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. Fix the requirement for documents to have periods

    For the documents I process, they frequently leave out periods from sentences.
    This results in a "key sentence" that is sometimes the entire document or most of the document, when submitted for processing to Azure.
    If there are periods it works great, otherwise fails.

    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. Sentiment is turned off in my apps

    I see that in my apps, the sentiment analysis has been turned off. Why is this? How can I turn it back on? There are no longer any switches.

    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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  3. Sentiment is turned off in my apps

    I see that in my apps, the sentiment analysis has been turned off. Why is this? How can I turn it back on? There are no longer any switches.

    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 →
  4. Can we extend text analytics API for general text classification, instead of just sentiment analysis?

    Can we extend text analytics API for general text classification, instead of just sentiment analysis?
    e.g. From customer chat information can we predict if the incoming request is an escalation of general inquiry
    OR
    news category classification - business news/ sports news/ politics etc.

    Thanks,
    Azured

    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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  5. 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 →
  6. 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?

    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 →
  7. 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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  8. 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 →
  9. 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 →
  10. 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 →
  11. 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 →
  12. Make "language" parameter optional for Sentiment Analysis

    Make "language" parameter optional or add another option as "auto" and add detected language to the response. So I won't need to make two seperate API calls one for detecting the language than for sentiment analysis.

    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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  13. Truncated input to first 100 tokens during analysis

    I got an error message from Text Analytics Sentiment
    "Truncated input to first 100 tokens during analysis".

    How fix it?

    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  ·  1 comment  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  14. Poor sentiment score for positive statement

    “It was great and he did help me.”
    Cognitive gives 18% which to me looks incorrect.

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

    We’ll send you updates on this idea

    Started  ·  2 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  15. Reporting a major bug in Azure cognitive-services/text-analytics

    I was using the text analysis service API by Azure & found many major flaws : (The API is not mature enough to handle simple real life sentences correctly).
    https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/?v=18.05
    Below are few sample sentences which I used & the result was absolutely wrong.


    1. I have many ways to not give you the expected grades

    2. There are many ways to not give you the desired grade

    3. How could you not understand what I said

    4. We have attempted to launch your course in a new window, but a popup blocker is preventing from opening it -> this should be neutral text.
    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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  16. Can I teach key-phase and sentiment ?

    There are many simple rule key-phases that expression feelings in Japanese.

    ex.
    にこにこ +(positive)
    じめじめ -(negative)
    などなど +- (neutral)

    I want to teach that's words cognitive engine.
    Can I teach key-phase and sentiment?

    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  ·  0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  17. Text analysis - Provide rewards and a way for users to provide feedback to service response so that it can learn(Machine Learning).

    While testing the sentences, it would be great to have users feedback whether the sentence and analysis makes sense or they feel the result has some issue.

    Get survey details such as emotion, positive and negative scale, keywords and all

    6 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  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  18. Sentiment Analysis Post via Spark

    Playing around with Sentiment Analysis but using Spark (pyspark actually). Have a Spark script that goes through a list of documents. As it goes through each document, it will post the contents into the Sentiment Analysis - one post at a time. Since this is running very quickly, I believe the posts can occur almost simultaneously.

    Attached is a file containing the print output of the Spark script.
    If you can see the sequence, the first post will show the response appropriate for it. However, as succeeding posts complete, the array grows - containing the first response up to the…

    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  ·  0 comments  ·  Sentiment Analysis  ·  Flag idea as inappropriate…  ·  Admin →
  • Don't see your idea?

Feedback and Knowledge Base