Sentiment Analysis is MeaningCloud's solution for performing a detailed multilingual sentiment analysis of texts from different sources.

It identifies the positive, negative, neutral polarity in any text, including comments in surveys and social media. It also extracts sentiment at the document or aspect-based level. In order to do this, the local polarity of the different sentences in the text is identified and the relationship between them evaluated, resulting in a global polarity value for the whole text.

Differentiators:

Documentation

Everything and anything you need to take advantage of this API's full potential.

Test Console

Choose an input and a configuration, and immediately check the results!

Developer Tools

Do you want to integrate this API into your environment? Check our Developer Tools!

Versions

Version Date Status
2.1 12/December/2018

2.1.16 (12/December/2018)

  • Minor bugs have been fixed, and resources have been updated.

2.1.15 (06/November/2018)

  • Minor bugs have been fixed, and resources have been updated.

2.1.14 (22/August/2018)

  • Improvements have been added to company detection heuristics.
  • Minor bugs have been fixed, and resources have been updated.

2.1.13 (28/June/2018)

  • Resources have been updated.

2.1.12 (31/May/2018)

  • Minor bugs have been fixed.
  • General sentiment models have been improved.
  • Lexical resources have been updated.

2.1.11 (12/April/2018)

  • Resources have been updated.

2.1.10 (03/April/2018)

  • Minor bugs related to the heuristic detection of entities have been fixed.

2.1.9 (18/January/2018)

  • Minor bugs have been fixed and resources have been updated.
  • Relevance calculations have been improved for concept and entity detection.

2.1.8 (13/November/2017)

  • Minor bugs have been fixed and resources have been updated.

2.1.7 (19/September/2017)

  • Minor bugs have been fixed and resources have been updated.

2.1.6 (26/June/2017)

  • Several minor bugs have been fixed and resources have been updated.

2.1.5 (27/March/2017)

  • New general model added: Portuguese.
  • General sentiment models have been improved.
  • Several minor bugs have been fixed and resources have been updated.

2.1.4 (27/October/2016)

  • Two new general models added: Italian and Catalan.
  • General sentiment models have been improved.
  • Bug in specific texts with parentheses has been fixed.
  • Several minor bugs have been fixed and resources have been updated.

2.1.3 (27/July/2016)

  • Several minor bugs have been fixed and resources have been updated.
  • General sentiment models have been improved.

2.1.2 (13/June/2016)

  • Several minor bugs have been fixed and resources have been updated.
  • General sentiment models have been improved.

2.1.1 (26/April/2016)

  • Several minor bugs have been fixed and resources have been updated.

2.1 (07/April/2016)

  • There have been several changes in the input parameters:
    • Instead of specifying the language of the text with the model parameter, now there are two parameters (lang and model) to convey this information.
    • The auto function of the model has been applied to the new lang parameter.
    • We've added support for URLs and files (url and doc parameters).
    • We've added the ilang parameter.
  • The API now allows you to use the sentiment models you define in the customization console.
2.0 07/July/2016

2.0.10 (07/July/2016)

  • Version retired.

2.0.9 (26/April/2016)

  • Several minor bugs have been fixed and resources have been updated.

2.0.8 (02/March/2016)

  • Several minor bugs have been fixed and resources have been updated.

2.0.7 (02/February/2016)

  • Several minor bugs have been fixed.
  • Both basic resources and sentiment resources have been updated.

2.0.6 (22/December/2015)

  • Several minor bugs have been fixed.
  • Both basic resources and sentiment resources have been updated.

2.0.5 (01/December/2015)

  • The tree view function has been integrated into the Lemmatization, PoS and Parsing API.
  • Both basic resources and sentiment resources have been updated.

2.0.4 (06/October/2015)

  • Several minor bugs have been fixed.
  • Both basic resources and sentiment resources have been updated.

2.0.3 (09/September/2015)

  • Basic and sentiment resources have been updated.
  • Small bugs have been fixed, including a bug related to the appearance of the field id in entities and concepts.
  • The field inherited_sentiment shows the entities and concepts affected by the sentiment in the sentence when tv=yes.
  • The behavior of negators has been improved.
  • Segments with no polarity are now shown.
  • Significant improvements have been added to URLs and HTML texts processing.

2.0.2 (28/July/2015)

  • Basic and sentiment resources have been updated.
  • Small bugs have been fixed.

2.0.1 (14/July/2015)

  • Sentiment resources have been updated.

2.0 (02/June/2015)

  • Sentiment analysis is shown at the sentence level before dividing it into segments giving more flexibility in the analysis.
  • More configuration options have been added regarding morphosyntactic analysis.
  • The internal architecture has been changed in order to greatly improve tenfold the response time of the service.
  • The sentiment rules accepted by the engine have been expanded, adding more definitions and new operators to gain expressivity and improve the overall results.
  • There are no longer numeric polarity values (that is, there is no score), polarity is given using score_tag.
  • The standard deviation value, sd, is now called agreement, and the numeric value no longer exists (sd_tag).
  • keywords are now called polarity_terms.
  • irony and subjectivity are now detected only at a global level.
  • A confidence value has been added to polarity scores to know how reliable the logic applied to the changes in the polarity are.
  • Concepts and entities have been standardized to be more coherent within the Sentiment Analysis response and with other APIs.
  • Offset values (inip and endp) have been added at different levels to ease integration and the possibility of visualization.
  • A new mode has been added, tv, that allows for the integration of the sentiment analysis with an output such as the one obtained in the Lemmatization, PoS and Parsing API.
1.2 09/September/2015

1.2.5 (09/September/2015)

  • Version retired.

1.2.5 (02/June/2015)

  • Python client has been improved.

1.2.4 (18/May/2015)

  • Several minor bugs have been fixed, and resources have been updated, including CASHTAG detection.

1.2.3 (06/April/2015)

  • Several minor bugs have been fixed, and resources have been updated.

1.2.2 (24/July/2014)

  • Several minor bugs have been fixed, and resources have been updated.
  • The loading time of resources has been optimized, improving the response time of the service has improved.

1.2.1 (17/June/2014)

  • Several minor bugs have been fixed, and resources have been updated.

1.2 (20/May/2014)

  • Entity/concept ID and type has been added to the output. Also, the form field has been unified so it's always called text (in previous versions, the form of concept/entity objects within a segment object were called entity/concept).
  • User dictionary parameter added.
  • Several bugs have been fixed in entity detection and resources have been updated.

Click on the version number to see the change log.

Languages

  • English
  • Spanish
  • French
  • Italian
  • Catalan
  • Portuguese

Integrations

Related Links

Contact us

Do you have any questions? Have you detected a bug? Contact us through our feedback section or at support@meaningcloud.com