Auto Sentiment Analysis Infographic

I have created this infographic to help summarise my experiences with auto sentiment analysis programs. I have used a few over the years and while they are getting better, they are far from perfect, and indeed are sometimes described as being no better than tossing a coin!

One peculiarity that I have noticed is that the sentiment engines which have undergone some form of sector-specific 'training' often seem to be more accurate.

For example I was checking some social media coverage on cigarettes and it was notable how poor the sentiment scoring was. Often the same tweet got re-tweeted with a different sentiment score. Then a week or so later I was looking at coverage on mobile phones and it was amazing how much more accurate the sentiment scoring was. Whereas in the first example I has changing possibly every other item, with the mobile phone sector it was more like one in every four items.

"Morally toxic and destructive"

I used the Brandwatch system to put together this word cloud from today's coverage on Goldman Sachs. Not surprisingly it is dominated by the resignation letter on one of their derivatives directors Greg Smith. It might just be sour-grapes or possibly a window in on a genuinely dis-functional organisation. 


I think most will be pretty horrified by this portrayal of life at this truly globally significant organisation. Could it make any difference? I Doubt it. They probably ‘know’ enough and are perceived to have saved enough money for their 

clients to guarantee their survival. Personally I was disturbed by the notion that society has allowed these qualities to be somehow valued above almost all others.