Text Analytics
Welcome to the Text Analytics Forum
Categories
API – Any ideas or feedback pertaining to features or enhancements to Text Analytics API.
Documentation – Any ideas or suggestions for the API Reference or Documentation.
Language Support – Submit a request to have a particular language supported.
Samples & SDK Request – Let us know if you would like to see a Code sample or SDK provided.
Attention!
We have moved our Customer Feedback & Ideas for Azure Cognitive Services portal to the Azure Feedback Forum.
-
Text Analytics for Czech
Please add Czech language support, thank you in advance.
16 votes -
[Chinese]! Please support Chinese for Text Analytics
Chinese language have high market demand, please support.
7 votes -
Arabic sentiments still need some work
Arabic sentiment analysis still provides a 50% score on most sentiments. I was hoping to sell the idea to a local university, but Arabic will be a major part of the story.
3 votes -
please include spanish languague support
Please include Spanish language support for "topics detection", It will be very useful in CRM scenarios!
1 voteDone.
-
Please support Korean for Text Analytics
I hope that we can use Korean for Azure Text Analytics.It will be a really great point for Korean customer. We also hope Cotana for Korea. Thanks!
140 votes -
detecting Sarcasm
Doesn't get sarcasm. It thought "What a fantastic meal. Not." was positive. Fair enough I suppose!
1 voteMarking as “declined” as we won’t be focusing on this one over the next 6 months or so…
We can always look at these in the future… -
Sentiment Analysis does not support certain Portuguese characters
when submit JSON to Sentiment Analysis , with characters like " ç , õ ", é return error , i should be works
2 votes -
sentiment analysis - Hindi Language
Hope to see some support for Sentiment Analysis in Hindi language
3 votes -
我希望可以提供中文
I want write procedure code Taiwan chinese
can you help me? give me Reference direction?3 votes -
How similar are two text be?
I have two paragraphs (or stories which is longer content). Is there any way to analyze how similar are they which resulted in score? Suppose that score near 1 is more similar
1 vote -
4 votes
-
5 votes
Please checkout our new Text Analytics Containers!
-
6 votes
-
We need more details on the score from Sentiment analysis
The sentiment analysis score is descibed as "returns a numeric score between 0 and 1. Scores close to 1 indicate positive sentiment and scores close to 0 indicate negative sentiment. Sentiment score is generated using classification techniques. The input features of the classifier include n-grams, features generated from part-of-speech tags, and word embeddings."
We need more information about the scoring. The text "I'm sorry, but you could do so much better." returns 0.58 but it is very negative. What can we do to ensure that we can trust the results? Would it be useful to use longer pieces of text?
3 votes -
Russian language support for Text Analytics
Will be very nice if russian will be supported by platform
5 votesI am happy to announce that we shipped key-phrase extraction for Russian.
-
Support Topic detection for Turkish Language
It would be Nice to have Turkish Language support.
2 votesThanks for the feedback, please note that we recently released a sentiment analyzer for Turkish (in preview mode). Please try it out.
Thanks!
Luis Cabrera
Text Analytics Program Manager -
Support Topic detection for Greek Language
It would be Nice to have greek Language support.
2 votesTopic detection was deprecated before going to General Availability.
https://gallery.cortanaintelligence.com/Experiment/Topic-Detection has a Azure Machine Learning Studio experiment you could use to continue to support this scenario.
Since it is an experiment, you could modify it to meet your needs.
Thanks!
Luis Cabrera
Text Analytics PM -
Support Topic detection for Italian Language
It would be Nice to have Italian Language support.
3 votesThanks for the feedback.
We will be deprecated the topic detection capability altogether on August 24, in preparation for general availability — so marking this as declined.
-
Can you enable CORS for your text sentiment analytics?
Got my key and I'm calling "https://westus.api.cognitive.microsoft.com/text/analytics/v2.0/sentiment?"
to get some text analyzed, but CORS is not enabled on your end. Can you turn it on please?1 voteDone. :-)
-
Norwegian language support
It would be Nice to have Norwegian Language support. We are looking in to analyze text sent to Our support desk, which is mostly in Norwegian
12 votesJust want to mention that we have shipped Norwegian (Bokmal) support for key-phrases.
Also, key-phrases now supports these new languages: Danish and Russian.
- Don't see your idea?