AI chatbots can take on many roles in our lives. James Muldoon's Love Machines looks into the relationships we're forging with them Artificial intelligence is now unavoidable - although there are those among us who try. Even if you don't seek out a chatbot, you will see new icons in your current apps to bring them within a single click: WhatsApp, Google Drive, even Microsoft Notepad, the simplest program imaginable. The tech industry is making an enormous and costly bet on AI, and, in turn, is forcing it on users to make good on this investment. Many are embracing it to take over writing, admin or planning, and a minority are going a step further and forming intimate relationships with it.

The sociology professor is suitably comfortable with AI helpers that he creates his own - it's their inventors' motives and unregulated environment he argues we should be concerned about I f much of the discussion of AI risk conjures doomsday scenarios of hyper-intelligent bots brandishing nuclear codes, perhaps we should be thinking closer to home. In his urgent, humane book, sociologist James Muldoon urges us to pay more attention to our deepening emotional entanglements with AI, and how profit-hungry tech companies might exploit them. A research associate at the Oxford Internet Institute who has previously written about the exploited workers whose labour makes AI possible, Muldoon now takes us into the uncanny terrain of human-AI relationships, meeting the people for whom chatbots aren't merely assistants, but friends, romantic partners, therapists, even avatars of the dead. To some, the idea of falling in love with an AI chatbot, or confiding your deepest secrets to one, might seem mystifying and more than a little creepy. But Muldoon refuses to belittle those seeking intimacy in "synthetic personas".

Process mining is a family of techniques that support the analysis of operational processes, in terms of key performance indicators, using event data Van Der Aalst (2012). Process mining can be used in number of ways, such as in identifying insights into current processes or in identifying actions or places within workflows where interventions should be made to improve performance. Although processing mining is typically used in the context of commercial business environments, there is crossover to other areas where processes play an important role, such as in water quality management processes administered by local government authorities or citizen science projects that use the Business Process Model and Notation (BPMN) Higgins, Williams, Leibovici, Simonis, Davis, Muldoon, van Genuchten, O'Hare and Wiemann (2016). In the case of water quality management, traditional event log data from information technology systems is often lacking in that many tasks, such as the manual sampling of water and the microbial culturing by biologists and laboratory technicians to identify faecal coliforms, are not performed using computers and are not logged. Nevertheless, it is likely that techniques developed to aid explainability and in the evaluation of machine learning algorithms in such cases will prove using in traditional process mining systems where similar problems must be addressed. This paper focuses on mining suitable features to perform inference for the level of bacteria, and specifically Enterococci and Escherichia coli (E.