Bipartite networks have vertices that can be divided into two disjoint sets (layers) and they have been recognized to provide particularly insightful portraits of many different systems, including: trade (products and country), location analysis (users, visited locations), mutualistic systems (plant and pollinator), citations (subject and authors), and many others. We will propose a theoretical framework to quantify the structural modification on the network during the time, defining a new class of null model with general applicability. As case of study we will analysed the binary export matrix of the World Trade Web, obtained by imposing the Revealed Comparative Advantage (RCA) on the country-product trade volumes matrix. Our analysis shows that the global structure of trade has deeply changed during the years following the 2007 worldwide crisis. Since 2003, the WTW becomes increasingly compatible with the picture of a network where correlations between countries and products were progressively lost. Moreover, we can use our framework to statistically validate the links between the countries and products based on node similarity (a.k.a. countries with similar exported products). The community detection on the country layers reveals modules of similarlyindustrialized nations, meanwhile on the products layer allows communities characterized by an increasing level of products complexity to be detected. This new theoretical framework not only assess the evolution of the topological structure of the WTW but is it able to highlight the temporal policy changes of the exports within the countries. Other applications range between: systems risk in portfolios’ management and similarity in recommendation networks.