Sentiment Analysis of tweets Pipeline (analyze_sentimentdl_use_twitter)

Description

A pre-trained pipeline to analyze sentiment in tweets and classify them into ‘positive’ and ‘negative’ classes using Universal Sentence Encoder embeddings

Live Demo Open in Colab Download

How to use

from sparknlp.pretrained import PretrainedPipeline 
pipeline = PretrainedPipeline("analyze_sentimentdl_use_twitter", lang = "en") 

result = pipeline.fullAnnotate(["im meeting up with one of my besties tonight! Cant wait!!  - GIRL TALK!!", "is upset that he can't update his Facebook by texting it... and might cry as a result  School today also. Blah!"])
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("analyze_sentimentdl_use_twitter", lang = "en")
val result = pipeline.fullAnnotate("im meeting up with one of my besties tonight! Cant wait!!  - GIRL TALK!!", "is upset that he can't update his Facebook by texting it... and might cry as a result  School today also. Blah!")
import nlu

text = ["""im meeting up with one of my besties tonight! Cant wait!!  - GIRL TALK!!", "is upset that he can't update his Facebook by texting it... and might cry as a result  School today also. Blah!"""]
sentiment_df = nlu.load('en.sentiment.twitter.use').predict(text)
sentiment_df

Results

|    | document                                                                                                         | sentiment   |
|---:|:---------------------------------------------------------------------------------------------------------------- |:------------|
|  0 | im meeting up with one of my besties tonight! Cant wait!!  - GIRL TALK!!                                         | positive    |
|  1 | is upset that he can't update his Facebook by texting it... and might cry as a result  School today also. Blah!  | negative    |

Model Information

Model Name: analyze_sentimentdl_use_twitter
Type: pipeline
Compatibility: Spark NLP 2.7.1+
Edition: Official
Language: en

Included Models

tfhub_use, sentimentdl_use_twitter