Microsoft

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.


  • Hot ideas
  • Top ideas
  • New ideas
  • My feedback
  1. rectify service name

    In the "Analyze recorded inbound customer calls" section under Text Analytics API refers to "Text-to-Speech" rather than "Speech-to-Text".

    can you please validate and rectify?

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

    We’ll send you updates on this idea

    2 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  2. Add clarification of sentiment algorithm being absolute or relative

    I would suggest to add some clarification on how the sentiment analysis algorithm processes the data.

    For example, are the returned scores absolute meaning they are deterministic for the same backing model or are the scores relative to the other content/data in the given request. Meaning this particular document is more positive or negative than the other documents in the request.

    Likewise for sentences of the document.

    The reason this is important to me is that I'm running into the document limits (only allows 10) and wondering if I create a larger artificial document which is really combined data, then…

    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 →
  3. Fix your home page

    Put in 5000 characters (or a bit less) and see the 403 error (in console): https://azure.microsoft.com/en-gb/services/cognitive-services/text-analytics/#features

    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 →
  4. 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 →
  5. 1 vote
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  6. Service Accuracy

    It would be nice to have a page in the documentation that describe the API performance and accuracy.

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

    We’ll send you updates on this idea

    Under Review  ·  0 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  7. What is the definition of transaction in Text Analytics API

    After several calls to Text Analytics API, I noticed that the amount of transactions > the amount of calls. So how is transaction defined?

    2 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  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  8. 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
    Sign in
    (thinking…)
    Sign in with: Facebook Google
    Signed in as (Sign out)

    We’ll send you updates on this idea

    Started  ·  4 comments  ·  Documentation  ·  Flag idea as inappropriate…  ·  Admin →
  • Don't see your idea?

Feedback and Knowledge Base