AUTHOR=Jacobs Arthur M. , Kinder Annette 

TITLE=Computational Models of Readers' Apperceptive Mass

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 5 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.718690

DOI=10.3389/frai.2022.718690

ISSN=2624-8212

ABSTRACT=Recent progress in machine-learning based distributed semantic models (DSM) offers new ways to simulate the apperceptive mass (AM; Kintsch, 1980) of reader groups or individual readers and to predict their performance in reading-related tasks. The AM integrates the mental lexicon with world knowledge, as e.g. acquired via reading books. Following pioneering work by Denhière and Lemaire (2004), here we computed DSMs based on a representative corpus of German children and youth literature (Jacobs et al., 2020) as null models of the AM for readers of different reading ages (grades 1-2, 3-4, and 5-6). After a series of DSM quality tests, we evaluated the performance of these models extensively in various tasks to simulate the different reader-groups’ hypothetical semantic and syntactic skills. In a final study we compared the models’ performance with that of human readers in two rating tasks. Overall the results show that with increasing reading age performance in practically all tasks becomes better. The approach taken in the present studies reveals the limits of DSMs for simulating human AM and their potential for applications in scientific studies of literature, research in education, or developmental science.