The likelihood ratio framework is an ideal way for an expert witness to present their evidence in court because it reflects their duty of expressing the strength of evidence in favour of a certain hypothesis (Morrison, 2009). Recent research by Ishihara (2021) demonstrates how this approach can be applied to authorship identification. In this talk I will describe the application of this framework to a real-life authorship identification case involving text messages. The method adopted is a special type of the General Impostors method, the state-of-the-art method for authorship verification problems (Koppel and Winter, 2014). The drawback of this method as applied in computer science is that it is dependent on dynamic feature sets, such as character 4-grams. These features are difficult to interpret and sensitive to topic and register variation. Instead, I will show how a manually curated static feature set, similar to a writeprint (Abbasi and Chen, 2008), can lead to equally excellent performance while limiting the capturing of confounding information. I will conclude by arguing that the move to the likelihood ratio framework for forensic authorship identification is not a goal in the distant future but a reality that should be adopted now. References Abbasi, A. and Chen, H. (2008) Writeprints : A stylometric approach to identity-level identification and similarity detection in cyberspace, In ACM Transactions on Information Systems, New York, NY, USA. Ishihara, S. (2021) Score-based likelihood ratios for linguistic text evidence with a bag-of-words model, Forensic Science International, Elsevier, 327, p. 110980. Koppel, M. and Winter, Y. (2014) Determining if two documents are written by the same author, Journal of the Association for Information Science and Technology, 65(1), pp. 178–187. Morrison, G. S. (2009) Forensic voice comparison and the paradigm shift, Science and Justice, 49(4), pp. 298–308.