cdipaolo / sentiment Goto Github PK

Just like python textblob library (but it's too slow and hard to embedded in go), using [-1, 1] float number to describe sentiment, -0.x means bad, +0.x means good, -1 means worst, 1 means best.

Thanks a lot!

Assuming that I have a new dataset in English, what are the steps to expand the knowledge of this library?

Hi,
I am trying to implement Russian language.

I've created train data in Russian and trained the model using .Train() (init.go) function previously added TrainRussianModel() line inside of it. Then I used go-bindata to generate a file and replaced bindata.go with it.
bindata.zip this is my version of the compiled model containing Russian language.

The problem is when I am trying to restore the model I am getting this error

panic: json: cannot unmarshal object into Go struct field NaiveBayes.tokenizer of type text.Tokenizer

in this code

models, err := sentiment.Restore()
if err != nil {
   panic(err)
}
result := models.SentimentAnalysis("Это отличный фильм!", sentiment.Russian)
mt.Println(result)

The model works if I train it and use it right away after training without trying to save it on the disk.

Could you provide example how to train the library for sentiment analysis in other languages?

Hello!
I have read the closed issue about Spanish language, and I think I go idea how to retrain the model, but I am a little not sure

• I should create my dataset/train folder with pos/neg and place the data there -- that clear
• Then I create my_en.go file which walks that dataset I just created

And then I am not sure what I should do to make it Train, and save trained data and use it for analyzes?

If possible please add a license, otherwise you are not legally allowed to use this code in other libraries

Why isn't neutral an option?