%0 Conference Paper %1 10.1007/978-3-031-01333-1_25 %A Stubbemann, Maximilian %A Stumme, Gerd %B Advances in Intelligent Data Analysis XX %C Cham %D 2022 %E Bouadi, Tassadit %E Fromont, Elisa %E Hüllermeier, Eyke %I Springer International Publishing %K 2022 homepage itegpub kdepub l3s myown regio %P 315--326 %T LG4AV: Combining Language Models and Graph Neural Networks for Author Verification %U https://link.springer.com/chapter/10.1007/978-3-031-01333-1_25 %X The verification of document authorships is important in various settings. Researchers are for example judged and compared by the amount and impact of their publications and public figures are confronted by their posts on social media. Therefore, it is important that authorship information in frequently used data sets is correct. The question whether a given document is written by a given author is commonly referred to as authorship verification (AV). While AV is a widely investigated problem in general, only few works consider settings where the documents are short and written in a rather uniform style. This makes most approaches impractical for bibliometric data. Here, authorships of scientific publications have to be verified, often with just abstracts and titles available. To this point, we present LG4AV which combines language models and graph neural networks for authorship verification. By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style is, at least to some extent, standardized. By the incorporation of a graph neural network structure, our model can benefit from relations between authors that are meaningful with respect to the verification process. %@ 978-3-031-01333-1

@inproceedings{10.1007/978-3-031-01333-1_25, abstract = {The verification of document authorships is important in various settings. Researchers are for example judged and compared by the amount and impact of their publications and public figures are confronted by their posts on social media. Therefore, it is important that authorship information in frequently used data sets is correct. The question whether a given document is written by a given author is commonly referred to as authorship verification (AV). While AV is a widely investigated problem in general, only few works consider settings where the documents are short and written in a rather uniform style. This makes most approaches impractical for bibliometric data. Here, authorships of scientific publications have to be verified, often with just abstracts and titles available. To this point, we present LG4AV which combines language models and graph neural networks for authorship verification. By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style is, at least to some extent, standardized. By the incorporation of a graph neural network structure, our model can benefit from relations between authors that are meaningful with respect to the verification process.}, added-at = {2023-12-12T12:42:39.000+0100}, address = {Cham}, author = {Stubbemann, Maximilian and Stumme, Gerd}, biburl = {https://www.bibsonomy.org/bibtex/2eb5cdf718b65cf848d9e9fc6d508c614/kde-alumni}, booktitle = {Advances in Intelligent Data Analysis XX}, editor = {Bouadi, Tassadit and Fromont, Elisa and H{\"u}llermeier, Eyke}, interhash = {83f4d81010a491963ffc5ee516b799e7}, intrahash = {eb5cdf718b65cf848d9e9fc6d508c614}, isbn = {978-3-031-01333-1}, keywords = {2022 homepage itegpub kdepub l3s myown regio}, pages = {315--326}, publisher = {Springer International Publishing}, timestamp = {2023-12-12T12:42:39.000+0100}, title = {LG4AV: Combining Language Models and Graph Neural Networks for Author Verification}, url = {https://link.springer.com/chapter/10.1007/978-3-031-01333-1_25}, year = 2022 }