Until the early 2000s, detection of infectious disease emergence (in animals and humans) relied on classical reporting of cases for known pathogens (called indicator-based surveillance [IBS]). Despite having standardized procedures for verification and confirmation of cases by field practitioners, laboratories and health officials, the IBS lacks sensitivity, mainly due to non-reporting and delayed reporting of cases. In a context of a continuously changing environment due to climate change, animal and human mobility, population growth and urbanization, there is an increased risk of emergence of new and exotic pathogens, which may pass undetected with the IBS. Hence, the need to detect signals of infectious disease emergence using informal sources (event-based surveillance [EBS]). The current EBS mainly relies on data from one type of source (e.g., electronic media, laboratory data or health records); thus, decision makers are confounded with the interpretation of data from multiple sources and systems. To overcome this, the project MOOD (MOnitoring Outbreak events for Disease surveillance in a data science context) aims to harness the state-of-the-art data mining and analytical techniques to big data originating from multiple sources to improve monitoring of the (re-)emergence of zoonotic infectious diseases in Europe, including antimicrobial resistance (AMR). Indeed, zoonotic diseases present the additional difficulty of needing a common framework to address the surveillance issues both in animals and humans. To this purpose, MOOD will establish a “one serves all” framework and visualisation platform that will allow real-time analysis and interpretation of epidemiological and gene sequence data in combination with climate, environmental and socio-economic covariates in an integrated and interdisciplinary “One health” approach. The MOOD framework will link research, national and international animal and public health organizations in Europe and beyond, to develop: 1) Data mining methods for collecting and combining heterogeneous and multi-source big data, 2) A network of disease experts to interpret the (possibly) weak signals and identify the drivers of infectious disease emergence, 3) Data analysis methods applied to Big data, including, but not limited to, spatial-temporal analysis, social network analysis, and fuzzy logic, to model infectious disease (re-)emergence and spread, 4) Ready-to-use online platform destined to a community of animal and public health users, including the public, tailored to their needs, and including capacity building and a network of disease experts to facilitate risk assessment of detected signals. The outcomes from MOOD will be designed in collaboration with national and regional European stakeholders, to assure their routine use during and beyond the project duration. These users will be implicated in the project to identify and adapt the project according to their needs. MOOD will complement and link to existing surveillance systems and other related projects or initiatives global and European level. The functionalities of MOOD will be tested and adapted through continuous assessment and evaluation using case studies on air-borne, vector-borne, water-borne and food-borne diseases, as well as AMR. Throughout the project, extensive consultations with potential users, studies into the barriers to open data sharing, dissemination and training activities, and studies on the cost-effectiveness of the project will support future sustainable user uptake.