Sensei FP7 Project » Case studies

SENSEI predicts Brexit Outcome

admin — Sun, 26 Jun 2016 22:32:37 +0000

Monitoring Brexit – The Story

In the month preceding the referendum date, SENSEI’s system monitored millions of social media conversations to predict the outcome of the referendum.
Every day, more than 300 000 posts across multilingual media sources on the topic of the UK EU Referendum are captured and automatically analysed by the SENSEI technology.
Most exit polls were showing confidence the REMAIN side would prevail. In contrast, the SENSEI system hit with very high accuracy the final outcome.

Monitoring BREXIT – What Happened

Press

Press Release (English)

Press Release (Italian)

Conversations in Social Media

admin — Thu, 28 Nov 2013 15:19:02 +0000

In a news publisher website such as The Guardian, The Observer or Le Monde, journalists publish articles on different topics from politics and civil rights to health, sports and celebrity news. The website design supports the publication and consumption of original news articles and at the same time facilitates user-involvement via reader comments. In this scenario there are a number of potential users: news readers and the originating journalist want to gain a structured overview of the mass of comments, both in terms of the sub-topics they address and their connection with the original article and in terms of the opinions (polarity and strength) the commenters hold about these topics; news readers who join a forum discussion need to be empowered so that they can respond to the originating article (or parts of it) and/or to a sub-set of earlier comments that may be relevant to their own personal view on the matter; editors or media analysts may need a more widely scoping analysis. At present none of these users can effectively exploit the current mass of comment data: what they need is new tools that help them make sense of this data deluge.

Conversations in Contact Centers

admin — Thu, 28 Nov 2013 15:18:42 +0000

In outsourced call centres, large corporations outsource their customer touch-point to a hosting call centre. The in-coming and out-going calls may be monitored in real time, or recorded for a later review. The monitoring is done by human evaluators for small random call samples (much less than 1%). Their job is to track indicators of call quality and efficiency of the agents’ job. The call centre’s corporate client may require reporting in different aggregated forms according to , e.g., the topic of the calls or in other words, what their customers are asking about or the emotional content of the call – concerned, frustrated etc. In the quality function, there are professional evaluators filling out forms which include behavioural and conversational indicators, such as politeness, listening attitudes, empathy, language use, ability to keep the interaction focused, etc.. . In the outbound marketing campaigns, the data collected by ad-hoc human evaluators are used for assessing the performance of the call centre agents, for identifying job training needs, and to provide recommendations the overall quality improvements in the course of interactions with customers. The services provided by the human analysts and evaluators are very expensive in some cases or not feasible in others because of the data deluge.