Microsoft

Text Analytics API

Welcome to the Text Analytics API 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.

  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. Wrong Results Some Times

    im using this for clients comments in a hotel, i notice that a some times is not so accured, a comment like "Tienen un excelente servicio" that in inglish is "you have an excelent service" just got a 0.17 = 17% of satisfaction, but when i use the same text in the public test API in this link https://azure.microsoft.com/es-es/services/cognitive-services/text-analytics/

    it get a 85% of satisfaction, im using this in a flow but it's suppose to be the same.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  2. How we can calculate sentiment for large documens? (more than 5120 characters)

    We are trying to analyze a large document (more than 5120 characters). We don't know how to calculate the overall sentiment score of the entire document.
    Let imagine we have a document with 5200 characters. So we can split it into two chunks( first with 5120 characters and the second is 80 characters) and the overall score calculates as an average of two documents. But this approach is not right because the second smaller document with 80 characters can dramatically affect the result.
    What are your suggestions?
    How we should split and calculate the overall score?

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  3. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Key Phrase Extraction  ·  Flag idea as inappropriate…  ·  Admin →
  4. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  5. Why input is required strictly in JSON format?

    Any thoughts why this isn't simplified for the most common use cases? I have txt/docx/pdf/image file as input and all the complexities or converting to structured format should be abstracted away from user. Isn't this a very common use case that you have several unstructured or different types of files present in blob containers, let the API crawls through it and present its results. Similar to what Azure Search does? Also, why don't you unify these services, meaning the text analytics in Azure ML recognizes only 3 NER types, whereas Azure cognitive services recognizes more. Shouldn't this all be internally…

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Entity Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  6. Armenian incorrectly detected as English

    Armenian (not currently supported for detection) is being labeled as English with a confidence of 1.

    Examples:

    For input text: 'Տուն'
    The detected language is 'en'. Confidence is: 1.

    For input text: 'Անձնական Տվյալների Ցուցակ'
    The detected language is 'en'. Confidence is: 1.

    For input text: 'Ժողովրդագրություն'
    The detected language is 'en'. Confidence is: 1.

    For input text: 'Օժանդակ'
    The detected language is 'en'. Confidence is: 1.

    For input text: 'Կապի անհատներ'
    The detected language is 'en'. Confidence is: 1.

    For input text: 'Տվյալների Հաստատում'
    The detected language is 'en'. Confidence is: 1.

    Many many more examples. Meanwhile, other popular…

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Language Detection  ·  Flag idea as inappropriate…  ·  Admin →
  7. Francisco Franco is not the spanish "jefe del estado" anymore

    If you enter "Clamor empresarial en presencia del jefe del Estado para poner fin cuanto antes a la violencia en Cataluña" in the test page, Text Analytics returns Francisco Franco!!! as "jefe del Estado".
    This guy died in 1975.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Entity Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  8. Support Arabic Jordan Country Language

    Can you support Arabic language for Jordan country.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  9. Ability to call these API's from Analysis Services (SSAS)

    We use tabular model as our semantic layer and hence can't call these API's from Power BI. Is there a way we can call these API's from tabular model ? Our immediate need is for Key Phrases. It's really a pain to do this manually as we are importing the data into Power BI, which is not a scalable solution.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  API  ·  Flag idea as inappropriate…  ·  Admin →
  10. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Entity Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  11. Issue on Decoding UTF-16

    Hello, I'm running your original tutorial sample on Azure Notebook, but here there is one error regarding UTF-16 decoding saying truncation happened.

    How to solve this?
    Thanks.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  12. Support for Danish

    Please add support for Danish. We need to analyze text string to help the kids in special situations.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Completed  ·  1 comment  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  13. The introduction 'not' completely confuses the sentiment analysis and is really unusable in real life.

    Example - "I didn't have a bad trip to Seattle. I enjoyed seeing the Space Needle!" returns 9% sentiment! Not really usable.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Resolved  ·  1 comment  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  14. Wrong sentiment returned

    I tried the following two message and got negative sentiment.
    "The market has been going up lately."
    "The global economy is still growing."

    They should clearly be positive.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    1 comment  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  15. Does the key phrase functionality allow words to be singularised from a plural or changed from past tense to present tense in an automated

    Currently, when using the key phrase extraction to count where IT issues are logged, phrases like "Service" and "Services", "Project" and "Projects", "Business" and "Businesses", etc all show up as separate phrases. However, we would like these plural phrases to be listed and counted as singular phrases so the single & plural instances of the phrase are all grouped & counted together. Is this something that would be possible?
    (similarly, being able to recognise and group togethre a past tense word into the present tense - i.e. "Pay" & "Paid" - would be a useful feature.

    2 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Key Phrase Extraction  ·  Flag idea as inappropriate…  ·  Admin →
  16. Swedish

    I find that the Sentiment Analysis in Swedish is just generally very low quality and bad. Return 0.8 for very negative text.

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  17. Please add German for Cognetive Services!

    We need German for Image-Klassifikation!

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Language Support  ·  Flag idea as inappropriate…  ·  Admin →
  18. detect more sentiments

    detect more sentiments specific like : anger, happiness, sadness, fear, surprise, disgust

    1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  19. Adding custom Named Entity Recognition to Text Analytics

    We need the ability to add custom entities to Text Analytics NER (Named Entity Recognition) than what is supported. For example: I want to add a skill or a quality measure to the text posted by a user.

    3 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    0 comments  ·  Entity Recognition  ·  Flag idea as inappropriate…  ·  Admin →
  20. Language detection for random text returns "English" with a score of 1.0 instead of "unknown"

    According to the documentation at https://westus.dev.cognitive.microsoft.com/docs/services/TextAnalytics.V2.0/operations/56f30ceeeda5650db055a3c7
    submitting random text like ":) :( :D" should return a result of "(Unknown)" with a score of 0, instead it returns "English" with a score of 1.

    This is pretty bad.

    0 votes
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  1 comment  ·  Language Detection  ·  Flag idea as inappropriate…  ·  Admin →
← Previous 1 3 4 5
  • Don't see your idea?

Feedback and Knowledge Base