Category Archives: Sentiment Analysis

Posts about Sentiment Analysis

MeaningCloud sentiment analysis powers SocialBro’s Twitter platform

The leading social marketing tool vendor applies MeaningCloud’s advanced sentiment analysis to detect the opinion of Twitter users with the highest quality and without having to develop language processing technology.

UPDATE: as of March 2016 SocialBro has been rebranded as Audiense.

SocialBro analyzes over 15 million tweets per month to extract insights that are essential for its clients’ marketing activities and campaigns. And a key ingredient of these insights is the analysis of Twitter users’ sentiment.SocialBro logo

Due to the characteristics of its business, SocialBro had some very demanding requirements in the field of sentiment analysis: a high throughput, great accuracy and the possibility of carrying out aspect-based analyses. Instead of developing its own sentiment analysis technology, SocialBro decided to turn to a specialized supplier to avoid undertaking developments outside its core business. With this aim, they chose MeaningCloud.

MeaningCloud’s Sentiment Analysis API service stands out for its semantic approaches based on advanced natural language processing. It internally employs a syntactic-semantic tree representation of the text on which it deploys the polarity of the different terms. Then, it combines and spreads these polarities according to the morphological category of each term and the syntactic relations among them.

Continue reading


An Introduction to Sentiment Analysis (Opinion Mining)

In the last decade, sentiment analysis (SA), also known as opinion mining, has attracted an increasing interest. It is a hard challenge for language technologies, and achieving good results is much more difficult than some people think. The task of automatically classifying a text written in a natural language into a positive or negative feeling, opinion or subjectivity (Pang and Lee, 2008), is sometimes so complicated that even different human annotators disagree on the classification to be assigned to a given text. Personal interpretation by an individual is different from others, and this is also affected by cultural factors and each person’s experience. And the shorter the text, and the worse written, the more difficult the task becomes, as in the case of messages on social networks like Twitter or Facebook.

Continue reading


Feature-level sentiment analysis

Back when we were called Textalytics, we published a tutorial that showed how to carry out feature-level sentiment analysis for a specific domain: comic book reviews.

Cover for Marvel's Black Widow #1

Marvel’s Black Widow #1

Since then, besides changing our name, we have improved our Sentiment Analysis API and how to customize the different analyses through our customization engine. In this post we are going to show you how to do a feature-level sentiment analysis using MeaningCloud.

One of the main changes in the latest release of our API is the possibility of using custom dictionaries in the detailed sentiment analysis provided by the Sentiment Analysis API. We are going to use comic book reviews to illustrate how to work, but the same process applies to any other fields where sentiment comes into play, such as hotel reviews, Foursquare tips, Facebook status updates or tweets about a specific event.

Continue reading


See you at the Sentiment Analysis Symposium 2015 in New York

Next July 15-16, New York will host a new edition of the Sentiment Analysis Symposium. This event is your opportunity to keep up with technologies and solutions that help you discover business value in opinions, emotions, and attitudes in social media, news, and enterprise feedback, to further your business goals.

This year, the program has two tracks: a Presentation Track featuring a mix of business and technical presentations and panels and a Workshop Track with longer-form content. See the agenda here.

Sentiment Analysis Symposium 2015
At MeaningCloud,  over the past year we’ve seen an explosion of interest in sentiment analysis from very diverse industries and the Sentiment Analysis Symposium is the premier event to learn about the latest developments in this and related areas, such as social listening and voice of customer analytics. This is the reason why we are sponsoring the Symposium again in 2015.

We’re thrilled to present and collaborate with other leaders in the industry at this year’s event in New York. Our main presentation will be titled: “From Strangers to Acquaintances: Multidimensional Customer Profiling” and will describe how businesses aim to integrate multichannel interactions (social conversations, web behavior, contact center activity) and other data for profiling and segmenting their users in real time. In this context, a winning approach is to combine dimensions like demographics, lifestyle, brand affinity, or intent to better understand your audience and to generate business opportunities.

For more information and registering, please visit the Symposium’s website. And if you want to save 20% in your registration, contact us at news@meaningcloud.com.

Meet us in New York City, at the Sentiment Analysis Symposium, and follow @SentimentSymp.


Sentiment Analysis 2.0: Migration guide

We have released a new version of one of our more popular APIs: Sentiment Analysis. In Sentiment Analysis 2.0:

  • The rules used for defining polarity terms have been greatly improved, adding new operators and making the models used much more flexible, which in turn leads to better results.
  • Sentiment analysis is now done at more levels, allowing to identify more complex syntactic structures and to obtain more detailed information about how the polarity is expressed.
  • More configuration options have been added related to the morphosyntactic analysis over which the sentiment analysis is carried out.
  • The architecture of the service has changed, leading to a tenfold improvement in the response time.
  • An integration with the Lemmatization, PoS and Parsing API has been added in order to ease the way of creating applications that use the information provided by both APIs.
  • Dictionary customization has been fully integrated in order to get out the most out of its functionality.

All these improvements mean the migration process is not as fast as it would be with a minor version. These are the things you need to know to migrate your applications from Sentiment Analysis 1.2 to Sentiment Analysis 2.0.
Continue reading


The Role of Text Mining in the Insurance Industry

What can insurance companies do to exploit all their unstructured information?

A typical big data scenario

Insurance companies collect huge volumes of text on a daily basis and through multiple channels (their agents, customer care centers, emails, social networks, web in general). The information collected includes policies, expert and health reports, claims and complaints, results of surveys, relevant interactions between customers and no-customers in social networks, etc. It is impossible to handle, classify, interpret or extract the essential information from all that material.

