Style Consistency and Authorship Attribution: A Statistical Investigation*

Bagavandas, M.; Manimannan, G.

doi:10.1080/09296170701803426

Cited by 8 publications

(8 citation statements)

References 17 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trying to predict for which persons word prediction will go well and for which persons it will not might be an interesting topic for future research. It is a question that is related to the field of computational stylometry and in particular automatic authorship attribution, although authorship attribution is the exact opposite of the task described here (guessing the author on the basis of text instead of guessing the text on the basis of the author) (Bagavandas & Manimannan, 2008).…”

Section: Idiolectsmentioning

confidence: 99%

Improving word prediction for augmentative communication by using idiolects and sociolects

Stoop

Bosch²

2014

DuJAL

View full text Add to dashboard Cite

Word prediction, or predictive editing, has a long history as a tool for augmentative and assistive communication. Improvements in the state-of-the-art can still be achieved, for instance by training personalized statistical language models. We developed the word prediction system Soothsayer. The main innovation of Soothsayer is that it not only uses idiolects, the language of one individual person, as training data, but also sociolects, the language of the social circle around that person. We use Twitter for data collection and experimentation. The idiolect models are based on individual Twitter feeds, the sociolect models are based on the tweets of a particular person and the tweets of the people he often communicates with. The sociolect approach achieved the best results. For a number of users, more than 50% of the keystrokes could have been saved if they had used Soothsayer.

show abstract

Section: Idiolectsmentioning

confidence: 99%

Improving word prediction for augmentative communication by using idiolects and sociolects

Stoop

Bosch²

2014

DuJAL

View full text Add to dashboard Cite

show abstract

“…Holmes and Forsyth (1995) use discriminant analysis to determine which vocabulary richness measures best discriminated between the Federalist papers written by Alexander Hamilton and those by James Madison. A similar work is undertaken by Bagavandas and Manimannan (2008) using canonical discriminant analysis to analyse three authors of Tamil language and show that their styles are clearly distinguishable from each other. Koppel et al (2002) CHANGE OF WORD CHARACTERISTICS IN TURKISH exploit combinations of simple lexical and syntactic features to detect the gender of the author of a formal written text with about 80% accuracy.…”

Section: Related Workmentioning

confidence: 92%

Change of Word Characteristics in 20th-Century Turkish Literature: A Statistical Analysis

Can

Patton

2010

Journal of Quantitative Linguistics

View full text Add to dashboard Cite

This article provides a century-wide quantitative analysis of the Turkish literature using 40 novels of 40 authors. We divide the century into four eras or quarter-centuries; allocate 10 novels to each era, and partition each novel into equal-sized blocks. Using crossvalidation-based discriminant analysis, with the most frequent words as discriminators, we achieve a classification rate with a relatively high accuracy when the novel blocks are classified according to their eras. We show that, by using statistical stylistic methods, the author gender of Turkish texts can be accurately identified. We also study the gender differences regarding the use of most frequent words. Using weighted least squares regression and a sliding window approach we show that as time passes, words, both in terms of tokens (in text) and types (in vocabulary), have become longer. The findings of this work have implications for the historical linguistic analysis of the Turkish language.

show abstract

“…Multivariate methods (Cortina-Borja et al, 2002), Bayesian networks (Maragoudakis et al, 2005), machine learning (Murthy & Kumar, 2006), two-dimensional classification (Vulanović, 2010) and syntactic dependency networks are used for language classification and identification. As for authorship attribution, methods are calculating intertextual distance (D. , using discriminant analysis (Bagavandas & Manimannan, 2008), neural networks (Bagavandas & Manimannan, 2009), adapted Burrows' Delta method (Smith & Aldridge, 2011), comparing entropy (Grabchak et al, 2013) and the combination of native Bayesian classifier and the k nearest neighbours (Pavlyshenko, 2013).…”

Section: Quantitative Aspects Of Jqlmentioning

confidence: 99%

Quantitative Aspects ofJournal of Quantitative Linguistics

Chen

Liu²

2014

Journal of Quantitative Linguistics

View full text Add to dashboard Cite

As one of the most authoritative journals in the field of quantitative linguistics, the Journal of Quantitative Linguistics has just passed its 20th birthday. In this paper, we collect information from the 20 volumes of this journal published so far (1994)(1995)(1996)(1997)(1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013) to build a corpus, then extract different categories of information using corpus tools. By quantitative analysis of the corpus data, complemented with information extracted from abstract and citation index databases such as Scopus and Web of Knowledge as important references, we aim to explore the objects, aims and methodologies of quantitative linguistics, its focuses and shifts in different periods, representative achievements in the past 20 years, and possible directions for the future. During the process, the role of JQL both in the development of quantitative linguistics and the wider scientific community are located and evaluated with quantitative-based evidence. The findings are that JQL contributes greatly to the development of quantitative linguistics and is in many aspects representative of changes in this field, keeping close pace with trends in the discipline and the ever-evolving characteristics of quantitative linguistics over the years.

show abstract

Style Consistency and Authorship Attribution: A Statistical Investigation*

Cited by 8 publications

References 17 publications

Improving word prediction for augmentative communication by using idiolects and sociolects

Improving word prediction for augmentative communication by using idiolects and sociolects

Change of Word Characteristics in 20th-Century Turkish Literature: A Statistical Analysis

Quantitative Aspects ofJournal of Quantitative Linguistics

Contact Info

Product

Resources

About