# News topic classifier

**URL:** <https://discuss.huggingface.co/t/news-topic-classifier/9065>\
**Category:** Intermediate\
**Created:** [August 8, 2021, 3:42pm UTC](https://discuss.huggingface.co/t/news-topic-classifier/9065 "2021-08-08T15:42:56Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Simpan](https://avatars.discourse-cdn.com/v4/letter/s/dfb087/32.png) [@Simpan](https://discuss.huggingface.co/u/Simpan)\
**Post date:** [August 8, 2021, 3:42pm UTC](https://discuss.huggingface.co/t/news-topic-classifier/9065/1 "2021-08-08T15:42:56Z")

</div>

Hi guys,

I’m building a multilingual news topic classifier. Any suggestions on what model might work best for this use case?

The input to the model would be a standard-length news article and a topic like “ethics in ai”.

I don’t have any training data yet so it would be nice to try a zero/few-shot classifier, at least as a first option.