Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Authorship attribution using co-occurrence networks

Authors: Pires, David Laranjo;

Authorship attribution using co-occurrence networks

Abstract

Atribuição de Autoria utlizando Redes de Co-Ocorrencia Nesta tese é abordada a tarefa de Atribuição de Autoria como uma tarefa de classificação. As metodologias utilizadas representam textos em grafos. Destes, várias medidas são extraídas, sendo utilizadas como amostras para o classificador. Já existem alguns trabalhos que também se focam nesta metodologia. Esta tese foca-se num método que divide o texto em várias partes e trata cada uma como um grafo. Deste, são extraídas as medidas, que são tratadas como uma série temporal, da qual são extraídos momentos. Assim, os momentos compõem o vetor final, representativo de todo o texto. A partir da metodologia aqui descrita surgem mais duas variações. A primeira variação omite o passo das séries temporais, e, por consequência, as várias medidas de cada grafo são utilizadas diretamente como amostras. A segunda variação representa todo o texto como um só grafo. As metodologias são testadas com corpus em Inglês e Português, com número variado de textos; Abstract: Authorship Attribution using Co-Occurrence Networks This thesis approaches the task of Authorship Attribution as a classification task. This is done using methodologies that represent text documents in graphs, from which several measures are extracted, to be used as samples for the classifier. There have been some works that also focus on this methodology. This thesis focuses on a methodology which splits the texts in multiple parts and treats each as a separate graph, from which measures are extracted. Each graph’s measures are treated as a time-series and moments are extracted. These moments make the final vector, representative of the entire text. This methodology is explored and extended with 2 variations. The first variation skips the time-series step, resulting in the various measures from each graph being used directly as samples. The second variation models the entire text as one graph. The methodologies are tested in corpus in both English and Portuguese, with varying number of texts.

Country
Portugal
Related Organizations
Keywords

Authorship Attribution, Redes de co-ocorrencia, Atribuição de Autoria, Classificação, Classification, Processamento de Lingua Natural, Graphs, Co-Occurrence Networks, Grafos, Natural Language Processing

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!