Mining Texts, Learner Productions and Strategies with ReaderBench
The chapter introduces ReaderBench, a multi-lingual and flexible environment that integrates text mining technologies for assessing a wide range of learners’ productions and for supporting teachers in several ways. ReaderBench offers three main functional
- PDF / 1,048,184 Bytes
- 33 Pages / 439.37 x 666.142 pts Page_size
- 92 Downloads / 141 Views
Mining Texts, Learner Productions and Strategies with ReaderBench Mihai Dascalu, Philippe Dessus, Maryse Bianco, Stefan Trausan-Matu and Aurélie Nardy
Abstract The chapter introduces ReaderBench, a multi-lingual and flexible environment that integrates text mining technologies for assessing a wide range of learners’ productions and for supporting teachers in several ways. ReaderBench offers three main functionalities in terms of text analysis: cohesion-based assessment, reading strategies identification and textual complexity evaluation. All of these have been subject to empirical validations. ReaderBench may be used throughout an entire educational scenario, starting from the initial complexity assessment of the reading materials, the assignment of texts to learners, the detection of reading strategies reflected in one’s self-explanations, and comprehension evaluation fostering learner’s self-regulation process. Keywords Cohesion-based discourse analysis strategies Textual complexity
Topics extraction
Reading
M. Dascalu (&) S. Trausan-Matu University Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania e-mail: [email protected] S. Trausan-Matu e-mail: [email protected] P. Dessus M. Bianco Laboratoire des Sciences de l’Education, University Grenoble Alpes, BP 47, 38040 Grenoble, France e-mail: [email protected] M. Bianco e-mail: [email protected] A. Nardy Laboratoire de linguistique et didactique des langues étrangères et maternelles, University Grenoble Alpes, BP 25, 38040 Grenoble, France e-mail: [email protected]
A. Peña-Ayala (ed.), Educational Data Mining, Studies in Computational Intelligence 524, DOI: 10.1007/978-3-319-02738-8_13, Springer International Publishing Switzerland 2014
345
346
M. Dascalu et al.
Abbreviations AA CAF CSCL DRP EA FFL ICC LDA LMS LSA NLP POS SVM TASA Tf-Idf WOLF
Adjacent agreement Complexity, accuracy and fluency Computer supported collaborative learning Degree of reading power Exact agreement French as foreign language Intra-class correlations Latent Dirichlet allocation Learning management system Latent semantic analysis Natural language processing Part of speech Support vector machine Touchstone Applied Science Associates, Inc Term frequency – inverse document frequency WordNet Libre du Français
13.1 Introduction Text mining techniques based on advanced Natural Language Processing (NLP) and Machine Learning algorithms, as well as the ever-growing computer power, enable the design and implementation of new systems that automatically deliver to learners summative and formative assessments using multiple sets of data (e.g., textual materials, behavior tracks, meta-cognitive explanations). New automatic evaluation processes allow teachers and learners to have immediate information on the learning or understanding processes. Furthermore, computer-based systems can be integrated into pedagogical scenarios, providing activity flows that foster learning. ReaderBench is a fully functi
Data Loading...
