• Computer Science
  • Published in ArXiv 2019

KnowBias: A Novel AI Method to Detect Polarity in Online Content

@article{Saligrama2019KnowBiasAN,
  title={KnowBias: A Novel AI Method to Detect Polarity in Online Content},
  author={Aditya Saligrama},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.00724}
}
We introduce KnowBias, a system for detecting the degree of political bias in textual content such as social media posts and news articles. In the space of scalable text classification, a common problem is domain mismatch, where easily accessible training data (i.e., tweets) does not correspond in format to the desired testing domain (i.e., longer form article content). While universal text encoders such as word or sentence embeddings could be leveraged to train target agnostic classifiers… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 20 REFERENCES

Knowbias, Mar 2019

  • Aditya Saligrama
  • 2019
VIEW 1 EXCERPT

This is what filter bubbles actually look like, Aug 2018

  • John Kelly, Camille François
  • 2018
VIEW 1 EXCERPT

Universal Sentence Encoder

VIEW 3 EXCERPTS

The importance of neutral class in sentiment analysis

  • Vasilis Vryniotis
  • 2013
VIEW 1 EXCERPT