Sentiment Analytics – Still in its Infancy?

Sentiment analysis, though not a new kid on the block, is a quite interesting topic. Organizations apply this analysis on the gathered data [from different social media] to know what kind of sentiment their products are attracting in the market.  

Wikipedia says that a basic task in sentiment analysis is classifying the polarity of a given text at the document, sentence, or feature/aspect level — whether the expressed opinion in a document, a sentence or an entity feature/aspect is positive, negative, or neutral. Advanced, "beyond polarity" sentiment classification looks, for instance, at emotional states such as "angry," "sad," and "happy."   

Wikipedia [Definition]: Sentiment analysis (also known as ’opinion mining’) refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials. This analysis aims to determine the attitude of a speaker or a writer with respect to some topic or the overall contextual polarity of a document.  

The problem is that most sentiment analysis algorithms use simple terms to express sentiment about a product or service. However, cultural factors, linguistic nuances and differing contexts make it extremely difficult to turn a string of written text into a simple pro or con sentiment. The fact that humans often disagree on the sentiment of text illustrates how big a task it is for computers to get this right. The shorter the string of text, the harder it becomes.

There are four main categories of sentiment analysis: keyword spotting, lexical affinity, statistical method [machine learning], and concept-level techniques. Of these, currently, the keyword spotting and lexical affinity are more popular techniques.  Semantic analysis is highly recommended for social media sites. However, there are a few issues with this analysis:

• Without taking context [of a phrase/word] into consideration, you won’t get the analysis right.
• Analyzing complex sentences is still a far dream
• Since this analysis is domain centered, you cannot re-use one domain related phrases  with another  

In summary, though organizations are using sentiment analysis to gather the sentiment regarding their products, brands, etc., there is still lot much yet to develop  for delivering concrete results.

What is your take on this?