The overall goals of the SENSEI project are twofold. First, SENSEI will develop summarization/analytics technology to help users make sense of human conversation streams from diverse media channels. Second, SENSEI will design and evaluate its summarization technology in ecological environments, aiming to improve task performance and productivity of end-users.Conversational interaction is the most natural and persistent paradigm for business relations with end-customers or users. In contact centres millions of customer spoken conversations are handled daily. On social media platforms hundreds of millions of blog posts are delivered through generalist or proprietary platforms. In both cases, conversations have little impact on the intended target "listeners" due to the volume, velocity and diversity (media, style, social context) of the document streams (spoken conversations and blog posts). Most language analytics technology is limited in that it performs keyword search, which does not provide automatic descriptions of what happened, who said what, which opinions are held on what subject, in a coherent, readable and executable form. In the SENSEI project we plan to go beyond keyword search and sentence based analysis of conversations. We will design and adapt lightweight and large coverage linguistic models of semantic and discourse resources to learn a layered model of conversations. SENSEI will address the issue of multidimensional textual, spoken and metadata descriptors in terms of semantic, para-semantic and discourse structures. The combination of supervised and unsupervised learning techniques will support the scaling and adaptation of such computational models to the diversity of the conversation data. Automated generation of readable analytics documents (summaries) will support end-users in the context of large data analysis tasks. Summarization technology developed in SENSEI will be evaluated with respect to user's productivity in the context of ecological scenarios, specifically, call centre and social media conversation analysis.