In recent years, improvements in automated data acquisition techniques have been carried out in order to sample, characterize and quantify phytoplankton communities during oceanographic campaigns or in the frame of monitoring networks (at low or high frequency). However, these acquisition and digitization techniques, including those concerning «imaging-in-flow» and «flow cytometry» systems, still generate an important quantity of data which cannot be processed manually. Indeed, a full manual quantification of the particles based on a simple visual inspection can be time-consuming, tedious and consequently lead to erroneous or missing identifications. For this purpose, different dedicated R-packages were and are still being developed to allow greater automation in data analysis and classification while permitting a limited user-interaction during the process. The common methodology consists in combining few expert knowledge and some “machine learning” algorithms at different levels: to classify particles into different groups based on the definition of a specific training set, but also to partially validate the “most suspect” predictions which can represent a consequent fraction of the global error. Moreover, in order to orientate the automated classification and consequently to reduce the global error rate, some interactive tools were developed to adapt the training set to the phytoplankton communities generally encountered in the studied area (“active learning”), or to constraint the algorithms to merge or separate some groups (“constrained clustering”). These different semi-automated analytical tools were applied on different in vivo image and signal datasets acquired with the FlowCAM and CytoSense devices respectively, during several cruises in the English Channel, in order to evaluate their operational ability to automatically monitor the diversity of samples. Spatial distributions of the target groups, based on their abundance, were computed and could allow to highlight different sub-regions in the English Channel during the studied periods.