Forensic Authorship Analysis of Microblogging Texts Using N-Grams and Stylometric Features
This work addresses the challenge of authorship attribution in microblogging texts for criminal investigations, but it is incremental as it applies existing stylometric features to a new small dataset.
The paper tackled the problem of identifying authors of short tweet messages (limited to 280 characters) for forensic analysis, achieving classification accuracies between 92% and 98.5% using a dataset of 40 users with 120-200 tweets each.
In recent years, messages and text posted on the Internet are used in criminal investigations. Unfortunately, the authorship of many of them remains unknown. In some channels, the problem of establishing authorship may be even harder, since the length of digital texts is limited to a certain number of characters. In this work, we aim at identifying authors of tweet messages, which are limited to 280 characters. We evaluate popular features employed traditionally in authorship attribution which capture properties of the writing style at different levels. We use for our experiments a self-captured database of 40 users, with 120 to 200 tweets per user. Results using this small set are promising, with the different features providing a classification accuracy between 92% and 98.5%. These results are competitive in comparison to existing studies which employ short texts such as tweets or SMS.