MUSCA is a research project aiming to create an innovative platform for brand monitoring and business intelligence. The platform integrates crawling, analytic and predictive capabilities, in order to address simultaneously the most important needs of those brands, considering their reputation an important asset.
Input data are crawled from major social networks, as well as web news feeds: a multi-channel extraction from diverse online sources. A further layer filters, classifies and tags the input information through Natural Language Processing techniques.
The social network analytics and predictive capabilities are the core distinctive features of MUSCA, compared to existing brand monitoring solutions. Advanced algorithms identify the roles of the people in the social network, providing insightful indication about key influencers. These metrics can weigh the sentiment scores of the users, providing a deep understanding of the web reputation of a brand: opinions of different people matter in accordance with their importance in the network, and our project aims to bring this basic principle back in the monitoring reports. A better modelling of the network structure provides a better insight, not only when a brand analyzes the situation as-is, but also when it struggles to forecast new trends.
A Business Intelligence layer matches historical sentiment data about a brand, with the trends of its real business drivers and KPIs, and compare the results with the performances of competitors. This approach attempts to deliver the return of investment of social media marketing initiatives in a quantitative manner.
Within this project the research partners adopts or develops innovative models and techniques of semantic analysis, graph theory and network dynamics, to build a new paradigm for brand monitoring. A dashboard embeds all the modules as above, and basic visualization tools. This offers also to participant beta-testers the opportunity to validate the architectural approach adopted, as well as its technical implementation.