Cyberbullying Classifier Pipeline in Turkish texts

Description

This pre-trained pipeline Identifies whether a Turkish text contains cyberbullying or not.

Predicted Entities

Download Copy S3 URI

How to use


pipeline = PretrainedPipeline("classifierdl_berturk_cyberbullying_pipeline", "tr")

result = pipeline.fullAnnotate("""Gidişin olsun, dönüşün olmasın inşallah senin..""")

val pipeline = new PretrainedPipeline("classifierdl_berturk_cyberbulling_pipeline", "tr")

val result = pipeline.fullAnnotate("Gidişin olsun, dönüşün olmasın inşallah senin..")(0)

Results


["Negative"]

Model Information

Model Name: classifierdl_berturk_cyberbullying_pipeline
Type: pipeline
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Language: tr
Size: 454.6 MB

Included Models

  • DocumentAssembler
  • TokenizerModel
  • NormalizerModel
  • StopWordsCleaner
  • LemmatizerModel
  • BertEmbeddings
  • SentenceEmbeddings
  • ClassifierDLModel