Consumer & Market Analytics: Q&A with Lauren Azulay, Confirmit

Our thesis: Language technologies — text, speech, and social analytics — natural language processing and semantic analysis — are the key to understanding consumer, market, and public voices. Apply them to extract the full measure of business value from social and online media, customer interactions and other enterprise data, scientific and financial information, and a spectrum of other sources. The insight you’ll gain means competitive edge, whatever your organization’s mission.

Insight, via business (and research and government) application of language technologies, is the central topic for LT-Accelerate, a new conference that takes place December 4-5 in Brussels.

Lauren Azulay, Confirmit
Lauren Azulay, Confirmit

I recently interviewed a number of LT-Accelerate speakers. My questions broadly cover the topics they’ll be addressing in their conference presentations. This article relays my Q&A with speaker Lauren Azulay of Confirmit, a customer, employee, and market insights solution provider.

Let’s get right into it!

Q1: The topic of this Q&A is consumer and market insight. What’s your personal background and your current work role, as they relate to these domains?

Lauren Azulay: My current role is Senior Product Manager for Text and Social Analytics at Confirmit, where consumer and market insight is at the heart of what we do. Text Analytics gives insight into the voice of the customer and the social analytics provides insight into the voice of the market. Previously, I was the Product Manager of the Channel and Brand insights platform for YouTube multi-channel network, Base79, where we discovered and uncovered meaningful patterns in data for brands and channels wanting to increase their exposure on YouTube. Before that I spent 7 years as Head of Product and then Head of Internationalisation and Billing on a social networking product, where consumer and market insight drove our new product development and launch in new territories.

Q2: What roles do you see for text and social analyses, as part of comprehensive insight analytics, in understanding and aggregating market voices?

Lauren Azulay: The voice of the market includes your competitors, independent analysts and commentators, or just consumers who may or may not be your customers. Understanding the buzz and sentiment around key topics or issues across all these voices can help marketing, sales, services and product functions within a business. Social analysis is also good for early issue detection which can protect you from brand damage, reduce service costs and improve customer satisfaction.

Q3: Are there particular tools or methods you favor? How do you ensure business-outcome alignment?

Lauren Azulay: Extracting social insights requires capturing not just the text but all of the metadata associated with each post or comment, such as the conversation data, author, etc. Because of the large volumes, statistical techniques are better than rules-based approaches to categorization and sentiment analysis, as they can process very large volumes of text much faster.

The right visualisations are important for bringing the data to life, and the ability to correlate the social insights with other business and customer data has the potential to offer significant value.

Q4: A number of industry analysts and solution providers talk about omni-channel analytics and unified customer experience. Do you have any thoughts to share on working across the variety of interaction channels?

Lauren Azulay: A centralised customer hub is essential. In the end, the solution will most likely be a hybrid combination of different technologies, as storing and managing social data is a different technical problem to solve than storing transactional data. So it’s important for any hub solution to easily integrate with other customer or data hubs within an organisation, and each one can be targeted at the problem it is best suited to solve. This is the only way businesses will be able to achieve the holy grail of a truly unified customer experience across all channels, including social.

Q5: To what extent does your work involve sentiment and subjective information?

Lauren Azulay: We have many customers that have deployed sentiment analysis for text from both voice of the customer data and social media data. For example, Sony Mobile have been using social media to detect consumer issues as they come up in order to improve their products and services, protect their brand and to avoid costs.

Q6: How do you recommend dealing with high-volume, high-velocity, diverse data — to ensure that analyses draw on the most complete and relevant data available and deliver the most accurate results possible?

Lauren Azulay: The key to analysis is to understand the data sources and how they all fit together for your business and your market. In order to deal with large volumes of diverse data, such as social data, you need to know your objectives and be very focused on the project goal. This drives the data sources you analyse and the categorisation model you apply. The data structure is also important, as mentioned before, so that you make sure that all relevant metadata is stored along with the text. Categorisation of all texts can be performed very quickly using Boolean search techniques. Knowing the volume of interactions by category gives you the buzz, which can then be tracked over time and can quickly highlight trending topics.

However, performing sentiment analysis on all the data captured is not practical, even with a high-performing statistically-based sentiment algorithm. Statistical sampling, performed correctly, can ensure an accurate sentiment and can be obtained by category, even if there are thousands or millions of text strings within each category. Research we have conducted shows that a collection of a million documents can be analysed in a very short time using a sample of 20,000 documents, with a high degree of accuracy.

In addition, with the right analytical tools and the right visualisations, humans can interpret the results and explore the root causes for specific topics. Human analysis is very important in pulling it all together and drawing the overall conclusions.

Q7: Could you provide an example (or two) that illustrates really well what your organization and clients have been able to accomplish via analytics that demonstrate strong ROI?

Lauren Azulay: Sony Mobile, through their social media ‘listening’ service, uncovered more than 15,000 unique issue reports in a year. This gave them the ability to prioritise the 3 main issue categories and focus on a process of remediation. This has saved the company tens of thousands of dollars and improved customer satisfaction, which has been measured through social media.

Q8: You’ll be presenting a lighting talk at LT-Accelerate. What will you be covering?

Lauren Azulay: Social analytics in action!

Thanks Lauren. Readers, if what you’ve read here sounds interesting, please do visit the LT-Accelerate Web site to learn more about the conference. We’ve designed the conference as a venue for learning, networking, and opportunity, for technologists and business users alike.

Leave a Reply