Authorship detection of SMS messages using unigrams

Abstract

Abstract-SMS messaging is a popular media of communication. Because of its popularity and privacy, it could be used for many illegal purposes. Additionally, since they are part of the day to day life, SMSes can be used as evidence for many legal disputes. Since a cellular phone might be accessible to people close to the owner, it is important to establish the fact that the sender of the message is indeed the owner of the phone. For this purpose, the straight forward solutions seem to be the use of popular stylometric methods. However, in comparison with the data used for stylometry in the literature, SMSes have unusual characteristics making it hard or impossible to apply these methods in a conventional way. Our target is to come up with a method of authorship detection of SMS messages that could still give a usable accuracy. We argue that, considering the methods of author attribution, the best method that could be applied to SMS messages is an n-gram method. To prove our point, we checked two different methods of distribution comparison with varying number of training and testing data. We specifically try to compare how well our algorithms work under less amount of testing data and large number of candidate authors (which we believe to be the real world scenario) against controlled tests with less number of authors and selected SMSes with large number of words. To counter the lack of information in an SMS message, we propose the method of stacking together few SMSes.

Surveying the Development of Authorship Identification of Text Messages

“…A large volume of literature is available on author identification for long documents and little literature exists on using author identification for short texts and focused upon different messaging systems. Most of the techniques used in this area have focused only on identifying users' stylometry in individual messaging systems [12,[16][17][18][19][20][21]. Some researchers in this field have focused only on using the relationship with the same user's stylometry linked to different messaging systems through a technique known as "linkability" [22]; for example, linking the user's stylometry based on a user profile.…”

“…Ragel et al [21] focused specifically on authorship detection of SMS to identify authorship using unigrams as features. They stated that the length of the SMS is limited to 140 characters.…”

Multilingual SMS-based author profiling: Data and methods

“…The researchers applied likelihood ratio for authorship analysis using N -gram approach (Ishihara 2011, 2014), vocabulary richness and lexical features (Ishihara 2012), and got the best result of their system in terms of log-likelihood-ratio cost that was 0.46. Ragel, Herath and Senanayake (2013) also utilized NUS SMS corpus for identifying the best experimental conditions for authorship detection/identification. For this purpose, they created a profile of each author treating it as a known author and at the same time creating a similar profile from testing data and treating it as unknown.…”

Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?

“…As a scientific endeavour it dates back at least to the 19th century [104,112], and was formulated as a computational task in the 1960s [118,163]. In contemporary work, the traditional focus on literary documents has largely been overshadowed by the increased use of online datasets, such as blog posts [121], e-mails [32,37], forum discussions [183], SMS messages [138], and tweets [25]. Neal et al [123] comprehensively survey the state-of-the-art in stylometry.…”