Author Archives: Antonio Matarranz

About Antonio Matarranz

Chief Marketing Officer at MeaningCloud

RapidMiner: Relationship between product scores and text review sentiment

This is the first of two tutorials where we will be using MeaningCloud Extension for RapidMiner to extract insights that combine structured data with unstructured text. See the second one here. To follow these tutorials you will need to have RapidMiner Studio and our Extension for RapidMiner installed on your machine (learn how here).

In this tutorial we shall analyze a set of food reviews from Amazon. We will use the MeaningCloud sentiment API and try to see how users score products and whether their review description of a certain product corresponds to the score that they have assigned – more specifically we will try to see

  • How closely the review sentiment corresponds to the manually assigned score (which we already have available in our dataset).

The dataset that we will be using throughout the tutorial can be found here. First thing we need to do is download the CSV to our computer.

Continue reading

You can now use MeaningCloud with RapidMiner

Expand text analytics with the tools to create the most sophisticated predictive models

At MeaningCloud, we have just launched a feature that enables users to incorporate our text analytics into complex predictive models based on structured data. With our new Extension for RapidMiner you can directly embed our semantic analysis engines into the process pipelines defined in this popular analytical tool.

RapidMiner is an open-source platform for data science, recognized as a leader in the field of advanced analytics tools. RapidMiner is used for preparing data, creating predictive models, validating them, and embedding them into business processes quickly and easily .

Continue reading

Active social listening to protect Online Reputation (Part 2)

EDITOR’S NOTE: This is a guest post by Leopoldo Martínez D., a researcher and consultant on social media corporate intelligence and lecturer at UCV and IESA (Venezuela), and it was originally published on his blog (in Spanish).


  1. Introduction

As I stated in the first part of this post, I will show how online reputation evaluation was used in a real situation related to the tourism industry.

  1. The unexpected event: A shooting at a music festival in Playa del Carmen, Riviera Maya

January 6-15, 2017, a music festival was scheduled to be held in Playa del Carmen, as well as a series of events related to both music and the tourism industry. On January 15, a shooting occurred in a well-known bar where people were celebrating the end of the festival.

When the shooting happened, messages quickly spread through social networks to give information and comment on the context in which the incident and how it happened. Some conversations revealed an interesting fact: The shooting was not an isolated event but stemmed from the “situation of crime that the Riviera Maya went through in 2011″.

Could this affect the Riviera Maya’s reputation as a tourist destination? Could “several years in a situation of crime” have already influenced the tourism industry’s image? These are some of the questions that the public and private actors that provide services and products in this tourist area might have been asking themselves.

Continue reading

Active social listening to protect Online Reputation (Part 1)

EDITOR’S NOTE: This is a guest post by Leopoldo Martínez D., a researcher, consultant on social media corporate intelligence and lecturer at UCV and IESA (Venezuela), and it was originally published on his blog (in Spanish).


1. Introduction

In this previous post, I suggested that conversations taking place in virtual communities fostered by a digital marketing plan generate feedback that is useful for assessing and monitoring a digital’s marketing strategy’s performance.

This feedback could generate a huge amount of valuable data (Big Data) which enables the creation of a knowledge base for the topic being talked about, who is participating, who is having the greatest impact on brand image, products, people, or organizations.

This knowledge base can also be fed by discussions arising from unexpected events which are not part of the communication plan but deal with the virtual community’s topics of interest.

To specifically assess the conversation’s impact, it is necessary to pay attention (beyond listening) to what is being said through metrics (qualitative and quantitative) that reflect the online community’s perception on brands, products, people, or organizations. After all, this perception is a way to measure an online reputation.

With this need in mind, the purpose of this post is to show how to use the active listening of conversations in social networks to evaluate your online reputation.
Continue reading

Recorded webinar: When to use the different Text Analytics tools?

Last February 9th we presented our webinar “Classification, topic extraction, clustering… When to use the different Text Analytics tools?”. Thank you all for your interest.

