Personal and Ubiquitous Computing https://doi.org/10.1007/s00779-019-01323-z ORIGINAL ARTICLE An IoT data analytics approach for cultural heritage Francesco Piccialli 1 · Paolo Benedusi 2 · Luca Carratore 3 · Giovanni Colecchia 4 Received: 1 June 2019 / Accepted: 11 September 2019 © Springer-Verlag London Ltd., part of Springer Nature 2020 Abstract The ability to integrate, manage, and analyze large amounts of data extracted from different sources is becoming a key asset for businesses, organizations, and research institutions that deal with the cultural heritage domain. Nowadays, it is well known that modern technologies and the massive use of mobile devices can contribute to generate an enormous flow of data, whose collection, analysis, and interpretation allows for real-time analysis related to the behaviors, preferences, and opinions of users. In this paper, we present and discuss a data analytics approach relying on an Internet of Things framework. The main goal is to assess how the collection of behavioral IoT data coming from the cultural heritage domain can be opportunely exploited by means of data science and data analytics techniques in order to produce useful insights. Experimental results performed in a real case study demonstrate how the cultural heritage domain, and the related stakeholders, can benefit from these kind of applications. Keywords Cultural heritage · Data analytics · Data science · Internet of Things 1 Introduction In the cultural heritage (CH) domain, the nature of museum visits lends itself to the categorization of patterns and behaviors that visitors perform while traversing such space. The study of museum visitors dates back to the early part of the twentieth century [1]. These studies can lead to a better understanding of visitors needs and to provide  Francesco Piccialli francesco.piccialli@unina.it Paolo Benedusi paolo.benedusi@databooz.com Luca Carratore luca.carratore@gmail.com Giovanni Colecchia giovanni.colecchia@unina.it 1 Department of Electrical Engineering and Information Technology, University of Naples Federico II, Naples, Italy 2 Databooz Italia s.r.l., Naples, Italy 3 Department of Mathematics and Applications “Renato Caccioppoli”, University of Naples Federico II, Naples, Italy 4 Centro Servizi Metrologici e Tecnologici Avanzati (CeSMA), University of Naples Federico II, Naples, Italy customized services. Museum visitors also represent a particular class of users, presenting multiple challenges for effective behavior monitoring and modeling: this is becoming more and more important for both traditional museums and for technologically aided/augmented versions of them. In spite of the widespread availability of any kind of fixed and mobile devices, a recent survey on international experiences of museums observatories [2] revealed that systematic data collection is almost exclusively based on ticketing and questionnaires. These entail many limitations, including small size of samples, reluctance of some people to answering, difficulties in ensuring proper randomization, time and cost of interviews, and low frequency of global investigations and analyses (i.e., 2 times per year) [2]. Indeed, such questionnaires include information which can be gathered or inferred, in great part, using technological devices: favorite hours and length of the visit, activities performed during the visit, preferred information channels used, types of materials, and information contents which were read or listened. For this purpose, non-invasive systems can exploit devices by tracking the presence and the movements of visitors without any form of pre-registration or explicit provisioning of devices for identification and interaction. As an alternative, interactive systems can offer multiple types of sensory experiences and services to the end-users, relying on mobile devices which also can monitor and save information on user positions, actions, and timings. Each kind of system has its own specific merits