Reflecting Comprehension through French Textual Complexity Factors

Abstract

Abstract-Research efforts in terms of automatic textual complexity analysis are mainly focused on English vocabulary and few adaptations exist for other languages. Starting from a solid base in terms of discourse analysis and existing textual complexity assessment model for English, we introduce a French model trained on 200 documents extracted from school manuals pre-classified into five complexity classes. The underlying textual complexity metrics include surface, syntactic, morphological, semantic and discourse specific factors that are afterwards combined through the use of Support Vector Machines. In the end, each factor is correlated to pupil comprehension metrics scores, spanning throughout multiple classes, therefore creating a clearer perspective in terms of measurements impacting the perceived difficulty of a given text. In addition to purely quantitative surface factors, specific parts of speech and cohesion have proven to be reliable predictors of learners' comprehension level, creating nevertheless a strong background for building dependable French textual complexity models.

How Well Do Student Nurses Write Case Studies? A Cohesion-Centered Textual Complexity Analysis

“…(id., p. 765) This is an aggregated measure based on the identification of paragraph relationships in terms of semantic relatedness that captures global cohesion. Besides a wide variety of textual complexity indices presented in detail in previous papers [11,29], ReaderBench integrates specific measures derived from the polyphonic model [30], inspired from Bakhtin's dialogism [31]. According to this model, interanimating 'voices', in a generalized way, are coherent points of view over semantically related concepts.…”

ReaderBench : An Integrated Cohesion-Centered Framework

“…Overall, the validations supported the accuracy of the models built on cohesion and dialogism, whereas the proposed methods emphasized the dialogical perspective of collaboration in CSCL conversations. Experiment 3 [7] consisted of building a textual complexity model that was distributed into five complexity classes and directly mapped onto five primary grade classes of the French national education system. Multiclass Support Vector Machine (SVM) classifications were used to assess exact agreement (EA = .733) and adjacent agreement (AA = .…”

Predicting Comprehension from Students’ Summaries

“…As presented in [22], there are three main categories of factors considered in the textual complexity analysis of the French language that also include the most common and frequently used indices from the previous solutions. Firstly, the surface category is comprised of quantitative measures and the analysis of individual elements (words, phrases, paragraphs) by extracting simple or combined indices (e.g., Page's grading technique for automated scoring including number of words, sentences or paragraphs, number of commas, average word length or words per sentence) [23], as well as word and character entropy [10].…”

“…Predefined rules and patterns were used to automatically clean the transcribed verbalizations. With regards to the proposed textual complexity factors applied on students' summaries, the same factors were used in [22] to predict the difficulty of the selected French stories. As a result, both texts were classified as being optimal for 3 rd graders, making them appropriate in terms of reading ease for all the students participating in our experiments.…”