We propose that machine-learned computational models (MLCMs), in which the model parameters and perhaps even structure are learned from data, can complement extant approaches to the study of text and discourse. Such models are particularly useful when theoretical understanding is insufficient, when the data are rife with nonlinearities and…

Little research has examined young children's reading preference by text type. We examined 37 children reading, evaluated their reading experience, and surveyed parents for at-home reading practices and parent predictions of their child's text preference. Framed by social learning theory using a multiple-case study research design, data analysis…