Date
Publisher
arXiv
Educational e-book platforms provide valuable information to teachers and researchers through two main sources: reading activity data and reading content data. While reading activity data is commonly used to analyze learning strategies and predict low-performing students, reading content data is often overlooked in these analyses. To address this gap, this study proposes LECTOR (Lecture slides and Topic Relationships), a model that summarizes information from reading content in a format that can be easily integrated with reading activity data. Our first experiment compared LECTOR to representative Natural Language Processing (NLP) models in extracting key information from 2,255 lecture slides, showing an average improvement of 5% in F1-score. These results were further validated through a human evaluation involving 28 students, which showed an average improvement of 21% in F1-score over a model predominantly used in current educational tools. Our second experiment compared reading preferences extracted by LECTOR with traditional reading activity data in predicting low-performing students using 600,712 logs from 218 students. The results showed a tendency to improve the predictive performance by integrating LECTOR. Finally, we proposed examples showing the potential application of the reading preferences extracted by LECTOR in designing personalized interventions for students.
Study at a glance
- Question: Can summarizing e-book reading content help identify struggling students and provide personalized support?
- Setting and data: 2,255 lecture slides, 600,712 reading logs from 218 students, and an evaluation involving 28 students.
- Method: Computational model testing against existing language models, human evaluation with students, and predictive modeling using student reading logs.
Why it matters
While reading activity data from educational e-books is commonly used to analyze learning strategies and predict low-performing students, reading content data is often overlooked in these analyses.
Key findings
- Across 600,712 e-book reading logs from 218 students, combining content summaries with activity data tended to improve predictions of low-performing students.
- In student evaluations, the AI tool extracted key slide information 21% more effectively than a model commonly used in current educational tools.
- The tool extracted key information from 2,255 lecture slides 5% more accurately on average than standard language processing models.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
