Twitter tool shows a real-time view of our emotions

By May 19th, 2014

Researchers from CSIRO have unveiled a new online tool developed for the Black Dog Institute, in partnership with Amazon Web Services, called ‘We Feel’ which analyses the words from millions of tweets to display a real-time view of our emotions.

The tool will help researchers understand how our emotions fluctuate over time due to changes in social, economic and environmental factors such as weather, time of day, news of a natural disaster or announcements about the economy.

We Feel will help Black Dog Institute’s researchers who are world leaders in the diagnosis; treatment and prevention of mood disorders such as depression, verify whether the large and fast sample of information coming from Twitter can accurately map our emotions. It is hoped the tool could help to understand how our collective mood changes, help monitor community mental health and predict where services needed to be assigned.

“We Feel looks for up to 600 specific words in a stream of around 27 million tweets per day and maps them to a hierarchy of emotions which includes love, joy, surprise, anger, sadness and fear,” Research Leader in language and social computing at CSIRO’s Digital Productivity and Services Flagship Dr Cecile Paris said.

“The power of this information cannot be underestimated.”

Professor Helen Christensen, Executive Director, Black Dog Institute

“You can explore emotional trends on a minute by minute time scale, across locations around the globe and gender to further refine the results.”

Professor Helen Christensen, Executive Director of the Black Dog Institute said the We Feel program represented the world’s first foray into understanding how social media can be used to detect poor mental health and observe shifts according to time and place.

“The power of this information cannot be underestimated,” Professor Christensen said.

“Currently, mental health researchers and associated public health programs use population data that can be over five years old.

“Should the real-time data gained using this incredible tool prove accurate, we will have the unique opportunity to monitor the emotional state of people across different geographical areas and ultimately predict when and where potentially life-saving services are required.”

The tool has already picked up a spike in the public’s emotional response to last week’s Budget and will continue to collect data that will be analysed by Black Dog’s researchers.

“To help us cope with the enormous volume of tweets coming down the pipe, up to 32,000 per minute, we’ve leveraged Amazon Web Services’ Kinesis platform, a fully managed big data service for real-time processing of streaming big data at massive scale. Without this we wouldn’t have been able to process the tweets in real time,” Dr Paris said.

Teresa Carlson, Vice President, Worldwide Public Sector at Amazon Web Services said the Kinesis platform offed users the flexibility to collect, store, analyse and share data en masse, efficiently.

“We’re very pleased to be part of this amazing project; Amazon Kinesis-enabled applications can power real-time dashboards, generate alerts and drive real-time business decisions,” Ms Carlson said.

Media resources

Click image for high resolution version.

More images available via Dropbox