Machine-Learned Computational Models Can Enhance the Study of Text and Discourse: A Case Study Using Eye Tracking to Model Reading Comprehension

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...

Full description

Saved in:
Bibliographic Details
Published in:Discourse processes 2020-07, Vol.57 (5-6), p.420-440
Main Authors: D'Mello, Sidney K., Southwell, Rosy, Gregg, Julie
Format: Article
Language:English
Subjects:
Accuracy
Case Studies
Classification
College Students
Comparative Analysis
Computational Linguistics
Computer Software
Correlation
Discourse Analysis
Eye Movements
Intervention
Machine learning
Measurement
Prediction
Private Colleges
Reading Comprehension
Reading Processes
Scores
Simulation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 interactivity, and when researchers aspire to take advantage of "big data." Being fully instantiated computer programs, MLCMs can also be used for autonomous assessment and real-time intervention. We illustrate these ideas in the context of an eye movement-based MLCM of textbase comprehension during reading along connected text. Using a dataset where 104 participants read a 6,500-word text, we trained Random Forests models to predict comprehension scores from six eye movement features. The models were highly accurate (area under the receiver operating characteristic curve  = .902; r = .661), robust, and generalized across participants, suggesting possible use in future studies. We conclude by arguing for an increased role of MLCMs in the future of discourse research.
ISSN:0163-853X
1532-6950
DOI:10.1080/0163853X.2020.1739600