In this paper we will demonstrate the feasibility of using Auto Profiling online to analyse an informant’s linguistic data and his/her language distributions. Automatic profiling is an extension of the linguistic profiling approach that was originally carried out manually. This procedure was further developed into a computer-based procedure (Rapid Profile) that assists the analyst. Nevertheless, Rapid Profile is still essentially a manual observation-based procedure. Automatic profiling is the first fully automatic procedure for linguistic profiling. It accepts free-style written interlanguage input and automatically assigns a c-structure and aspects of the L2 morphology to the
interlanguage input. On this basis the system is capable of reliably assessing the stage of acquisition of the input sample. In addition, the system gives feedback to the specific errors contained in the input. It can also be used for automatically tagging L2 corpora. At the end of this paper, we will provide real data and their analysis to demonstrate that the algorithm of Auto Profiling is not only based on the application of Processability Theory to Specific L2s and on the logic of Rapid Profile but also can be used online to elicit and analyse an informant’s data in real time under time-constrained function.