Entity mood analysis

Question

Entity mood analysis

I have been working on a sentiment analysis at the document level for 1 year. An analysis of moods at the document level provides an idea of the complete document. For example, the text “Nokia is good, but vodafone sucks a long time” will have a negative polarity associated with it, as it would be agnostic for Nokia and Vodafone entities. How could one get a sense of the level of essence, as positive for Nokia, but negative for Vodafone? Are there any research documents that provide a solution to such problems?

+5

nlp named-entity-recognition sentiment analysis

Jasneet Jun 21 '12 at 15:11

source share

4 answers

Pedram · Answer 1 · 2015-09-20T06:41:45+0000

You can try Level Mood Analysis . Good efforts are already being made to find opinions on aspects of the proposal. You can find some work here . You can also go further and deeper and look at those articles that are related to extraction (aspect) . What does it mean? Let me give you an example:

"The quality of the screen is great, but the battery life is short."

, . , ( ), / . , () ( " " "" " " ). , , , ( "" "" "" "" ). () ( , ), , .

, , .