fbpx

Facebook: Sentiment Measurement and social media


Facebook status updates tell us the emotional health of the nation and the Gross National Happiness of members. 300 million ? 400 million? of ’em.

We talk a lot about sentiment measurement in social media measurement classes. What constitutes a good sentiment, or bad. Does a computer understand sarcasm or vernacular “that car was da bomb” doesn’t mean it’s an old bomb, apparently. This is quite a different use of sentiment and Facebook:

Every day, millions of people share how they feel with the people who matter the most in their lives through status updates on Facebook. These updates are tiny windows into how people are doing. They’re brief, to the point and descriptive of what’s going on this week, today or right now. Grouped together, these updates are indicative of how we are collectively feeling. Measuring how well-off, happy or satisfied with life the citizens of a nation are is part of the Gross National Happiness movement. When people in their status updates use more positive words–or fewer negative words–then that day as a whole is counted as happier than usual. (To protect your privacy, no one at Facebook actually reads the status updates in the process of doing this research; instead, our computers do the word counting after all personally identifiable information has been removed.)

The graph contains several metrics. The first, GNH represents our measure of Gross National Happiness. The other two, Positivity and Negativity, represent the two components of GNH: The extent to which words used on that day were positive and negative. Gross National Happiness is the difference between the positivity and negativity scores, though they are interesting to view on their own.

You may notice that Positivity and Negativity are going down over time–that’s because as Facebook grows, there is more variability in the Facebook demographic and how people use status updates (using more or less emotional words). That’s why the GNH metric looks at the difference rather than the raw scores.

Facebook status update for State of the Nation emotions? This has huge implications for social psychology in the future.

Look at the holidays and which ones make a mark
Look at the holidays and which ones make a mark

Have a play with the graph on the FACEBOOK blog. You’ll see that happiness goes up on holidays – though St Patricks doesn’t do as well as others, probably because of alcohol related stuff – and negativity retreats.  It would be cool to do this graph again, for Australia, over Christmas. I might check back again then.

hat tip: AllFacebook

Laurel Papworth

Named by Forbes™ Magazine in the Top 50 Social Media Influencers globally, named Head of Industry, Social Media (Marketing Magazine™) and in the Power150 Media bloggers (AdAge™). CERT IV Training and Assessment certified trainer (Diplomas and Certificates etc) Adult Education. Laurel has manager Facebook Pages for Junior Masterchef, Idol, Big Brother etc. and have consulted on private online communities for banks Westpac, not for profits UNHCR & governments in SE Asia. Lecturer, social media, University of Sydney for 10 years and Laurel has 11,000 online students. Laurel Papworth personally connects to 6 million followers online and has taught around 100,000 people in the last 10 years how to be social media managers.

17 thoughts on “Facebook: Sentiment Measurement and social media

  1. Indeed an interesting graph. It would be interesting to overlay this with other data – perhaps:

    – Retail spending habbits to see if shopping indeed makes us happy or sad
    – Weather – to see if sunny days makes us happier
    – Sport – do gold medals at the olympics make the country happier?

    1. Whether Twitter is Fail Whaling or not, who’s been voted out on Idol, traffic jams… :p
      so many factors to happiness!

  2. This Facebook Graph is a very interesting concept. Since happiness is relative and sometimes has opposing sides, it would be interesting to see the graph results of major sporting events. There will be a group that is happy and a group that is unhappy.

Comments are closed.

Recent Content