Readability Measures as Predictors of Understandability and Engagement in Searching to Learn

Ghafourian, Yasin; Hanbury, Allan and Knoth, Petr (2023). Readability Measures as Predictors of Understandability and Engagement in Searching to Learn. In: Linking Theory and Practice of Digital Libraries. TPDL 2023. (Alonso, Omar; Cousijn, Helena; Silvello, Gianmaria; Marrero, Mónica; Teixeira Lopes, Carla and Marchesin, Stefano eds.), Lecture Notes in Computer Science, vol 14241, Springer, Cham, pp. 173–181.



Search engines have become essential tools for learning, providing access to vast amounts of educational resources. However, selecting the most suitable resources from numerous options can be challenging for learners. While search engines primarily rank resources based on topical relevance, factors like understandability and engagement are crucial for effective learning as well. Understandability, a key aspect of text, is often associated with readability. This study evaluates eight commonly used readability measures to determine their effectiveness in predicting understandability, engagement, topical relevance, and user-assigned ranks. The empirical evaluation employs a survey-based methodology, collecting explicit relevance feedback from participants regarding their preferences for learning from web pages. The relevance data was then analyzed concerning the readability measures. The findings highlight that readability measures are not only reliable predictors of understandability but also of engagement. Specifically, the FKGL and GFI measures demonstrate the highest and most consistent correlation with perceived understandability and engagement. This research provides valuable insights for selecting effective readability measures to tailor search results to the users’ learning needs.

Viewing alternatives

Download history


Public Attention

Altmetrics from Altmetric

Number of Citations

Citations from Dimensions

Item Actions