{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/domain-specific-author-attribution-based-on","title":"Domain Specific Author Attribution Based on Feedforward Neural Network Language Models","arxiv_id":"1602.07393","date":"2016-02-24","proceeding":null,"authors":["Zhenhao Ge","Yufang Sun"],"abstract":"Authorship attribution refers to the task of automatically determining the\nauthor based on a given sample of text. It is a problem with a long history and\nhas a wide range of application. Building author profiles using language models\nis one of the most successful methods to automate this task. New language\nmodeling methods based on neural networks alleviate the curse of dimensionality\nand usually outperform conventional N-gram methods. However, there have not\nbeen much research applying them to authorship attribution. In this paper, we\npresent a novel setup of a Neural Network Language Model (NNLM) and apply it to\na database of text samples from different authors. We investigate how the NNLM\nperforms on a task with moderate author set size and relatively limited\ntraining and test data, and how the topics of the text samples affect the\naccuracy. NNLM achieves nearly 2.5% reduction in perplexity, a measurement of\nfitness of a trained language model to the test data. Given 5 random test\nsentences, it also increases the author classification accuracy by 3.43% on\naverage, compared with the N-gram methods using SRILM tools. An open source\nimplementation of our methodology is freely available at\nhttps://github.com/zge/authorship-attribution/.","url_abs":"http://arxiv.org/abs/1602.07393v1","url_pdf":"http://arxiv.org/pdf/1602.07393v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"domain-specific-author-attribution-based-on","repo_url":"https://github.com/zge/authorship-attribution","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"author-attribution","task_name":"Author Attribution"},{"task_slug":"authorship-attribution","task_name":"Authorship Attribution"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}