During the session we covered the following agenda:

  • An introduction to Text Analytics.
  • Which application scenarios can benefit most from Text Analytics? Conversation analysis, 360° vision, intelligent content, knowledge management, e-discovery, regulatory compliance… Benefits and challenges.
  • What are the different Text Analytics functions useful for? Information extraction, categorization, clustering, sentiment analysis, morphosyntactic analysis… Description, demonstration and applications.
  • What features should a Text Analytics tool have? Is it all a question of precision? How to enhance quality?
  • A look at MeaningCloud’s roadmap.

IMPORTANT: The data analyzed during the webinar can be found in this tutorial.

Interested? Here you have the presentation and the recording of the webinar.

(También presentamos este webinar en español. Tenéis la grabación aquí.)
Continue reading

Classification, topic extraction, clustering… When to use the different Text Analytics tools? (webinar)

How to leverage Text Analytics technology for your business

Text AnalyticsMost valuable information for organizations is hidden in unstructured texts (documents, contact center interactions, social conversations, etc.). Text Analytics helps us to structure such data and turn it into useful information. But which text analytical tools are the most appropriate for each case? When should I use information extraction, categorization, or clustering? Which applications can benefit most from Text Analytics? What are the challenges?

Register for this MeaningCloud webinar on Wednesday, February 8th at 9:00 PDT and discover answers to these and other questions through practical examples.

UPDATE: this webinar has already taken place. See the recording here.

(Este webinar también se realizó en español, ver la grabación aquí.)

Learn to develop custom text classifiers (recorded webinar)

Last October 5th we presented our webinar “Learn to develop custom text classifiers with MeaningCloud”. Thank you all for your attendance.

We began by presenting how to do text classification with MeaningCloud and why it is necessary to develop models that are adapted to each specific application scenario. The bulk of the presentation consisted in using a practical case (analysis of restaurant reviews) to show how these models can be developed using our product.

Continue reading

Learn to develop custom text classifiers with MeaningCloud (webinar)

Learn in this webinar how to use MeaningCloud’s tools to create classification models completely adapted to your scenario

Users frequently ask us through our support line how to perform text classification according to application-specific taxonomies. For example, somebody needing to analyzing a bank’s contact center calls and open survey responses might be interested in classifying such messages according to the institution’s different types of products and services (deposits, loans, mortgages, etc.) or the type of interaction (request for information, contracting, complaint, etc.).

Custom classification

Continue reading

Automatic IAB tagging enables semantic ad targeting

Our Text Classification API supports IAB’s standard contextual taxonomy, enabling content tagging in compliance with this model in large volumes and with great speed, and easing the participation in the new online advertising ecosystem. The result is the impression of ads in the most appropriate context, with higher performance and brand protection for advertisers.

What is IAB’s contextual classification and what is it good for

The IAB QAG contextual taxonomy was initially developed by the Interactive Advertising Bureau (IAB) as the center of its Quality Assurance Guidelines program, whose aim was to promote the advertised brands’ safety, assuring advertisers that their ads would not appear in a context of inappropriate content. The QAG program provided certification opportunities for all kinds of agents in the digital advertising value chain, from ad networks and exchanges to publishers, supply-side platforms (SSPs), demand-side platforms (DSPs), and agency trading desks (ATDs).

The Quality Assurance Guidelines serve as a self-regulation framework to guarantee advertisers that their brands are safe, enhance the advertisers’ control over the placement and context of their ads, and offers transparency to the marketplace by standardizing the information flowing among agents. All this, by providing a clear, common language that describes the characteristics of the advertising inventory and the transactions across the advertising value chain.

Essentially, the contextual taxonomy serves to tag content and is made of standard Tiers, 1 and 2 – specifying, respectively, the general category of the content and a set of subcategories nested under this main category – and a third Tier (or more) that can be defined by each organization. The following pictures represent those standard tiers.
Continue reading