Automatic Classification of the Complexity of Nonfiction Texts in Portuguese for Early School Years

Abstract

Recent research shows that most Brazilian students have serious problems regarding their reading skills. The full development of this skill is key for the academic and professional future of every citizen. Tools for classifying the complexity of reading materials for children aim to improve the quality of the model of teaching reading and text comprehension. For English, Feng's work [11] is considered the state-of-art in grade level prediction and achieved 74% of accuracy in automatically classifying 4 levels of textual complexity for close school grades. There are no classifiers for nonfiction texts for close grades in Portuguese. In this article, we propose a scheme for manual annotation of texts in 5 grade levels, which will be used for customized reading to avoid the lack of interest by students who are more advanced in reading and the blocking of those that still need to make further progress. We obtained 52% of accuracy in classifying texts into 5 levels and 74% in 3 levels. The results prove to be promising when compared to the state-of-art work. 1 , Brazilian students have serious problems regarding their reading skills. The most recent survey, carried out in 2012, showed results for Brazil below the average of the countries surveyed. 49.5% of Brazilian students did not reach the levels considered minimum in reading, which means that, at best, they can only recognize themes of simple and familiar texts. Furthermore, only 0.5% of Brazilian students reached maximum reading levels, which means that only one in every 200 young people in Brazil is able to deal with complex texts and perform in-depth analysis on such texts. More negative numbers were seen in the Brazilian National High School Exam (ENEM -Exame Nacional do Ensino Médio) in 2014: from the 6.1 million students who did the exam, 529 flunked the composition. Experts stated that most students do not even understand the wording of the question. Only 250 students, equivalent to 0.004%, aced the composition.The development of reading skills has long been related to success in future academic and professional activities. Aimed at raising the quality of the teaching model for reading and text comprehension in this country and trying to close some gaps in Brazilian public policies for education, many features and computer systems for the Brazilian Portuguese have been launched recently. An example is the First Book Project (Projeto Primeiro Livro) 2 , which helps children and young people from public schools to learn grammar, spelling and develop narratives. Another example is the Victor Civita Foundation, sponsored by the publishing house Abril, which supports teachers, school managers and public policy makers of Elementary Education with lesson plan search engines, social network for educators to exchange experience and share knowledge, and a resource bank for classes 3 .Currently, in Brazil, the elementary school is divided into two stages -1st to 5th year, and 6th to 9th year. The National Curriculum Parameters (1998), however, divide these two stages ...

Adaptação Lexical Automática em Textos Informativos do Português Brasileiro para o Ensino Fundamental

“…O SIMPLEX-PB ) (ou somente SIMPLEX)é um córpus originalmente concebido para avaliação de métodos de Simplificação Lexical em Português Brasileiro, criado e disponibilizado ao público como um esforço para fomentar a pesquisa naárea. Ele contém 1.719 instâncias segundo a proporção de palavras de conteúdo encontradas no corpus (Hartmann et al, 2016): 56 % substantivos, 18% adjetivos, 18% verbos e 6% advérbios. A partir dessa distribuição, há ainda uma subdivisão igualmente distribuída para favorecer: palavras mais frequentes, palavras com maior número de sinônimos e palavras com mais sentidos.…”

Adaptação lexical automática em textos informativos para o Ensino Fundamental

“…3 O córpus SIMPLEX-PB 3.0 O SIMPLEX-PB (Hartmann, Paetzold e Aluísio, 2018) (ou somente SIMPLEX)é um córpus originalmente concebido para avaliação de métodos de Simplificação Lexical em Português Brasileiro, criado e disponibilizado ao público como um esforço para fomentar a pesquisa naárea. Ele contém 1.719 instâncias segundo a proporção de palavras de conteúdo encontradas no corpus (Hartmann et al, 2016a): 56 % substantivos, 18% adjetivos, 18% verbos e 6% advérbios. A partir dessa distribuição, há ainda uma subdivisão igualmente distribuída para favorecer: palavras mais frequentes, palavras com maior número de sinônimos e palavras com mais sentidos.…”

“…Sabendo, ainda, que há uma progressão natural na aquisição lexical conforme os anos escolares avançam (Hartmann et al, 2016b),é natural afirmarmos que as palavras do dicionário do tipo 3 são mais complexas que as palavras dos dicionários do tipo 2, e que essas são mais complexas do que as palavras do dicionários do tipo 1. Para a tarefa de Simplificação Lexical, podemos utilizar essas diferenças para aprendermos, com uso de métodos de Machine Learning, quais são as características que determinam a gradação da complexidade de uma palavra e, consequente-mente, ranqueá-la de acordo com a sua complexidade frente a outras palavras.…”

“…Treino Desenvolvimento Teste • Contagem -Frequência e diversidade contextual das palavras e de seus lemas no córpus Leg2Kids (Hartmann e Aluísio, 2019) e no córpus de textos informativos infantis (Hartmann et al, 2016b);…”

“…• Frequência da palavra no córpus de textos informativos para crianças do Ensino Fundamental (Hartmann et al, 2016a);…”