Analyzing Two Automatic Latent Semantic Analysis (LSA) Assessment Methods (Inbuilt Rubric vs. Golden Summary) in Summaries Extracted from Expository Texts

Abstract

The purpose of this study was to compare two automatic assessment methods using Latent Semantic Analysis (LSA): a novel LSA assessment method (Inbuilt Rubric) and a traditional LSA method (Golden Summary). Two conditions were analyzed using the Inbuilt Rubric method: the number of lexical descriptors needed to better accommodate an expert rubric (few vs. many) and a weighting function to penalize off-topic contents included in the student summaries (weighted vs. non-weighted). One hundred and sixty-six students divided in two different samples (81 undergraduates and 85 High School students) took part in this study. Students summarized two expository texts that differed in complexity (complex/easy) and length (1,300/500 words). Results showed that the Inbuilt Rubric method simulates human assessment better than Golden summaries in all cases. The similarity with human assessment was higher for Inbuilt Rubric (r = .78 and r = .79) than for Golden Summary (r = .67 and r = .47) in both texts. Moreover, to accommodate an expert rubric into the Inbuilt Rubric method was better using few descriptors and the weighted function.

Keywords

• LSA
• Inbuilt rubric
• Automatic essay scoring (AES)
• Lexical descriptors
• Summaries