical tagging is not the primary source of error in DSSA 2.0 analysis.
Identifer | oai:union.ndltd.org:BGMYU2/oai:scholarsarchive.byu.edu:etd-6891 |
Date | 01 May 2016 |
Creators | Janis, Sarah Elizabeth |
Publisher | BYU ScholarsArchive |
Source Sets | Brigham Young University |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | All Theses and Dissertations |
Rights | http://lib.byu.edu/about/copyright/ |
Page generated in 0.0015 seconds