What is exactly sentiment analysis?
Sentiment analysis is used to determine the emotional tone behind words to gain understanding of the attitudes, opinions and emotions expressed within an online mention. It is also known as opinion mining, deriving the opinion or attitude of a speaker. The aim is to discover whether a piece of writing is positive, negative or neutral. The attitude analysed may be a judgment or evaluation, affective state, or the intended emotional communication.
Sentiment analysis uses
This technology is used to collect and analyse opinions about product, service or even a brand. However, the main use of this technology is on social networks. It allows to gain an overview of the wider public opinion behind certain topics and emotional reaction to a document, interaction or event.
Nowadays, the applications of sentiment analysis are broad and powerful. The ability to extract insights from social data is a practice that is being widely adopted by organisations across the world. Indeed, the ability to quickly understand consumer attitudes and react accordingly is something that businesses take advantage of. These businesses listening to that feedback and adjusting accordingly are being proactive and are current winning companies.
As an example, the Obama administration used sentiment analysis to gauge public opinion to campaign messages and policy announcements ahead of 2012 presidential election.
Sentiment Analysis is not perfect
It’s important not to forget that sentiment analysis is not a perfect science at all. It can’t understand perfectly the complexities of human language. Recognizing context and tone is a difficult process for a machine. Humans are fairly intuitive when it comes to interpreting the tone of a piece of writing, but it’s much harder to teach a machine how to do that. For now, sentiment analysis is still rather incompetent in measuring things like sarcasm, scepticism, hope, anxiety, excitement, etc. The fact is that human’s expression doesn’t fit into just three buckets: not all sentiment can be categorised as simply as positive, negative or neutral.
As an example, the following sentence is a hard one for a machine to analyze: “My train has been delayed. Brilliant!”. Most humans would be able to quickly interpret that the person was being sarcastic and to categorize the sentence as negative. But without contextual understanding, a machine looking at this sentence might see the word “brilliant” and categorize it as positive.
To further complicate the task of machines, with the use of social media, language is evolving: 140 character limits, the need to be succinct, etc. This brings with it many challenges.
What about the future of sentiment analysis?
For now, the technology is still relatively new so it’s hard to speculate about its evolvement in the future. But one thing that we know is that sentiment analysis needs to move beyond a one-dimensional positive to negative scale because there are other kinds of sentiment that cannot be placed on a simple barometer. What we will need is a multidimensional scale to truly understand and capture the broad range of emotions that humans express. Moreover, the focus will be on how to make results interpretable and actionable.