Bring your best ideas to the AI Use Case Contest! Enter to win 40 hours of expert engineering support and bring your vision to life using the powerful combination of Alteryx + AI. Learn more now, or go straight to the submission form.
Start Free Trial

General Discussions

Discuss any topics that are not product-specific here.

Sentiment Analysis

Azadeh
5 - Atom

Hello All,

 

I have these sentences "i have no problem with any thing l ask l get as the comment saying no worries thanks" or  "i have not really had any problems with ... over the years. and i have no reason to not give a good mark." When I used the sentiment analysis, the sentiment category is negative. Is there any way to get positive for these two sentences?

 

Thanks a lot for your help! 

3 REPLIES 3
PhilippK
Alteryx Alumni (Retired)

Hi @Azadeh ,

 

are you referring to the "Sentiment Analysis" tool of the Text Mining Category?

screenshot.png

 

This tool is working with the VADER algorithm:

https://community.alteryx.com/t5/Data-Science/Try-Sentiment-Analysis-with-Designer-You-Must/ba-p/589...

 

For your mentioned example, there are better alternatives to VADER.

 

I recommend that you use a Python tool and leverage another existing Python library instead.

I am not an expert, but Feature- based or Embedding-based methods could perform better for your case:
https://towardsdatascience.com/fine-grained-sentiment-analysis-in-python-part-1-2697bb111ed4

 

I hope this gives you a good starting point.

 

Best regards

Phil

 

Azadeh
5 - Atom

Hi Phil,

 

Thanks a lot for response. Yes I did want to use the Sentiment Analysis tool of the Text Mining Category. I'll have a look at your reference  🙂

PhilippK
Alteryx Alumni (Retired)

Hi @Azadeh ,

did you had a look at the references?

I am interested in how you are going to solve your special sentiment analysis use case 🙂

 

Thank you and best regards

Phil

Labels
Top Solution Authors