# Use ES for contextual chatbot

**URL:** <https://discuss.elastic.co/t/use-es-for-contextual-chatbot/86664>\
**Category:** Elasticsearch\
**Created:** [May 22, 2017, 12:25pm UTC](https://discuss.elastic.co/t/use-es-for-contextual-chatbot/86664 "2017-05-22T12:25:54Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Karma](https://avatars.discourse-cdn.com/v4/letter/k/bcef8e/32.png) [@Karma](https://discuss.elastic.co/u/Karma)\
**Post date:** [May 22, 2017, 12:25pm UTC](https://discuss.elastic.co/t/use-es-for-contextual-chatbot/86664/1 "2017-05-22T12:25:54Z")

</div>

Is it practical to use ES tf-idf nature to predict user intent based on user query (text classification)?

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [May 25, 2017, 10:08am UTC](https://discuss.elastic.co/t/use-es-for-contextual-chatbot/86664/2 "2017-05-25T10:08:54Z")

</div>

You may be able to do it with a "more like this" query or a suggester I guess, or even graph, but it's not really anything ES was built for. Interesting use case though!

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [June 22, 2017, 10:09am UTC](https://discuss.elastic.co/t/use-es-for-contextual-chatbot/86664/3 "2017-06-22T10:09:03Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.