Open AccessAnalysing corpus-based criterial conjunctions for automatic proficiency classification
Author(s) -
Ángeles Zarco-Tejada,
Carmen Noya Gallardo,
Ma Carmen Merino Ferradá,
Isabel Calderón López
Publication year - 2016
Publication title -
journal of english studies
Language(s) - English
Resource type - Journals
eISSN - 1695-4300
pISSN - 1576-6357
DOI - 10.18172/jes.3090
Subject(s) - cohesion (chemistry) , computer science , natural language processing , conjunction (astronomy) , artificial intelligence , coherence (philosophical gambling strategy) , linguistics , variety (cybernetics) , profiling (computer programming) , language proficiency , mathematics , programming language , statistics , philosophy , chemistry , physics , organic chemistry , astronomy
The linguistic profiling of L2 learning texts can be taken as a model for automatic proficiency assessment of new texts. But proficiency levels are distinguished by many different linguistic features among which the use of cohesive devices can be a criterial element for level distinctions, either in the number of conjunctions used (quantitative) and/or in the type and variety of them (qualitative). We have carried such an analysis with a subgroup of the CLEC (CEFR-levelled English Corpus) using Coh-Metrix, a tool for computing computational cohesion and coherence metrics for written and spoken texts, but our results suggest that automatic proficiency level assessment needs a deeper examination of conjunctions that should rely on the analysis of conjunction-types use and conjunction varieties, with an analysis of lexical choice. A variable based on familiarity ranks could help to predict cohesive levels proficiencyoriented.