An event is defined as “a particular thing which happens at a specific time and place” and can be extracted from news articles, social networks, forums, as well as any digital documents associated with metadata describing temporal and geographical information. In practice, this knowledge is a digital representation (virtual world) of various phenomena that occur in our physical world. The manual analysis of large event collections is not feasible, thereby motivating the development of intelligent data analytic tools to automate the knowledge extraction process. In this paper we present a computational tool called Websensors Analytics that uses machine learning methods for learning sensors from events to monitor and understand various phenomena in the real world. Websensors Analytics is the first initiative to analyze events in Portuguese and currently contains all the necessary features for extracting and analyzing knowledge from events: (i) web crawling to collect events in real time, (ii) statistical and natural language preprocessing techniques for event extraction (iii) machine learning methods for learning sensors, and (iv) Application Programming Interface (API) using the Websensors Analytics infrastructure. The Websensors Analytics tool is potentially useful for media analytics, opinion mining, web engineering, content filtering and recommendation systems – for both academic research and industrial applications.