NLP in the SSIX project
October 10th 2017 12:40 - 13:00
Social Sentiment Indices powered by X-Scores (SSIX) aims to provide European SMEs with a collection of easy to interpret tools to analyse and understand social media users attitudes for any given subject; these sentiment characteristics can be exploited to help SMEs to operate more efficiently resulting in increased revenues. Social media data represents a collective barometer of thoughts and ideas touching every facet of society. SSIX will search and index conversations taking place on social network services, such as Twitter, StockTwits, and Facebook including the most reliable and authoritative Newswires, online newspapers, trade publications and blogs. SSIX will classify and score content using a framework of qualitative and quantitative parameters called X-Scores, regardless of language, locale or data architecture. The X-Scores framework will interpret economically significant sentiment signals in social media conversations producing sentiment metrics, such as momentum, awareness scope, topic density and historical comparison. These metrics will create commercially viable social sentiment indices, which can be tailored to any domain of interest. By enabling European SMEs to analyse and leverage social sentiment in their discipline, SSIX will facilitate the creation of innovative products and services by enhancing the investment decision making process, thus increasing revenue while also minimising risk. The focus of this talk will on the research and development surrounding the ongoing multilingual aspect orientated sentiment analysis from financial microblogs and the challenges encountered within the SSIX project, the various levels of linguistic analysis required to overcome these and solutions and resources provided by the project.