A Corpus-based Computational Stylometric Analysis of the Word “Árabe” in Three Spanish Generación Del 98 Writers

Abstract

Although the Generation of ’98 writers represents a group of renown Spanish novelists, philosophers, essayists and poets active during the 1898 Spanish-American war, no previous studies have attempted to analyze the diverse linguistic and stylistic features employed by such writers. This study aims to use computational stylometry to detect hidden stylistic and linguistic patterns employed by three Generation of ’98 writers, namely Pío Baroja, Vicente Blasco Ibáñez and Miguel de Unamuno. We employ a large corpus comprising 1,702,243 words representing nineteen works by the three writers. Several rigorous criteria were satisfied in designing the corpora such as authorship, genre, topic and register. Concordance, wordclouds, consensus trees, multidimensional and cluster analyses were performed to reveal the different stylistic and linguistic patterns used by the three writers. Although we focus solely on the use of the word “árabe”, we show that computational stylometry techniques can be used to help detect hidden stylistic and linguistic patterns employed by different writers. This result is significant since it can help the reader navigate across various possibilities of expressions and terminologies employed by different writers.