MoodViews, what about Studying Blogger's Mood
This is a very interesting study created by a group of researchers from Information and Language Processing Systems
Informatics Institute, University of Amsterdam. The study focus on mood used by bloggers collected mainly from LiveJournal where about 80% of the posts indeed have a mood attached to them.
MoodViews is a collection of tools for tracking the stream of mood-annotated text made available by LiveJournal. At present, MoodViews consists of three components, each offering a different view of global mood levels, the aggregate across all postings of the various moods:
* Moodgrapher tracks the global mood levels,
* Moodteller predicts them, and
* Moodsignals helps in understanding the underlying reasons for mood changes.
The graph below for example is a comparative of happy and sad mood over the last 10 days. It's amazing to see that there is peaks over the happy graph while the sad mood is keeping almost the same average. This could be interesting to study the effect of some events on the blogosphere according the evolution of their mood.
I loved the idea of the Moodsignals and how it works. Since MoodViews tracks and analyzes mood annotations used by bloggers in their writings. Moodsignals looks at unusual peaks in the levels of mood annotations. It identifies peaks, and then tries to explain the peaks found by analyzing the language used by bloggers. In looking for explanations, Moodsignals searches news archives.
The graph below show for example a detected peak around the "loved" mood, detected between 02/13/2006 14h - 02/16/2006 06h and explained by the keywords "valentin, day, love, rose, happi, card, flower, chocol, chu, gift, heart, mulder, dinner" which refere mainly to the Valentine's Day.
A very interesting study, I bet there will be more useful usage if the mood will be adopted by more bloggers, personaly I rarely put my mood anywhere if I have one ! So this will depend on adoption of this by bloggers and also how it could be used, for example to monitor the evolution of the blogosphere, which event have a higher influence, and what is this influence since with the mood you can know if someone is happy, sad, angry or whatever.
