Detecting Emotions in Social-Media Streams

Recently my research and development work within the EMOTIVE project - looking at fine-grained, cross-cultural emotion detection from Twitter datasets - has received considerable national and international mass-media attention. Despite its' relatively low budget the project was an overall success; achieving the highest currently known performance on test-datasets in the world (in terms of F-Measure) and processing tweets at a speed of 1500-2000 tweets per second (on an avg. dual-core processor). The system that was developed detects a range of 8 "Basic Emotions", anger, disgust, fear, happiness, sadness, surprise, and shame and confusion, rather than a variation on the less informative positive / negative sentiment score.

The ontology employed gives a rich linguistic context to the eight emotions through its ability to analyse both ordinary speech and slang. This ability to monitor how the public mood changes over time is particularly useful when assessing what interventions are most successful in dealing with civil unrest or concern. However, potential analysis of tweets with the developed system can range from marketing to personality profiling through computational models which are based on emotions.

To me the project was particularly interesting mainly as it allowed me to further focus on my interests that I had throughout my PhD and also to further delve into very interesting social-media questions, NLP related issues in sparse texts processing (i.e. 140 characters per message vs. traditional NLP on large documents) and Ontology processing applications.

The work has resulted in several conference papers (and at least one Journal paper is on the way, with more in the pipeline). Currently we are continuing work within another EPSRC & DSTL funded project and are in collaboration with several organisations to further explore applications of our fine-grained emotions detection system.

Social Media Monitoring

WARNING: This article is critical of the Loughborough University Enterprise Office (an initiative to help commercials ideas & work from academia into viable business oportunities).

Well over a year ago (back in 2009, actually the idea came in 2008) I entertained myself with the idea of starting up a social media monitoring business. I have worked on the topic within my PhD and I have published on the topic and also did some decent work with a student of mine back through 2008/2009 academic year. Our results were great, winning me an IEEE best PhD student paper award at a conference among some encouraging feedback from my paper reviewers.

The idea was to use my student's existing server infrastructure (he runs a web hosting service in Poland) to accumulate web 2.0 datasets and apply data-mining and statistical techniques summarisation, and finally to build a nice and fancy User Interface based on edgy web-design techniques (which I lectured about to my large Introduction to Web Programming undergraduate class last year) and further wrap it all up into ontologies to be usable by semantic web capable agents!

The above sounded like a decent Business Plan to me, with relatively low risk, as I could have done this part time (aligned with the PhD) and we could have just used, as mentioned, my students server infrastructure to a degree. See this article for a very timely overview of Social Media Monitoring tools, and how significant they have become in business (There is much more academic work, looking at many case studies - drop me a line if you want some references to those).

We therefore decided to seek some initial funding or at least support from Loughborough's student enterprise office, in one form or another and depending on their response we wanted to begin development of the initial prototypes! After a few email exchanges and several phone conversations, I was very dissapointed...

The ent. office consultant was obviously overworked, and complained about her high volume of meetings, business trips and other responsibilities. Once I mentioned that we have published and received an award, her reaction shocked me. Apparently since the work was published we could not patent it, and hence without any possibilities of patenting she lost any interest. I was shocked by this reaction, assuming that patents still rule the world of software is something I consider quite ridiculous (just like the once click amazon buy button patent), in my opinion a barrier to innovation that's what my whole experience dealing with the entr. office at loughborough felt like.

It is ironic that reading the BBC article today, I realise that with a little bit support we could have had a finished beta product by today, covering local demand in social media monitoring in the Midlands area. Great way to throw logs under the feet of young university talent, Loughborough Student Enterprise Office, well done ;-)!

Any comments are welcome, at same time, I do know the Office was behind a few interesting projects, however they have a lot of improvement ahead to become worthy for a university of Loughboroughs Profile!