MeaningCloud helps you discover unexpected insights in your contents

MeaningCloud enables you to automatically discover emerging subjects and relationships between documents, allowing a more agile and exploratory analysis of unstructured content.

28 SEPTEMBER 2015, NEW YORK, USA
Summary
With this new release of MeaningCloud you can perform text analytics tasks with no need to configure predefined dictionaries and models. Its unsupervised learning technology enables users to discover emerging subjects and relationships between documents, allowing more agile and dynamic analytics and enabling all kinds of applications: content recommendation, document organization or exploratory analysis of the customers' opinions.

Standard text analytics techniques extract information and classify content according to predefined dictionaries and categories, so it is required to have a prior idea of the kind of insights that will be obtained from the analysis.

MeaningCloud will contribute to change this way of doing text analytics by incorporating unsupervised learning techniques that allow to explore a series of documents for discovering and extracting unexpected insights (subjects, relationships). Besides, it makes these techniques available to everyone as part of its cloud-based semantic analysis product, "meaning as a service".

In particular, this new release of MeaningCloud includes a Text Clustering API that allows to discover the implicit structure and the meaningful subjects that emerge from all kinds of content: documents, contact center interactions, social conversations, etc.

This new API is specialized in the processing of unstructured content (it is not, as often happens with the offer available in the market, a clustering functionality for structured data). The API groups the documents not by applying a purely textual similarity, but depending on their relationship with the subjects appearing in the collection, and automatically assigns to each cluster a title or name which represents its predominant subject.

Clustering complements MeaningCloud's capabilities for information extraction, classification, and sentiment analysis, providing more exploratory, flexible and dynamic analytics. This functionality is especially indicated for those applications that aim at detecting relationships between different texts, distributing them dynamically in natural groups or discovering the most relevant subjects within their content and expressing them in their own terms.

It can be used to detect duplicate texts, recommend related contents, organize a collection of texts according to its contents (not depending on categories predefined externally) and discover meaningful subjects within the customers' feedback and in all type of unstructured interactions. More specifically, in the key fields of the analysis of the Voice of the Customer or the management of the User Experience, clustering is applied when it is required to discover the “new voice” of those customers.

Text Clustering comes in addition to other differentiating characteristics of MeaningCloud, such as its graphic customization tools -which permit to easily create custom models and dictionaries-, the possibility of experimenting and prototyping analysis pipelines thanks to its plug-ins for Micosoft Excel and GATE, and its integrability in all kinds of architectures.

Learn more about the new release of MeaningCloud and the Text Clustering functionality.

Quotes
"This new release enables a more exploratory semantic analysis based on the discovery of insights, and contributes to more agile text analytics." Antonio Matarranz, CMO MeaningCloud
news