Twitter is often used by people to vent their frustration about something (or someone), make their opinions heard and generally comment on the day to day happenings of their life. The fact that we have to condense these thoughts into 140 characters means we get our mood across in the most concise way we can. An interesting new study suggests that it is possible for our tweets to be studied and analysed to detect how the country as a whole is feeling.Can social media tell what mood we’re in?
The study was conducted by academics at Bristol University. It focused on measuring the mood and changes, using standard tools for mood detection, of a large sample of the UK population. A collection of 484 million tweets generated by more than 9.8 million users from the UK were analysed between July 2009 and January 2012, a period marked by economic downturn and some social tensions.
The researchers found that a significant increase in negative mood indicators coincided with the announcement of the cuts, and also to public spending by the government, and that this effect is still lasting. They also noted a negative downturn during the summer riots of 2011, with many people showing their disgust and anger at the rioters online.
You have to wonder if there were some more jubilant Tweets coming from a small minority during this time…
Nello Cristianini, Professor of Artificial Intelligence said:
Social media allows for the easy gathering of large amounts of data generated by the public while communicating with each other.“While we leave the interpretation of our findings to social and political scientists, we observed how the period preceding the royal wedding seems to be marked by a lowered incidence of anger and fear, which starts rising soon after that. Of course, other events also happened in early May 2011, so they may also be responsible for that increase.
The aim of the study was to see if the effects of social events happening across the country would be seen in the contents of Twitter. They have made an entertaining animated graphic of their data here – www.mediapatterns.enm.bris.ac.uk/mood/
The Bristol University site says:
While this approach is standard in many applications, the researchers felt that a sanity check in the domain of mood detection via Twitter was necessary. By making use of lists of words that are correlated with the sentiments of joy, fear, anger and sadness, they observed that periodic events such as Christmas, Valentine’s Day and Halloween evoke the same response in the population, year after year.
It is important to remark that the real-time detection of social trends via the analysis of social media content, presents various possible limitations. Social media analysis can only be accomplished with text mining technologies, which are less accurate than human assessment, but can be applied to vast amounts of data. Also the population that is assessed is necessarily that of Twitter users, which is a biased subsample of the general population. Particular care needs to be paid when extracting information but also when reporting it.