Category Archives: MeaningCloud

This category groups the different aspects of MeaningCloud we talk about in the blog.

Performance Metrics for Text Categorization

One of the most common and extensively studied knowledge extraction task is text categorization. Frequently customers ask how we evaluate the quality of the output of our categorization models, especially in scenarios where each document may belong to several categories.

The idea is to be able to keep track of changes in the continuous improvement cycle of models and know if those changes have been for good or bad, to commit or reject them.

This post gives answer to this question describing the metrics that we commonly adopt for model quality assessment, depending on the categorization scenario that we are facing.

 

Continue reading →

NLP technologies: state of the art, trends and challenges

This post presents MeaningCloud’s vision on the state of Natural Language Processing technology by the end of 2019, based on our work with customers and research projects.

NLP technology has practically achieved human quality (or even better) in many different tasks, mainly based on advances in machine learning/deep learning techniques, which allow to make use of large sets of training data to build language models, but also due to the improvement in core text processing engines and the availability of semantic knowledge databases.

Continue reading →

Case Study: Text Analytics against Fake News

Everybody has heard about fake news. Fake news is a neologism that can be formally defined as a type of yellow journalism or propaganda that consists of deliberate disinformation or hoaxes spread via traditional print and broadcast news media or online social media. It is also commonly used to refer to fabricated or junk news, with no basis in fact, but presented as being factually accurate.

The reason for putting someone’s efforts in creating fake news is mainly to cause financial, political or reputational damage to people, companies or organizations, using sensationalist, dishonest, or outright fabricated headlines to increase readership and dissemination among readers using viralization. In addition, clickbait stories, a special type of fake news, earn direct advertising revenue from this activity.

Continue reading →

Use case: VoC program for retail

Voice of the Customer (VoC) programs have become an established path for retailers to deliver enhanced customer experiences.

Consumer behavior, nevertheless, is always changing. Retailers are rarely able to anticipate these behavioral changes or adapt quickly enough to preserve or grow their market share.

In 2018, a regional supermarket brand with over 800 hundred stores wanted to understand customer experience at every touchpoint in order to identify potential areas of customer frustration.

The company undertook a strategic Voice of the Customer (VoC) program with the aim of systematically and consistently capturing insights from the customer experience.

The program is still running. It comprises of around 23,000 surveys per month, completed by customers at various branches of the supermarket chain.

In retail, listening to the Voice of the Customer to identify the strengths and weaknesses of business is fundamental. Competition is fierce. Given that the scale of information to be analyzed is immense, the company decided to work with MeaningCloud to process the literal answers to the open-ended questions of the surveys, so they need not worry about the amount or the time needed to process them.
Continue reading →

Introducing the Demo for VoC Retail

Illustration showing a group of shops. Voc Retail

At MeaningCloud, we know how important unstructured data is for  Voice of the Customer Analysis; so we’ve defined a model that will allow you to characterize any feedback, focusing on the retail domain, in detail that you receive from your customers.

Our experience in Voice of the Customer Analysis has shown us that to obtain useful results when consolidating or reorienting a business strategy the detection of peculiarities of a specific domain is vital, as much in a linguistic way as a conceptual way, taking into account the identifying characteristics of the brand to be analyzed. For this reason, we have not only developed an analysis model focused on the retail trade, but we have also adapted analytical tools towards the sale of groceries, personal care and homecare in the retail sector.

Continue reading →

MeaningCloud achieves ISO/IEC 27001 certification

In MeaningCloud, we know how important it is to manage and ensure information security, even more so for a platform that processes all kinds of texts — including texts with sensitive information — to help you extract insightful information from them. For this reason, at the end of last year Sngular prioritized confirming and improving our good practices by obtaining the ISO 27001 certification, which we achieved in our first attempt in February after following an extensive audit process carried out by RINA.

For those unfamiliar with it, ISO/IEC 27001 is an information security standard that specifies a management system that is intended to bring information security under management control and gives specific requirements.

Organizations that meet the requirements may be certified by an accredited certification body following successful completion of an audit. The standard is published by the International Organization for Standardization (ISO) and the International Electrotechnical Commission (IEC) under a joint subcommittee.

ISO27001

The certification obtained applies to both MeaningCloud in its SaaS and its on-premises version, and includes all its stages: development, maintenance and deployment.

MeaningCloud adheres to the Privacy Shield Framework

Privacy Shield Framework

At MeaningCloud, privacy issues represent a major concern. That’s because we have adhered to the Privacy Shield Framework, to guarantee our EU and Swiss customers full compliance to the European regulation of data privacy issues, as established by the EU General Data Protection Regulation (GDPR).

What is the EU-US Privacy Shield

The EU–US Privacy Shield is a framework for regulating transatlantic exchanges of personal data for commercial purposes between the European Union and the United States. One of its objectives is to enable US companies to more easily receive personal data from EU entities under EU privacy laws meant to protect European Union citizens. The EU–US Privacy Shield is a replacement for the International Safe Harbor Privacy Principles, which were declared invalid by the European Court of Justice in October 2015.

Continue reading →

New Release: Financial Industry Vertical Pack

Some text analytics scenarios need more than general purpose resources to get the results you need. If you are familiar with MeaningCloud, you’ll know that resource customization is one of our main features and great advantages. The parametrization available in the different analyses we offer enables you to adapt our tools to exactly the type of analysis you want. You can do this in two ways: using any of our predefined resources or creating your own with our customization consoles.

In this line, we are happy to announce that we have released a new vertical pack for the finance industry. This pack will allow you to analyze your financial contents and interpret them according to a standard vocabulary (FIBO™).

MeaningCloud release

Continue reading →

Liberty Shared: how an NGO uses Text Analytics

Liberty Shared[EDITOR’S NOTE: This is a guest post by Xinyi Duan, Director of Technology and Data Research at Liberty Shared.]

Liberty Shared is committed to ensuring that the experiences of vulnerable and exploited workers around the world is represented in our markets, legal systems, and information infrastructures. To do this, we have to take on the daunting task of wrangling some of the messiest data that have been previously un-mined and unstructured.

MeaningCloud has enabled us to quickly and effectively deploy NLP techniques to tackle these problems, and it works easily for team members who are using NLP statistical models already to those without that technical background. It is also powerful enough to grow with our programs. As we learn more about the problem, it is easy to update the models to reflect our learnings.

Continue reading →

Invoking the MeaningCloud Sentiment Analysis API from Minsait’s Onesait Platform

Minsait’s Onesait Platform is an IoT & Big Data Platform designed to facilitate and accelerate the construction of new systems and digital solutions and thus achieve the transformation and disruption of business. Minsait is a brand of Indra: its business unit addressing the challenges posed by digital transformation to companies and institutions.

Minsait has published a post about the procedure to invoke an external API from the integrated flow engine of the Onesait Platform (formerly known as Sofia2).

MeaningCloud integrated with Minsait Onesait Platform

The post titled HOW TO INVOKE AN EXTERNAL REST API FROM THE SOFIA2 FLOW ENGINE? uses as an example the integration of MeaningCloud Sentiment Analysis API (in Spanish).

The article illustrates one of the strengths of MeaningCloud: how easy it is to integrate its APIs into any system or process.