The abundance of online media content requires highly scalable architectures to allow cross-media monitoring targeted to specific needs of marketers. We will present an innovative big data-as-a-service platform for analysing large complex networks in order to enhance cross-media monitoring.
In contrast to existing systems, our platform provides marketers with several distinctive features: First, while most of the systems perform quantitative exploratory analysis of social media, our platform applies graph analytics in order to reveal social interaction types, hidden patterns in the cross-media network and the information diffusion over time. The graph animation gives marketers a better understanding about the formation of communities, propagation of the content, etc.
Second, the creation of cross-media graphs is triggered by user-defined queries that can be easily specified by marketers. Thus, end-users can build and analyse different graphs according to specific goals of the analysis.
Third, the platform allows reducing Hadoop cluster usage costs due to executing big data analytics operations on demand triggered by user-defined queries. Instead of running costly streaming processes that continuously listen for new queries, we implemented Spark-as-a-service via Apache Livy REST interface. It allows running batch Spark jobs on demand.
Finally our platform integrates distributed versions of graph analytics algorithms (Louvain, HITS and other algorithms) that can scale to a large volume of data.
During our presentation we will showcase how you can harness all these features of the platform in order to dig into details of complex cross-media networks.
Liana Napalkova holds the PhD degree in engineering science from the Riga Technical University (Latvia). Liana worked as a Visiting Research Assistant Professor in the Department of Electrical and Computer Engineering at the University of Arizona (U.S.).
She is currently a senior data scientist and big data developer at Eurecat technology center. Moreover, Liana is an Adjunct Professor at the Autonomous University of Barcelona. Her professional interests include the design and development of intelligent decision support systems, using big data technological stack, optimisation and machine learning techniques.
Juan Carlos Castro holds an MBA from IESE Business School and Bsc in Computer Engineering from the UAB. During his more than 15 years of professional experience in the Digital sector and in public-private environments, he has played different management roles in Capgemini, Hewlett-Packard, Grifols and i2CAT. In the eHealth-related domain, he has been principal entity investigator of finished projects Help4Mood (FP7-ICT-2009, http://help4mood.info ), Fearless (AAL-Call 3, http://www.aal-europe.eu/projects/fearless/ ) and Life 2.0 (CIP-PSP-2010, https://cordis.europa.eu/project/rcn/191746_en.html), with special focus in the research area of User Centered Design to deliver technology solutions that solve patient needs. He is currently responsible for digital product development at the Eurecat technology center, identifying new market opportunities in the fields of Digital Health, Marketing, Retail and Tourism, through the application of Big Data, IoT, Artificial Intelligence and advanced analysis technologies Social Networks.
Data Council, PO Box 2087, Wilson, WY 83014, USA - Phone: +1 (415) 800-4938 - Email: community (at) datacouncil.ai