English RoBertaForSequenceClassification Cased model (from KeithHorgan)

Description

Pretrained RoBertaForSequenceClassification model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. TweetClimateAnalysis is a English model originally trained by KeithHorgan.

Predicted Entities

Global warming is not happening - Sea level rise is exaggerated/not accelerating, Climate impacts/global warming is beneficial/not bad -Species/plants/reefs aren’t showing climate impacts/are benefiting from climate change, Global warming is not happening - Extreme weather isn’t increasing/has happened before/isn’t linked to climate change, Climate solutions won’t work - Climate policies areineffective/flawed, Climate solutions won’t work - People need energy (e.g. from fossil fuels/nuclear), No claim, Global warming is not happening - Climate hasn’t warmed/changed over the last (few) decade(s), Climate movement/science is unreliable - Climate movement is unreliable/alarmist/corrupt, Climate impacts/global warming is beneficial/not bad -Climate sensitivity is low/negative feedbacks reduce warming, Global warming is not happening - Ice/permafrost/snow cover isn’t melting, Global warming is not happening - Weather is cold/snowing, Climate solutions won’t work - Climate policies (mitigation or adaptation) are harmful, Human greenhouse gases are not causing climate change - It’s natural cycles/variation, Climate impacts/global warming is beneficial/not bad -CO2 is beneficial/not a pollutant, Climate solutions won’t work - Clean energy technology/biofuels won’t work, Global warming is not happening - We’re heading into an ice age/global cooling, Human greenhouse gases are not causing climate change - There’s no evidence for greenhouse effect/carbon dioxide driving climate change

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
    .setInputCol("text") \
    .setOutputCol("document")

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")

seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_tweetclimateanalysis","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("class")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, seq_classifier])

data = spark.createDataFrame([["PUT YOUR STRING HERE"]]).toDF("text")

result = pipeline.fit(data).transform(data)

val documentAssembler = new DocumentAssembler()
      .setInputCols(Array("text"))
      .setOutputCols(Array("document"))

val tokenizer = new Tokenizer()
    .setInputCols("document")
    .setOutputCol("token")

val seq_classifier = RoBertaForSequenceClassification.pretrained("roberta_classifier_tweetclimateanalysis","en")
    .setInputCols(Array("document", "token"))
    .setOutputCol("class")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, seq_classifier))

val data = Seq("PUT YOUR STRING HERE").toDS.toDF("text")

val result = pipeline.fit(data).transform(data)

import nlu
nlu.load("en.classify.roberta.tweet.by_keithhorgan").predict("""PUT YOUR STRING HERE""")

Model Information

References

References

• https://huggingface.co/KeithHorgan/TweetClimateAnalysis