%0 Generic %1 halvani2017authorship %A Halvani, Oren %A Winter, Christian %A Graner, Lukas %D 2017 %K toread %T Authorship Verification based on Compression-Models %U http://arxiv.org/abs/1706.00516 %X Compression models represent an interesting approach for different classification tasks and have been used widely across many research fields. We adapt compression models to the field of authorship verification (AV), a branch of digital text forensics. The task in AV is to verify if a questioned document and a reference document of a known author are written by the same person. We propose an intrinsic AV method, which yields competitive results compared to a number of current state-of-the-art approaches, based on support vector machines or neural networks. However, in contrast to these approaches our method does not make use of machine learning algorithms, natural language processing techniques, feature engineering, hyperparameter optimization or external documents (a common strategy to transform AV from a one-class to a multi-class classification problem). Instead, the only three key components of our method are a compressing algorithm, a dissimilarity measure and a threshold, needed to accept or reject the authorship of the questioned document. Due to its compactness, our method performs very fast and can be reimplemented with minimal effort. In addition, the method can handle complicated AV cases where both, the questioned and the reference document, are not related to each other in terms of topic or genre. We evaluated our approach against publicly available datasets, which were used in three international AV competitions. Furthermore, we constructed our own corpora, where we evaluated our method against state-of-the-art approaches and achieved, in both cases, promising results.

@misc{halvani2017authorship, abstract = {Compression models represent an interesting approach for different classification tasks and have been used widely across many research fields. We adapt compression models to the field of authorship verification (AV), a branch of digital text forensics. The task in AV is to verify if a questioned document and a reference document of a known author are written by the same person. We propose an intrinsic AV method, which yields competitive results compared to a number of current state-of-the-art approaches, based on support vector machines or neural networks. However, in contrast to these approaches our method does not make use of machine learning algorithms, natural language processing techniques, feature engineering, hyperparameter optimization or external documents (a common strategy to transform AV from a one-class to a multi-class classification problem). Instead, the only three key components of our method are a compressing algorithm, a dissimilarity measure and a threshold, needed to accept or reject the authorship of the questioned document. Due to its compactness, our method performs very fast and can be reimplemented with minimal effort. In addition, the method can handle complicated AV cases where both, the questioned and the reference document, are not related to each other in terms of topic or genre. We evaluated our approach against publicly available datasets, which were used in three international AV competitions. Furthermore, we constructed our own corpora, where we evaluated our method against state-of-the-art approaches and achieved, in both cases, promising results.}, added-at = {2019-04-10T08:55:16.000+0200}, author = {Halvani, Oren and Winter, Christian and Graner, Lukas}, biburl = {https://www.bibsonomy.org/bibtex/2144eb334bc9a710ad400ef04dfe964cc/hotho}, description = {Authorship Verification based on Compression-Models}, interhash = {25e362ff24c0a46c4dedbda5e94b0a3d}, intrahash = {144eb334bc9a710ad400ef04dfe964cc}, keywords = {toread}, note = {cite arxiv:1706.00516}, timestamp = {2019-04-10T08:55:16.000+0200}, title = {Authorship Verification based on Compression-Models}, url = {http://arxiv.org/abs/1706.00516}, year = 2017 }