We conducted two experiments to assess the alignment between Generative AI (GenAI) text personalization and hypothetical readers' profiles. In Experiment 1, four LLMs (i.e., Claude 3.5 Sonnet; Llama; Gemini Pro 1.5; ChatGPT 4) were prompted to tailor 10 science texts (i.e., biology, chemistry, physics) to accommodate four different profiles…

The paper provides an example of how immigration is constructed by receiving societies as a comprehension or language problem that requires special solutions. It focuses on the application of Easy-to-Read, a simplified register currently in expansion which addresses different groups of people with intellectual disabilities, to immigrants in Spain.…

In this paper, we applied the crowdsourcing approach to develop an automated popularity summary scoring, called wild summaries. In contrast, the golden standard summaries generated by one or more experts are called expert summaries. The innovation of our study is to compute LSA (Latent Semantic Analysis) similarities between target summary and…

A study investigated the effect of properties of words and texts on the incidental learning of word meanings during normal reading. Subjects--352 students in third, fifth, and seventh grades--read either expository or narrative passages selected from grade-level textbooks, and after six days were tested on their knowledge of difficult words from…

Linguistic cohesion involves the semantic and syntactic relationships that link sentences together. Research on linguistic cohesion is related to readability and to developmental and ability-level issues in reading/writing. Instructional strategies for low-ability readers/writers include predicting comprehension problems through cohesion analysis…