Visible to the public Accurate Detection of Automatically Spun Content via Stylometric Analysis

TitleAccurate Detection of Automatically Spun Content via Stylometric Analysis
Publication TypeConference Paper
Year of Publication2017
AuthorsShahid, U., Farooqi, S., Ahmad, R., Shafiq, Z., Srinivasan, P., Zaffar, F.
Conference Name2017 IEEE International Conference on Data Mining (ICDM)
Date Publishednov
ISBN Number978-1-5386-3835-4
Keywordscontent spinning techniques, Dictionaries, feature extraction, Frequency measurement, Human Behavior, Metrics, Plagiarism, plagiarism detection, plagiarism detector evasion, pubcrawl, search engines, Software, spam, spammers, Spinning, spun content detection, spun documents, stylometric analysis, stylometric artifacts, stylometry, text analysis, text spinner dictionary, text spinning, text spinning software, unsolicited e-mail

Spammers use automated content spinning techniques to evade plagiarism detection by search engines. Text spinners help spammers in evading plagiarism detectors by automatically restructuring sentences and replacing words or phrases with their synonyms. Prior work on spun content detection relies on the knowledge about the dictionary used by the text spinning software. In this work, we propose an approach to detect spun content and its seed without needing the text spinner's dictionary. Our key idea is that text spinners introduce stylometric artifacts that can be leveraged for detecting spun documents. We implement and evaluate our proposed approach on a corpus of spun documents that are generated using a popular text spinning software. The results show that our approach can not only accurately detect whether a document is spun but also identify its source (or seed) document - all without needing the dictionary used by the text spinner.

Citation Keyshahid_accurate_2017