Author Archives: Blanca Galego

Voice of the Customer in the banking industry

The Voice of the Customer (VoC) is a market research technique that produces a detailed set of customer wants and needs, organized into a hierarchical structure, and then prioritized in terms of relative importance and satisfaction with current alternatives.

Voice of the Customer (VoC)

The Voice of the Customer (VoC) is not a new concept. In one way or another, it’s been included in quality assurance processes for years, and yet, its full integration in the workflow is a pending tasks for many companies. The Voice of the Customer allows you to listen, interpret and react to what’s being said, and then monitor the impact your actions have over time.

The current challenge companies are facing comes from the volume of data available. In this digital age, feedback is ever-growing and not just limited to the periodic surveys sent to clients. Word-of-mouth has gone digital and has become more relevant than ever: everyone with a Twitter or a Facebook account has an opinion, and more often than not, it’s about the products and services they consume.

A typical client

A client

As so many other sectors, banking needs to figure out how to translate this first-hand source of knowledge their clients are providing into something useful, something that can be used in the company’s decision-making process.

Voice of the Customer combines two key aspects of information extraction: the need to know in detail what the customer is talking about and to interpret correctly his feelings about it. The former gives a quantitative view of the feedback obtained while the latter gives a more qualitative analysis, measuring what clients think a company is doing right or wrong.

The banking domain has the added difficulty of providing an extremely wide array of products and services, each one of them with very specific subcategories and received through completely different channels.

Continue reading


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