Automated Scoring of Students’ Small‐Group Discussions to Assess Reading Ability

• Published in: Educational measurement, issues and practice Vol. 37; no. 2; pp. 20 - 34
• Main Authors: Kosh, Audra E., Greene, Jeffrey A., Murphy, P. Karen, Burdick, Hal, Firetto, Carla M., Elmore, Jeff
• Format: Journal Article
• Language: English
• Published: Washington Wiley-Blackwell 01.06.2018; Wiley Subscription Services, Inc
• Subjects: assessment; automated scoring; Automation; Computer Assisted Testing; Content Analysis; Discourse Analysis; Educational tests & measurements; Elementary School Students; Feasibility Studies; Grade 4; Group Discussion; Hierarchical Linear Modeling; Multiple Choice Tests; Predictor Variables; Reading Ability; Reading Comprehension; Reading Fluency; Reading Tests; Scores; Semantics; Small Group Instruction; Statistical Analysis; Student Evaluation; Students; Transcripts (Written Records); Validity
• ISSN: 0731-1745; 1745-3992
• DOI: 10.1111/emip.12174

We explored the feasibility of using automated scoring to assess upper‐elementary students’ reading ability through analysis of transcripts of students’ small‐group discussions about texts. Participants included 35 fourth‐grade students across two classrooms that engaged in a literacy intervention called Quality Talk. During the course of one school year, data were collected at 10 time points for a total of 327 student‐text encounters, with a different text discussed at each time point. To explore the possibility of automated scoring, we considered which quantitative discourse variables (e.g., variables to measure language sophistication and latent semantic analysis variables) were the strongest predictors of scores on a multiple‐choice and constructed‐response reading comprehension test. Convergent validity evidence was collected by comparing automatically calculated quantitative discourse features to scores on a reading fluency test. After examining a variety of discourse features using multilevel modeling, results showed that measures of word rareness and word diversity were the most promising variables to use in automated scoring of students’ discussions.