ReaderBench, an Environment for Analyzing Text Complexity and Reading Strategies

ReaderBench Learns Dutch: Building a Comprehensive Automated Essay Scoring System for Dutch Language

“…According to McNamara et al [15], textual complexity is linked with cohesion in terms of comprehension, as the lack of cohesion can artificially increase the perceived difficulty of a text. Thus, our model uses a local and global evaluation of cohesion within the CNA graph, computed as the average value of the semantic similarities of all linksat intra-and inter-paragraph levels [31,36]. Cohesion is estimated as the average value of [6]: (a) Wu-Palmer semantic distances applied on the WordNet lexicalized ontology, (b) cosine similarity in Latent Semantic Analysis (LSA) vector space models, and (c) the inverse of the Jensen Shannon dissimilarity (JSD) between Latent Dirichlet Allocation (LDA) topic distributions [37].…”

What Makes Your Writing Style Unique? Significant Differences Between Two Famous Romanian Orators

“…Thus, the lack of cohesion flow can increase the difficulty of a text [30] as readers can easily loose interest by finding text segments too unrelated one to another. In order to evaluate local and global cohesion, our model uses Cohesion Network Analysis (CNA) [31] to compute cohesion as the average semantic similarity [32,33] at the following levels: intra-paragraph (between sentences of each paragraph), inter-paragraph (between any pair of paragraphs), or adjacency/transition from one paragraph or sentence to the next one. Cohesion between any two text segments is estimated as the average value of the cosine similarity in Latent Semantic Analysis (LSA) vector spaces [34,35] and the inverse of the Jensen Shannon dissimilarity (JSD) [36] between Latent Dirichlet Allocation (LDA) topic distributions [37,38].…”

Predicting Comprehension from Students’ Summaries

“…Thirdly, whereas the first two categories are more representative for writing ability, the semantics and discourse analysis category is more comprehension centered by identifying the underlying cohesive links [7,8,11]. This category makes use of lexical chains, semantic distances, and discourse connectives, all centered on cohesion, a key feature in terms of discourse representation [8] and textual complexity analysis.…”

“…Hence, their ability to interconnect information based on previous experience is clearly lower. The current work builds on previous research by using refined mechanisms for identifying reading strategies and a comprehensive set of textual complexity indices incorporating classic surface indices derived from automatic essay grading techniques, morphology and syntax [10], as well as semantics and discourse [7,11]. In addition, Support Vector Machine classification models [12] use combined subsets of reading strategies and textual complexity factors, which are applied on the analyzed summaries, in order to predict students' comprehension levels.…”