Social Media offer a vast amount of geo-located and time-stamped textual content directly generated by people. This information can be analysed to obtain insights about the general state of a large population of users and to address scientific questions from a diversity of disciplines. In this work, we estimate temporal patterns of mood variation through the use of emotionally loaded words contained in Twitter messages, possibly reflecting underlying circadian and seasonal rhythms in the mood of the users. We present a method for computing mood scores from text using affective word taxonomies, and apply it to millions of tweets collected in the United Kingdom during the seasons of summer and winter. Our analysis results in the detection of strong and statistically significant circadian patterns for all the investigated mood types. Seasonal variation does not seem to register any important divergence in the signals, but a periodic oscillation within a 24-hour period is identified for each mood type. The main common characteristic for all emotions is their mid-morning peak, however their mood score patterns differ in the evenings.
In our latest paper ("Effects of the Recession on Public Mood in the UK", presented in MSND/SMANE at WWW'12), among other interesting results which are derived by performing mood analysis on Twitter content geolocated in the UK, we show that a steady increase in Anger and Fear was observed in the weeks predecing the UK riots (August, 2011).
Those two emotions have been steadily increasing after the announcement of budget cuts in October, 2010. The only "calming" period observed in the inferred mood time series occurred in early May, possibly due to the Royal Wedding.
One of These Days my dear Friends
This is Mood of the Nation, a website implementing our methodology for exploiting Twitter content to monitor Mood and Affect norms in the United Kingdom's population. It displays the scores for four mood categories (namely Joy, Sadness, Anger and Fear) in a comparable manner. The mood scores are updated automatically on a daily basis and are available for several UK regions (North, South England etc.).