Automated assessment of learner text complexity

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10441575" target="_blank" >RIV/00216208:11320/21:10441575 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=hyKw8Rj.Wk" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=hyKw8Rj.Wk</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.asw.2021.100529" target="_blank" >10.1016/j.asw.2021.100529</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automated assessment of learner text complexity

Popis výsledku v původním jazyce

EFL methodology has always recognized the importance of giving student learners of foreign languages regular and quick feedback on student production, both written and oral. The presented paper describes the decisions taken during the development of an application to measure text complexity, and shows how the results achieved with this application were translated into feedback related to the author&apos;s language proficiency. Along with some standard text complexity features, this tool takes into account those that are significant for Russian learners of English. The application provides students with the statistics of the relevant linguistic features of the text in comparison with texts of the learner essays that were considered the top and the bottom levels in the learner corpus. The paper also points out what text features are especially relevant for the assessment of the essays written in English by Russian students. The choice was made possible after the analysis of 3440 texts from Russian Error-Annotated English Learner Corpus, and after applying methods of machine learning and statistical analysis to predict the grade that could be received for the essay.

Název v anglickém jazyce

Automated assessment of learner text complexity

Popis výsledku anglicky

EFL methodology has always recognized the importance of giving student learners of foreign languages regular and quick feedback on student production, both written and oral. The presented paper describes the decisions taken during the development of an application to measure text complexity, and shows how the results achieved with this application were translated into feedback related to the author&apos;s language proficiency. Along with some standard text complexity features, this tool takes into account those that are significant for Russian learners of English. The application provides students with the statistics of the relevant linguistic features of the text in comparison with texts of the learner essays that were considered the top and the bottom levels in the learner corpus. The paper also points out what text features are especially relevant for the assessment of the essays written in English by Russian students. The choice was made possible after the analysis of 3440 texts from Russian Error-Annotated English Learner Corpus, and after applying methods of machine learning and statistical analysis to predict the grade that could be received for the essay.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2021

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Assessing Writing

ISSN

1075-2935

e-ISSN

1873-5916

Svazek periodika

49

Číslo periodika v rámci svazku

červenec 2021

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

16

Strana od-do

100529

Kód UT WoS článku

000671850600002

EID výsledku v databázi Scopus

2-s2.0-85105042026