Content generation is the quintessence of online social interaction and news updates.
A significant portion of the information transmitted via content generation is not only textual, but also visual (i.e. images and photographs).
We note that in 2011 the estimated number of images uploaded to Flickr per day were 4.5 million. Part of this generated content contains reference to a variety of brands, and other named entities, such as persons, companies, locations. Recent brand monitoring technologies rely mostly on the textual aspect of content to derive the underlying public sentiment with respect to a brand, essentially ignoring the wealth of – constantly increasing – visual content.
SentIMAGi will create a powerful brand monitoring and reputation management framework, exploiting multi-modal sentiment analysis methods and summarization. The aim of the framework is to provide an efficient but complete view of the public sentiment towards different aspects of a brand. We will break the text-only barrier by fusing the information conveyed via textual and visual content under a unified analysis methodology.
SentIMAGi will also apply summarization and text mining techniques to provide efficient yet complete reports through intuitive visualizations.
The SentIMAGi framework will allow the user to describe an information need. Then the system will gather related multi-modal content, analyze it and will visualize the results in an actionable manner, forming a useful decision support tool kit.