Exploring an intelligent tutoring system as a conversation-based assessment tool for reading comprehension

Shi, Genghu; Lippert, Anne; Shubeck, Keith T.; Ying, Fang; Chen, Su; Pavlik, Philip I.; Greenberg, Daphne; Graesser, Arthur C.

doi:10.1007/s41237-018-0065-9

Cited by 13 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Intelligent tutoring systems (ITS) have been increasingly used in literary education during the past two decades. Traditionally, a reading process consists of pre-reading, during reading, and post-reading activities, and intelligent reading tutoring systems built on this principle are often organized reading units that contain pre-assessment, warmup activities for comprehension guides, comprehension practice, and multiple-choice questions for post-assessment (Jones et al, 2004 ) or enhance the interactions during a reading with cooperative dialogs in natural languages (Shi et al, 2018 ; Afzal et al, 2019a , b ). However, the lessons in these reading ITS are fixed, which limits their applications in the reading comprehension courses that must meet the diverse requirements of readers at different proficiency levels.…”

Section: Literature Review: Reading Models and Computer Technology In...mentioning

confidence: 99%

Reading bots: The implication of deep learning on guided reading

Huang

Dou²,

Zhang³

2023

Front. Psychol.

View full text Add to dashboard Cite

This study introduces the application of deep-learning technologies in automatically generating guidance for independent reading. The study explores and demonstrates how to incorporate the latest advances in deep-learning-based natural language processing technologies in the three reading stages, namely, the pre-reading stage, the while-reading stage, and the post-reading stage. As a result, the novel design and implementation of a prototype system based on deep learning technologies are presented. This system includes connections to prior knowledge with knowledge graphs and summary-based question generation, the breakdown of complex sentences with text simplification, and the auto-grading of readers' writing regarding their comprehension of the reading materials. Experiments on word sense disambiguation, named entity recognition and question generation with real-world materials in the prototype system show that the selected deep learning models on these tasks obtain favorable results, but there are still errors to be overcome before their direct usage in real-world applications. Based on the experiment results and the reported performance of the deep learning models on reading-related tasks, the study reveals the challenges and limitations of deep learning technologies, such as inadequate performance, domain transfer issues, and low explain ability, for future improvement.

show abstract

Section: Literature Review: Reading Models and Computer Technology In...mentioning

confidence: 99%

Reading bots: The implication of deep learning on guided reading

Huang

Dou²,

Zhang³

2023

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…Each lesson was assigned a measure of the relevance to one to three of the four theoretical levels according to the extent to which the level was targeted in this lesson. The assigned codes were primary, secondary, tertiary or no relevance of a component to a lesson, corresponding to a relevance score of 1.00, 0.67, 0.33 and 0.00 respectively ( Shi et al, 2018 ). In this study, we simply consider the primary theoretical level that characterizes the lesson.…”

Section: Datamentioning

confidence: 99%

Automated Disengagement Tracking Within an Intelligent Tutoring System

Ying

Shi

et al. 2021

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

This paper describes a new automated disengagement tracking system (DTS) that detects learners’ maladaptive behaviors, e.g. mind-wandering and impetuous responding, in an intelligent tutoring system (ITS), called AutoTutor. AutoTutor is a conversation-based intelligent tutoring system designed to help adult literacy learners improve their reading comprehension skills. Learners interact with two computer agents in natural language in 30 lessons focusing on word knowledge, sentence processing, text comprehension, and digital literacy. Each lesson has one to three dozen questions to assess and enhance learning. DTS automatically retrieves and aggregates a learner's response accuracies and time on the first three to five questions in a lesson, as a baseline performance for the lesson when they are presumably engaged, and then detects disengagement by observing if the learner's following performance significantly deviates from the baseline. DTS is computed with an unsupervised learning method and thus does not rely on any self-reports of disengagement. We analyzed the response time and accuracy of 252 adult literacy learners who completed lessons in AutoTutor. Our results show that items that the detector identified as the learner being disengaged had a performance accuracy of 18.5%, in contrast to 71.8% for engaged items. Moreover, the three post-test reading comprehension scores from Woodcock Johnson III, RISE, and RAPID had a significant association with the accuracy of engaged items, but not disengaged items.

show abstract

“…This tool is widely used for evaluation of writing quality (Zedelius et al, 2019;Macarthur et al, 2019), writing ability (Perin and Lauterbach, 2018) and cognitive understanding (Wiley et al, 2017). Some researchers have also proposed new text analysis methods based on Coh-Metrix tools (Wolfe et al, 2019) or developed new application platforms (Shi et al, 2018;McNamara et al, 2013). In addition, relevant researchers have carried out some research on the measurement of text readability and complexity (Tortorelli, 2020;Spencer et al, 2019), which also provides some valuable guidance and reference for the selection of method in this paper.…”

Section: Coh-metrix Toolmentioning

confidence: 99%

Analysis of the scientific literature's abstract writing style and citations

Wang

Deng

2021

OIR

View full text Add to dashboard Cite

PurposeThe citation counts are an important indicator of scholarly impact. The purpose of this paper is to explore the correlation between citations of scientific articles and writing styles of abstracts in papers and capture the characteristics of highly cited papers' abstracts.Design/methodology/approachThis research selected 10,000 highly cited papers and 10,000 zero-cited papers from the WOS (2008-2017) database. The Coh-Metrix 3.0 textual cohesion analysis tool was used to quantify the 108 language features of highly cited and zero-cited paper abstracts. The differences of the indicators with significant differences were analyzed from four aspects: vocabulary, sentence, syntax and readability.FindingsThe abstracts of highly cited papers contain more complex and professional words, more adjectives, adverbs, conjunctions and personal pronouns, but fewer nouns and verbs. The sentences in the abstracts of highly cited papers are more complex and the sentence length is relatively longer. The syntactic structure in abstracts of highly cited papers is relatively more complex and syntactic similarities between sentences are fewer. Highly cited papers' abstracts are less readable than zero-cited papers' abstracts.Originality/valueThis study analyses the differences between the abstracts of highly cited and those of zero-cited papers, reveals the common external and deep semantic features of highly cited papers in abstract writing styles, provide suggestions for researchers on abstract writing. These findings can help increase the scientific impact of articles and improve the review efficiency as well as the researchers' abstract writing skills.

show abstract

Exploring an intelligent tutoring system as a conversation-based assessment tool for reading comprehension

Cited by 13 publications

References 29 publications

Reading bots: The implication of deep learning on guided reading

Reading bots: The implication of deep learning on guided reading

Automated Disengagement Tracking Within an Intelligent Tutoring System

Analysis of the scientific literature's abstract writing style and citations

Contact Info

Product

Resources

About