844 research outputs found
Number of 3-grams per author (in thousands).
No full textNumber of 3-grams per author (in thousands).</p
Author Assertion of furtive Write Print Using Character n-Grams
No full textThe exceptionality of shape and style of authors can be used for author's identification. The goalmouth of authorship attribution is to identify a set of features that remain relatively constant among a number of writings by a particular author. This paper deals with text author identification problem using character n-grams. However, the commonly usage is total n-gram for identification purpose but we consider all types of n-grams e.g. initial, medial, final and total bi.grams and tri.grams. Experiments show that authors profiles generated with initial bi.grams and initial tri.grams are effective in identifying texts authors in comparison with other n-gram profiles. The results disclosed in this paper leads to approximate 100% accuracy in identifying the author from unknown text
Fine dust and allergy measurement in schools - Results of a coordinated project in Lower Saxony, Bavaria, Berlin and Baden-Wurtternberg
No full textExploring Word Embeddings and Character N -Grams for Author Clustering Notebook for PAN at CLEF 2016
No full textAbstract We presented our system for PAN 2016 Author Clustering task. Our software used simple character n-grams to represent the document collection. We then ran K-Means clustering optimized using the Silhouette Coefficient. Our system yields competitive results and required only a short runtime. Character n-grams can capture a wide range of information, making them effective for authorship attribution. We also present a comparison study of two different features: character n-grams and word embeddings
Ensemble-based Author Identification Using Character N-grams
No full textAbstract. This paper deals with the problem of identifying the most likely author of a text. Several thousands of character n-grams, rather than lexical or syntactic information, are used to represent the style of a text. Thus, the author identification task can be viewed as a single-label multiclass classification problem of high dimensional feature space and sparse data. In order to cope with such properties, we propose a suitable learning ensemble based on feature set subspacing. Performance results on two well-tested benchmark text corpora for author identification show that this classification scheme is quite effective, significantly improving the best reported results so far. Additionally, this approach is proved to be quite stable in comparison with support vector machines when using limited number of training texts, a condition usually met in this kind of problem.
Author Verification Using Syntactic N-grams Notebook for PAN at CLEF 2015
No full textAbstract This paper describes our approach to tackle the Author Verification task at PAN 2015. Our method builds a representation of an author's style by using the information contained in dependency trees. This information is represented as syntactic n-grams and used to conform a vector space. Using unsupervised machine learning approach, each instance is associated to the correponding author using the Jaccard distance. In this paper, we describe the features that were used and the employed unsupervised machine learning algorithm
Local n-grams for author identification: Notebook for PAN at CLEF 2013 C3 - CEUR Workshop Proceedings
No full textOur approach to the author identification task uses existing authorship attribution methods using local n-grams (LNG) and performs a weighted ensemble. This approach came in third for this year's competition, using a relatively simple scheme of weights by training set accuracy. LNG models create profiles, consisting of a list of character n-grams that best represent a particular author's writing. The use of a weighted ensemble improved upon the accuracy of the method without reducing the speed of the algorithm; the submitted solution was not only near the top of the leaderboard in terms of accuracy, but it was also one of the faster algorithms submitted
A Multi-Language Comparison of Influences on Author Verification using Character N-Grams
No full textWe create a new multi-language corpus for author verification based on Wikipedia talkpages, and evaluate the influence that differences in topic and time have on character n-gram author profiles. Topic alignment between two texts is found to increase author verification precision, and an authors writing style is found to change over time, but not more significantly after 3 years than after 1 year.Information ArchitectureWISElectrical Engineering, Mathematics and Computer Scienc
Recommended from our members
Identifying idiolect in forensic authorship attribution: an n-gram textbite approach
No full textForensic authorship attribution is concerned with identifying authors of disputed or anonymous documents, which are potentially evidential in legal cases, through the analysis of linguistic clues left behind by writers. The forensic linguist “approaches this problem of questioned authorship from the theoretical position that every native speaker has their own distinct and individual version of the language [. . . ], their own idiolect” (Coulthard, 2004: 31). However, given the diXculty in empirically substantiating a theory of idiolect, there is growing concern in the Veld that it remains too abstract to be of practical use (Kredens, 2002; Grant, 2010; Turell, 2010). Stylistic, corpus, and computational approaches to text, however, are able to identify repeated collocational patterns, or n-grams, two to six word chunks of language, similar to the popular notion of soundbites: small segments of no more than a few seconds of speech that journalists are able to recognise as having news value and which characterise the important moments of talk. The soundbite oUers an intriguing parallel for authorship attribution studies, with the following question arising: looking at any set of texts by any author, is it possible to identify ‘n-gram textbites’, small textual segments that characterise that author’s writing, providing DNA-like chunks of identifying material
Author identification for under-resourced language Kadazandusun
No full textThis paper presents the task of Author Identification for KadazanDusun language by using tweets as the source of data to perform Author Identification task of short text on KadazanDusun, which is considered as one the under-resourced language in Malaysia. The aim of this paper is to demonstrate Author Identification of short text on KadazanDusun. Besides, this paper also examines the performance of two machine learning algorithms on the KadazanDusun data set by analyzing the stylometric features. Stylometric features are used to quantify the writing styles of the authors which includes character n-grams and word n-grams. The workflow of Author Identification implements the machine learning approach to solve the single-labelled multi-class problem and predict the author of a given message in KadazanDusun. Two classifiers are used to compare the accuracy including Naïve Bayes and Support Vector Machine (SVM). The results show that the combination of n-grams which is word-level unigram and {1-5}-grams with character 3-grams are the most relevant stylometric features in identifying the author of KadazanDusun message with an accuracy of 80.17%. The results also show that SVM classifier has outperformed Naive Bayes in this Author Identification task with the accuracy of 80.17%
- …
