Price is no longer the first thing that a customer looks at in supermarkets. Listening to the Voice of the Customer to identify the strengths and weaknesses of any business is fundamental when applying efficient retention techniques.
Category Archives: MeaningCloud
Recorded webinar: Solve the most wicked text categorization problems
Thank you all for your interest in our webinar “A new tool for solving wicked text categorization problems” that we delivered last June 19th, where we explained how to use our Deep Categorization customization tool to cope with text classification scenarios where traditional machine learning technologies present limitations.
During the session we covered these items:
- Developing categorization models in the real world
- Categorization based on pure machine learning
- Deep Categorization API. Pre-defined models and vertical packs
- The new Deep Categorization Customization Tool. Semantic rule language
- Case Study: development of a categorization model
- Deep Categorization – Text Classification. When to use one or the other
- Agile model development process. Combination with machine learning
IMPORTANT: this article is a tutorial based on the demonstration that we delived and that includes the data to analyze and the results of the analysis.
Interested? Here you have the presentation and the recording of the webinar.
(También presentamos este webinar en español. Tenéis la grabación aquí.)
Continue reading
Tutorial: create your own deep categorization model
As you have probably know by now if you follow us, we’ve recently released our new customization console for deep categorization models.
Deep Categorization models are the resource we use in our Deep Categorization API. This API combines the morphosyntactic and semantic information we obtain from our core engines (which includes sentiment analysis as well as resource customization) with a flexible rule language that’s both powerful and easy to understand. This enables us to carry out accurate categorization in scenarios where reaching a high level of linguistic precision is key to obtain good results.
In this tutorial, we are going to show you how to create our own model using the customization console: we will define a model that suits our needs and we will see how we can reflect the criteria we want to through the rule language available.
The scenario we have selected is a very common one: support ticketing categorization. We have extracted (anonymized) tickets from our own support ticketing system and we are going to create a model to automatically categorize them. As we have done in other tutorials, we are going to use our Excel add-in to quickly analyze our texts. You can download the spreadsheet here if you want to follow the tutorial along. If you don’t use Microsoft Excel, you can use the Google Sheets add-on.
The spreadsheet contains two sheets with two different data sets, the first one with 30 entries, the second one with 20. For each data set, we have included an ID, the subject and the description of the ticket, and then a manual tagging of the category it should be categorized into. We’ve also added an additional column that concatenates the subject and the description, as we will use both fields combined in the analysis.
To get started, you need to register at MeaningCloud (if you haven’t already), and download and install the Excel add-in on your computer. Here you can read a detailed step by step guide to the process. Let’s get started! Continue reading
New Release: Deep Categorization Customization Console
One of the APIs that has had more “movement” lately in our updates is the Deep Categorization API, which — as many of you already know — provides an easier, more flexible and precise way to categorize texts. Most of this movement has come in the form of new supported models such as Intention Analysis, as well as many under-the-hood improvements.
We are happy to announce that we have finally released the Deep Categorization customization console in our web.
This console will allow you to create accurate models for those scenarios where you need a very high level of linguistic precision to differentiate between the different categories you want to detect.
Case study on the voice of the patient for the Pharma industry
Pharmaceutical companies are extending their Voice of the Patient projects to include social media: comments on web forums, surveys, Twitter, and more.
The goal of the proof of concept ordered by one particular pharmaceutical company in Spain was to: ” Collect and analyze the voice of the patient, both quantitatively and qualitatively, from the channels where it is expressed”, including social networks like web forums, Facebook, Twitter, and other systems.
For the pharma industry, it is essential to listen and understand the feedback that their current and potential customers communicate through various means and touchpoints.
Web forums, for instance, gather millions of posts, and function as a meeting point for patients where support, experiences, and wisdom are shared with peers, family members, and friends.
MeaningCloud Release: Sentiment + Nordic Pack
Not long ago we published the first of our Language Packs: the Nordic pack, which includes several text analytics tasks in Swedish, Danish, Norwegian and Finnish.
Among the text analytics tasks supported, there’s one that was missed by many of you: Sentiment Analysis API. Well, no more!
We are happy to announce that from now on you can also analyze sentiment in the four languages included in the Nordic pack. And what’s more, for those of you that are already subscribed to the pack, it has been automatically included and so you can start using it right away without any change in pricing.
For those of you that are not subscribed to the Nordic pack, remember that you can test all our packs full functionality by requesting a 30 day period trial. It’s super easy!
MeaningCloud participates in T3chFest 2019
This year MeaningCloud participates in T3chFest, the technology fair in University Carlos III de Madrid.
T3chFest was born as a show of the research works made in the Department of Informatics. Today, the event has become a reference in Spain’s technology scene. In the last edition 1600 people attended to more than 80 talks.
This year we have submitted a call titled “NLP for Small Data“, where we review the state of the art in the Natural Language Processing. We will also discuss the advances in Deep Learning and the usage of Linguistic Models.
The talk will be presented by two members of our Linguistics team: Concepción Polo, Director of Linguistics, and María José García, computational linguist. They are actively involved in every linguistic model in all our products, from the initial model sketch to its final fine tuning.
Text analytics explained: MeaningCloud in Italian
In previous posts we spoke about text analysis performed in French and Portuguese. Today we’re wrapping up this linguistics series by discussing the analyses that can be done with Italian texts.
Italian is spoken in several European countries such as Italy, San Marino and Switzerland, totaling almost 70 million speakers. As Italians have migrated all over the world, its language is also present on the other side of the pond. In South America, for instance, it is the second most spoken language in Argentina. In the US, even though it is not an officially spoken language, many of its citizens are of Italian descendent and thus speak the language at home. We wanted to include such a widely spread language in our Standard Languages Pack.
Similarly to our previous posts, we are going to explain, in a linguistically-inclined way, what Text Analytics is and which functionalities MeaningCloud provides in Italian.
Are you listening to the Voice of the Customer?
“Your most unhappy customers are your greatest source of learning.” Bill Gates
In a widely digitalized market, open to all and undoubtedly more accelerated than just a decade ago, quickly identifying customer complaints and needs is key to preserve a company’s competitiveness within its industry. Technological democratization has provided users with skills and tools that not only turn the product but also many other aspects into an experience. If after several years of investment and development, your product has come to position itself among the best in the market, does it make sense for a poorly designed purchasing process to threaten the conviction of potential customers that you are worth choosing?
TASS 2018: Fostering Research on Semantic Analysis in Spanish
MeaningCloud and University of Jaen have been the organizers of TASS, the Workshop on Semantic Analysis in Spanish language at SEPLN (International Conference of the Spanish Society for Natural Language Processing), again in 2018.
During the years, the research has extended to other tasks related to the processing of the semantics of texts that attempt to further improve natural language understanding systems. Apart from sentiment analysis, other tasks attracting the interest of the research community are stance classification, negation handling, rumor identification, fake news identification, open information extraction, argumentation mining, classification of semantic relations, and question answering of non-factoid questions, to name a few.
TASS 2018 was the 7th event of the series and was held in conjunction with the 34rd International Conference of the Spanish Society for Natural Language Processing, in Seville (Spain), on September 18th, 2018. Four research tasks were proposed. MeaningCloud sponsored this edition with prizes for the best systems in each of the tasks. A comprehensive description paper is (to be) published in Procesamiento del Lenguaje Natural journal, vol 62: TASS 2018: The Strength of Deep Learning in Language Understanding Tasks.
