Lexical Stress-Based Authorship Attribution with Accurate Pronunciation Patterns Selection

Ivanov, Lubomir; Aebig, Amanda; Meerman, Stephen

doi:10.1007/978-3-030-00794-2_7

Cited by 6 publications

(4 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With this goal in mind, various techniques can be employed. One possibility consists of using only features that are obviously topic-agnostic, such as function words or syntactic features (Halvani et al, 2020;Jafariakinabad et al, 2020). A second possibility consists of actively masking topical content via a so-called "text distortion" approach (Stamatatos, 2018;van der Goot et al, 2018).…”

Section: Topic-agnostic Features: Base Features and Distorted Viewsmentioning

confidence: 99%

“…The work by Dumalus and Fernandez (2011) is a pioneering one in this sense: using the CMU Pronouncing Dictionary, they extract the pronunciation of each word and transform it into a “stress string,” where the symbols {0, 1, 2} represent the absence of stress, a primary stress, and a secondary stress in the syllable, respectively. Ivanov et al (2018) improve on this work: since many English words are homographs (i.e., they have the same spelling but different pronunciation and meaning), they select the correct pronunciation, and hence the correct stress string, by studying the parts of speech of the words in the text. Similarly, Plecháč (2021) employs the frequencies of “rhythmic types” (where a rhythmic type is a bit string representing the distribution of stressed and unstressed syllables in a line) as features in tackling the attribution problem for Henry VIII .…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Syllabic quantity patterns as rhythmic features for Latin authorship attribution

Corbara

Moreo

Sebastiani

2022

Asso for Info Science & Tech

View full text Add to dashboard Cite

It is well known that, within the Latin production of written text, peculiar metric schemes were followed not only in poetic compositions, but also in many prose works. Such metric patterns were based on so-called syllabic quantity, that is, on the length of the involved syllables, and there is substantial evidence suggesting that certain authors had a preference for certain metric patterns over others. In this research we investigate the possibility to employ syllabic quantity as a base for deriving rhythmic features for the task of computational authorship attribution of Latin prose texts. We test the impact of these features on the authorship attribution task when combined with other topic-agnostic features. Our experiments, carried out on three different datasets using support vector machines (SVMs) show that rhythmic features based on syllabic quantity are beneficial in discriminating among Latin prose authors.

show abstract

Section: Topic-agnostic Features: Base Features and Distorted Viewsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Syllabic quantity patterns as rhythmic features for Latin authorship attribution

Corbara

Moreo

Sebastiani

2022

Asso for Info Science & Tech

View full text Add to dashboard Cite

show abstract

“…The work by Dumalus and Fernandez (2011) is a pioneering one in this sense: using the CMU Pronouncing Dictionary, they extract the pronunciation of each word and transform it into a "stress string", where the symbols {0, 1, 2} represent the absence of stress, a primary stress, and a secondary stress in the syllable, respectively. Ivanov et al (2018) improves on this work: since many English words are homographs (i.e., they have the same spelling but different pronunciation and meaning), they select the correct pronunciation, and hence the correct stress string, by studying the parts of speech of the words in the text. Similarly, Plecháč (2021) employs the frequencies of "rhythmic types" (where a rhythmic type is a bit string representing the distribution of stressed and unstressed syllables in a line) as features in tackling the attribution problem for Henry VIII.…”

Section: Prosodic Features In Aidmentioning

confidence: 99%

Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution

Corbara¹,

Moreo²,

Sebastiani³

2021

Preprint

View full text Add to dashboard Cite

It is well known that, within the Latin production of written text, peculiar metric schemes were followed not only in poetic compositions, but also in many prose works. Such metric patterns were based on so-called syllabic quantity, i.e., on the length of the involved syllables, and there is substantial evidence suggesting that certain authors had a preference for certain metric patterns over others. In this research we investigate the possibility to employ syllabic quantity as a base for deriving rhythmic features for the task of computational authorship attribution of Latin prose texts. We test the impact of these features on the authorship attribution task when combined with other topic-agnostic features. Our experiments, carried out on three different datasets, using two different machine learning methods, show that rhythmic features based on syllabic quantity are beneficial in discriminating among Latin prose authors.

show abstract

“…Recent examples of such novel stylistic features include prosodic features such as lexical stress, assonance, consonance, and alliteration. They have been shown to raise the accuracy of the attribution task when used in combination with traditional stylistic features (Ivanov 2019;Ivanov, Aebig, and Meerman 2018, Ivanov 2016, Ivanov and Petrovic 2015. Our work seeks to enhance this set of alternative stylistic features by exploring the usefulness of abstractness/concreteness of words and phrases as stylistic features for authorship attribution.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Dictionary Approach to Abstractness/Concreteness-Based Authorship Attribution

Ivanov

2023

FLAIRS

View full text Add to dashboard Cite

We present some early results from a research project aimed at exploring the usefulness of abstractness/concreteness as stylistic features for authorship attribution. We conjecture that authors use abstract/concrete words and phrases in suf- ficiently unique ways, so that machine learning classifiers can learn to distinguish the individual authors’ writing styles. Our approach is based on using the abstractness rat- ings of words and phrases from texts with established au- thorship to generate training vectors for different machine learning classifiers. The combined word/phrase ratings are extracted from two separate abstractness dictionaries – an approach that yields stronger results than using single ab- stractness dictionaries. The paper describes the details of our methodology and compares the results to those obtained using traditional authorship attribution stylistic features. The limitations of our current methodology and directions for further research are outlined at the end of the paper.

show abstract

Lexical Stress-Based Authorship Attribution with Accurate Pronunciation Patterns Selection

Cited by 6 publications

References 18 publications

Syllabic quantity patterns as rhythmic features for Latin authorship attribution

Syllabic quantity patterns as rhythmic features for Latin authorship attribution

Syllabic Quantity Patterns as Rhythmic Features for Latin Authorship Attribution

A Multi-Dictionary Approach to Abstractness/Concreteness-Based Authorship Attribution

Contact Info

Product

Resources

About