Techniques and tools for textual analysis of educational resources

In the Erasmus+ project We-Collab, we developed a toolkit for Text Analysis and applied it to educational materials. The analysis addresses mainly lexicon level and lexicon variety, sentence structure and text complexity, contexts of use of words. Specific functions support the management of multilingual glossaries and the annotation of texts with references to glossary entries and with links to online lexico-semantic resources. The multilingual architecture is based on spaCy, a modern library for Natural Language Processing (NLP). Target users include content creators, teachers and students; teachers could be interested in assessing the suitability of text materials for a target audience or an educational goal; learners, in text understanding, finding or guessing the meaning of unknown terms.