Why does the sentiment analysis classified a negative text as positive?

AmosGH

I run some sentiment analysis but it gave me wrong analysis in the sense that a text that supposes to be negative was classified as positive. What accounts for this misinterpretation and what can be done to rectify it. Again how does the sentiment analysis from Aylien classified a text to be negative, positive and neutral?

lionelderkrikor

Hi @AmosGH

I don't know what are the algorithm(s) behind Aylien. Aylien is a 3th part extension, I think that, if you want more information about how this extension works, you will need to contact Aylien directly.
For your problem, have you tried other methods like : 

1. In RapidMiner : 
 - Extract Sentiment operator from the Toolbox extension (to install from the MarketPlace)
2. Python libraries : 
 - TextBlob
 - NLTK (Natural Language ToolKit)

Hope this helps,

Reagrds,

Lionel

Telcontar120

Also note that Aylien no longer supports their RapidMiner extension.  That won't answer the question as to why their text is misclassified, but it may mean you have a hard time getting help with it.  You should probably try one of the options that Lionel mentions or one of the other 3rd party text analysis extensions such as Rosette or MonkeyLearn.