- Emotive software maps ‘moods’ of tweets in geographical area
- Tweets analysed by eight different emotions
- Plans to expand system to create personality profiles based on language used by individuals
- Twitter a major organisation and coordination aid to London 2011 rioters
The Emotive software can process up to 2,000 tweets a second and boil each one down to eight basic emotions: anger, disgust, fear, happiness, surprise, sadness, shame and confusion.
Designers said it could be used on a mass scale to evaluate crowd emotions, alert police to potential criminals or public safety threats, and even guide national policy on dealing with major incidents.
They said it could be used to create a geographical map of the national mood.
While it currently focuses on the UK, it could be expanded to monitor the 10,000 tweets that are sent out every second worldwide from Twitter’s hundreds of millions of users.
Academics said they were also exploring ways of creating personality profiles from the language individuals used on Twitter and similar social streams.
Together with Facebook and BlackBerry Messenger, Twitter has proved a useful aid to rioters, such as those involved in the violent attacks that swept England – and particularly London – in the summer of 2011.
Twitter already groups and flags up ‘trends’ on the site – topics that many users are tweeting about at a given time.
Professor Tom Jackson, who led the team from Loughborough University who developed the programme, said: ‘Following the murder of soldier Lee Rigby in Woolwich there was an outpouring of sadness and disgust through Twitter.
Emotions: Twitter was a major organisational aid for people involved in riots in London in August 2011
‘Across the country people expressed their emotions at this unprovoked attack, with some using the incident to incite racial hatred against Muslims.
‘Two days after his murder his family appealed for calm, stating that their son would not have wanted his name to be used as an excuse to carry out attacks against others.
‘This appeal had an almost immediate effect, leading to an outpour of positive sentiment.’
He said that public postings through social media give an accurate real-time record of how and what people are feeling.
‘Twitter is a very concise platform through which users express how they feel about a particular event, be that a criminal act, a new government policy or even a change in the weather,’ he said.
‘Through the computer program we have created we can collate these expressions of feelings in real time, map them geographically and track how they develop.’
Dr Ann O’Brien, who was part of the research team that created the structural model used by Emotive, said: ‘The ontology (structural model) we created takes the eight emotions and gives them a rich linguistic context so that we can chart the strength of emotions expressed in ordinary language and also in slang. For any incident we can view how reactions grow and diminish over time.’
Mass mood: The Emotive software is said to provide a geographical map of social network users’ emotions
The team has already secured further funding that will enable researchers to develop another prototype system that can automatically detect events, analyse emotions and extract more summary details from social media.
The Emotive project was funded by the Engineering and Physical Sciences Research Council and the Defence Science and Technology Laboratory.