Stylometry-based Approach for Detecting Writing Style Changes in Literary Texts

Adorno, Helena Montserrat Gomez; Ríos, Germán; Durán, Juan Pablo Posadas; Sidorov, Grigori; Sierra, Gerardo

doi:10.13053/cys-22-1-2882

Cited by 24 publications

(12 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, it is necessary to experiment with classifiers and deep learning to enhance the automatic classification of texts. We also want to tackle the analysis of style changes that can be observed in scientific writings during different periods, similar to what has been proposed via stylometry-based approach for detecting writing style changes in literary texts [41].…”

Section: Discussionmentioning

confidence: 99%

Written Documents Analyzed as Nature-Inspired Processes: Persistence, Anti-Persistence, and Random Walks—We Remember, as Along Came Writing—T. Holopainen

López-Ortega

Pérez-Cortés

Castillejos-Fernández

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Written communication is pivotal for societies to develop. However, lexicon and depth of information vary greatly among texts according to their purpose. Scientific texts, diffusion of science reports, general and area-specific news are all written differently. Thus, we explore the characterization of different text categories through a nature-inspired feature known as the Hurst parameter. We contend that the Hurst exponent is useful to unveil the rhetorical structure within written documents. We collected and processed texts in five categories: scientific articles, diffusion of science reports, business news, entertainment news, and random texts. Each category contains 350 documents. We found that the median for scientific texts has the highest value of the Hurst parameter (0.575), followed by business news (0.54); the median for randomly-generated texts is 0.48, which lies in the region associated with random walks. The median value for diffusion texts is 0.49, and for entertainment texts is 0.53. However, these two categories present high dispersion. We conclude that the Hurst parameter is a measure that quantifies the structure of communication in the selected categories of texts. Application of our finding in the field of e-research is discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

Written Documents Analyzed as Nature-Inspired Processes: Persistence, Anti-Persistence, and Random Walks—We Remember, as Along Came Writing—T. Holopainen

López-Ortega

Pérez-Cortés

Castillejos-Fernández

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In this study, the researchers wanted to see how the students styled the keywords of their short descriptive texts. There are several ways to identify a writer's style used in work, either from the choice of dictions, punctuations, lexical-semantic features, syntactic components, such as phrase and sentence constructions (Abdulmughni, 2019;Gómez-Adorno, Posadas-Duran, Ríos-Toledo, Sidorov, & Sierra, 2018). This study analyzed the syntactic component phrase, especially the NP.…”

Section: Figure 1 Construction Of Noun Phrasementioning

confidence: 99%

“…The stylistics integration could be seen from the NP variation and ambiguity topics. In expressing the detail of the head, the learning materials showed that combinations of determiners and modifiers could distinguish the NP style (Gómez-Adorno et al, 2018;Abdulmughni, 2019).…”

Section: Stylistic-integrated Learning Materialsmentioning

confidence: 99%

Implementing Stylistics in IELTS Writing Preparation Focusing on Noun Phrases

Andriani

Noviani

Bram

2021

JFLTL

View full text Add to dashboard Cite

In the IELTS writing preparation class, the teacher can facilitate the students by integrating the stylistic approach in building writing students’ style. Not only achieving the primary goals in English proficiency by focusing on the writing style, but students can also comfortably share their ideas in their style. The paper examined the stylistics integrated material in IELTS writing through noun phrase construction. This study employed a qualitative method and a descriptive design. The data were collected using structured observation sheets as the instrument and were analyzed stylistically. Writing materials and the writing results of 12 students at an English course were collected. Results showed that stylistics was used in phrase complexity and ambiguity as a part of writing strategies. It was supported by the three dominant types of noun phrases produced by the students in their writing: determiner + head, determiner + pre-modifier + head, and pre-modifier + head, as the evidence of the implementation of integrated material in IELTS writing. For the noun phrase uses, the students could vary the noun phrases in their complexity, function, and type in their tests, though the variations in each of those aspects were still low. Implications of the results are stylistics could be implemented in language learning-teaching activities in general. It could encourage students to develop their writing style for self-expression and more explicit writing products.

show abstract

“…Writing style change detection, defined as the task of identifying authorship changes in a document by examining the writing styles of individual authors and quantifying the differences in writing styles applied in a document, is steadily gaining momentum thanks to the annual PAN tasks [1], [2]. Traditionally it involved verifying whether a document is written entirely by one known author characterized by a uniform style throughout the document, or if it contains elements of style breaches considered as the existence of new authors [3]- [5]. It has since evolved to include even more difficult tasks of determining the total number of authors involved in documentsof known or unknown authorship, identifying the exact places where authorship switch occurs and mapping the authorship switch with its corresponding authors.…”

Section: Introductionmentioning

confidence: 99%

An Optimal Feature Set for Stylometry-based Style Change detection at Document and Sentence Level

2022

View full text Add to dashboard Cite

Writing style change detection models focus on determining the number of authors of documents with or without known authors. Determining the exact number of authors contributing in writing a document particularly when the authors contribute short texts in form of a sentence is still challenging because of the lack of standardized feature sets able to discriminate between the works of authors. Therefore, the task of identifying the best feature set for all the tasks of the writing style change detection is still considered important. This paper sought to determine the best feature set for the writing style change detection tasks; separating documents with several style changes (multi-authorship) from documents without any style changes (single-authorship), and determining the number and location of style changes in the case of multi-authorship. We performed exploratory research on existing stylometric features to determine the best document level and sentence level features. Document level features were extracted and used to separate single authored from multi-authored documents, while sentence level features were used to answer the question of determining the number of style changes To answer this question, we trained a random forest classifier to rank document level features and sentence level features separately, and applied an ablation test on the top 15 sentence level features using k-means clustering algorithm to confirm the effect of these features on model performance. The study found out that the best document level feature set for separating documents with and without style change was provided by an ensemble of features including number of sentence repetitions (num_sentence_repetitions) as the most determinant feature, 5-grams, 4-grams, Special_character, sentence_begin_lower, sentence_begin_upper, diversity, automated_readability_index, parenthesis_count, first_word_uppercase, lensear_write_formula, dale_chall_readability, difficult_words, type_token_ratio. These were the top ranked features in experiment one. On the other hand, the top fifteen sentence level features based on feature ranks using random forest classifier were diversity, dale_chall_readability grade, check_available_vowel, flesch_kincaid grade, parenthesis_count, colon_count, verbs, bigrams, alphabets, personal pronouns, coordinating conjunctions, interjections, modals, type_token ratio and punctuations_count. Consequently, the optimal feature set for determining the number of style changes in documents was considered based on the results of the ablation study on the top fifteen sentence level features, and was provided by an ensemble of features including personal pronouns, check_available_vowels, punctuations_counts, parenthesis count, coordinating conjunctions and colon count.

show abstract

Stylometry-based Approach for Detecting Writing Style Changes in Literary Texts

Cited by 24 publications

References 7 publications

Written Documents Analyzed as Nature-Inspired Processes: Persistence, Anti-Persistence, and Random Walks—We Remember, as Along Came Writing—T. Holopainen

Written Documents Analyzed as Nature-Inspired Processes: Persistence, Anti-Persistence, and Random Walks—We Remember, as Along Came Writing—T. Holopainen

Implementing Stylistics in IELTS Writing Preparation Focusing on Noun Phrases

An Optimal Feature Set for Stylometry-based Style Change detection at Document and Sentence Level

Contact Info

Product

Resources

About