The Insurance Industry is among the ones that most can benefit from the application of technologies for the intelligent analysis of free text (known as Text Analytics, Text Mining or Natural Language Processing).

Insurance companies have to cope also with the challenge of combining the results of the analysis of these textual contents with structured data (stored in conventional databases) to improve decision-making. In this sense, industry analysts consider essential the use of multiple technologies based on Artificial Intelligence (intelligent systems), Machine Learning (data mining) and Natural Language Processing (both statistical and symbolic or semantic).

Most promising areas of text analytics in the Insurance Sector

Fraud detection

Detección de Fraude

According to Accenture, in a report released in 2013, it is estimated that in Europe insurance companies lose between 8,000 and 12,000 million euros per year due to fraudulent claims, with an increasing trend. Additionally, the industry estimates that between 5% and 10% of the compensations paid by the companies in the previous year were due to fraudulent reasons, which could not be detected due to the lack of predictive analytic tools.

According to the specialized publication “Health Data Management”, Medicare’s fraud prevention system in the United States, which is based on predictive algorithms that analyze patterns in the providers’ billing, in 2013 saved more than 200 million dollars in rejected payments.

Continue reading


Analyzig audience and opinion on live events for Social TV

By the end of June, we took part in the TVX 2014 international conference on interactive experiences for television and online video with a demo entitled “Numbat – Tracking Buzz and Sentiment for Second Screens”. On it we showed our work and expertise on social media analytics applied to television and live events, combining semantic analysis technologies and real-time data processing to get metrics on social audience and opinions about each feature of the live program or event.

Social TV is not only a continuously growing area, but also a thoroughly mature one, with dozens of companies interested in user interaction and social marketing. Social media are giving particular importance to this interaction between users and TV broadcasts. To realize how far the social conversation about international events goes, you could take a look at Twitter’s recap on FIFA World Cup 2014 group stage.

cristianoDuring the conference we could see the ways industry and researchers are taking to make their point on Social and Interactive TV. For example, second screen applications allow viewers to have a deeper understanding on what they are watching, providing additional information related to the broadcast (usually ad hoc and synchronized for a better user experience) or through automatic trends discovery. Other approaches try to help users finding the right TV programs by studying their habits and behaviors when watching television.

For our demo, we chose to visualize two World Cup matches being played at the same time: United States – Germany and Portugal – Ghana.

Continue reading


Use MeaningCloud API with the GATE plug-in

In our attempt to make MeaningCloud API the easiest way to use semantics in your application, today we are proud to present our latest development, a MeaningCloud plug-in for GATE.

GATE (General Architecture for Text Engineering) is an open-source workbench for text engineering that makes use of any kind of language processing component, from document crawling to search, and intelligent semantic annotations in particular.

Benefits for GATE and MeaningCloud API users

The plug-in provides GATE users a new set of multilingual functionalities, from parsing to entity extraction and sentiment analysis. For MeaningCloud users it would mean an easier and quicker method to prototype full applications including crawling, post-processing or indexing on annotated documents.  Besides, if you’re familiar with JAPE rules, it would enable to post-process, mix and match annotations from different processing resources for more complex pipelines. Finally, GATE is ideal for sharing and evaluating pipelines between team members, which increases productivity and produces more accurate results.


Tutorial for feature-level sentiment analysis

Heads up!

This tutorial was made for Textalytics and as such, it has become obsolete. You can read the updated version for MeaningCloud in this post.

MeaningCloud provides an API to carry out advanced opinion mining, Sentiment Analysis, which extracts both a global aggregated polarity of the text and a more in-depth analysis, giving a sentence-level breakdown of the polarity, extracting entities and concepts and the sentiment associated to each one of them.

Cover for Marvel's Black Widow #1

Marvel’s Black Widow #1

What makes MeaningCloud Sentiment Analysis API different is the possibility of defining entities and concepts for each call of the API, allowing you to obtain the same detailed sentiment analysis for entities or concepts specific to the domain of your application.

We are going to use comic book reviews to learn how to use this feature, as it’s a very rich domain in which it’s easy to illustrate how useful user-defined concepts and entities can be. This applies either to this field or to others where sentiment comes into play, such as hotel reviews, Foursquare tips, Facebook status updates or tweets about a specific event.

Continue reading


Sentiment Analysis tool for your brand in 10 minutes!

Have you ever tried to understand the buzz around your brand in social networks? Simple metrics about the amount of friends or followers may matter, but what are they are actually saying? How do you extract insights from all those comments? At MeaningCloud, we are planning a series of tutorials to show you how you could use text analytics monitor your brand’s health.

Today, we will talk about the fanciest feature: Sentiment Analysis. We will build a simple tool using Python to measure the sentiment about a brand in Twitter. The key ingredient is MeaningCloud Media Analysis API which will help to detect the sentiment in a tweet. We will also use Twitter Search API to retrieve tweets and the library matplotlib to chart the results.

Brand monitoring

Listening to what customers say on social networks about brands and competitors has become paramount for every kind of enterprise. Whether your purpose is marketing, product research or public relations, the understanding of sentiment, the perception and the topics related to your brand would provide you valuable insights.  This is the purpose of MeaningCloud Media Analysis API, make easier the extraction of these insights from the myriad of comments that are potentially talking about a brand. This tutorial will guide you through the process of building an application that listens to Twitter for your brand keywords and extract the related sentiment.
Continue reading