Auto-Select Reading Passages in English Assessment Tests?
This work addresses test development efficiency for educators or assessment designers, but appears incremental as it builds on existing similarity-based approaches with limited success.
The paper tackles the problem of automatically selecting reading passages for English assessment tests by proposing a method to find similar passages to existing ones, but finds that analyzed textual features lack coverage and show no meaningful correlation with suitability scores.
We show a method to auto-select reading passages in English assessment tests and share some key insights that can be helpful in related fields. In specifics, we prove that finding a similar passage (to a passage that already appeared in the test) can give a suitable passage for test development. In the process, we create a simple database-tagger-filter algorithm and perform a human evaluation. However, 1. the textual features, that we analyzed, lack coverage, and 2. we fail to find meaningful correlations between each feature and suitability score. Lastly, we describe the future developments to improve automated reading passage selection.