Sentiment analysis
Sentiment analysis that delivers more than just positive or negative valuations with built-in sentiment scoring, topic identification and categorisation.

The purpose of this service would be to extract opinions from text. An opinion represents the topic an author is authoring and a sentiment score that classifies how positively or negatively the writer feels towards that subject. Deep Linguistic Analysis can be used to identify the subject the author is discussing. This is often:

? an entity (brand/ person/product/place?
? a thought (like ?global warming?, ?public policies? or ?financial meltdown?).


The sentiment analysis service may also break the opinion down to detect exactly which features or attributes or elements of the subject are increasingly being discussed. For a product this could be the main components or accessories as for example, the ?screen? in ?the screen of the Galaxy Tab? or the ?case? in ?my new iPad case?. For a person this could be the activities or attitudes connected with them. For a place maybe it's the specific buildings or institutions located there.

When combined with our categorisation service these features or attributes can be used to place the opinion in a category extracted from a taxonomy. This provides a robust way to structure a couple of texts in accordance with what topics folks are discussing and how they feel about those topics.

Sentiment scores are also predicated on Deep Linguistic Analysis. The more intense the feelings of the author about the subject, the bigger or lower the score. To achieve this, the analysis detects linguistic features including the strength of the vocabulary or the use of intensifiers like ?really?, ?very? or ?extremely?. So a comment like ?Installing software with this machine is painful!? will undoubtedly be scored as less negative than ?Installing software with this machine is actually very painful indeed!?

Deep Linguistic Analysis accurately handles complex issues like negation: ?the brand new Nikon is really not too bad?.

Talee Limited handles complex linguistic issues that play a major role in sentiment analysis, such as negation or comparative sentences. Deep Linguistic Analysis automatically handles this sort of phenomena capturing the difference between opinions like:


? ?This phone is much better than my old phone.? ? Positive
? ?This phone is not superior to my old phone.? ? Negative

The sentiment analysis service isn't limited to extracting an individual opinion per sentence. It actually detects as much opinions because the sentence contains. For instance in the sentence ?This phone is awesome, but it was way too expensive and the screen isn't big enough? three opinions will undoubtedly be extracted: ?phone? + ?awesome?, ?phone? + ?way too expensive? and ?screen? + ?not big enough?.