sentiment analysis

2月 012017
 

Each day, the SAS Customer Contact Center participates in hundreds of interactions with customers, prospective customers, educators, students and the media. While the team responds to inbound calls, web forms, social media requests and emails, the live-chat sessions that occur on the corporate website make up the majority of these interactions.

The information contained in these chat transcripts can be a useful way to get feedback from customers and prospects. As a result, the contact center frequently asked by departments across the company what customers are saying about the company and its products – and what types of questions are asked.

The challenge

Chat transcripts are a source for measuring the relative happiness of those engaged with SAS. Using sentiment analysis, this information can help paint a more accurate picture of the health of customer relationships.

The live-chat feature includes an exit survey that provides some data including the visitor’s overall satisfaction with the chat agent and with SAS. While 13 percent of chat visitors complete the exit survey (which is above the industry average), that means thousands of chat sessions only have the transcript as a record of participant sentiment.

Analyzing chat transcripts often required the contact center to pore through the text to identify trends within the chat transcripts. With other, more pressing priorities, the manual review only provided some anecdotal information.

The approach

Performing more formal analytics using text information gets tricky due to the nature of text data. Text, unlike tabular data in databases or spreadsheets, is unstructured. There are no columns that dictate what bits of data go where. And, words can be assembled in nearly infinite combinations.

For the SAS team, however, the information contained within these transcripts were a valuable asset. Using text analytics, the team could start to uncover and understand trends and connections across thousands of chat sessions.

SAS turned to SAS Text Miner to conduct a more thorough analysis of the chat transcripts. The contact center worked with subject-matter experts across SAS to feed this text information into the analytics engine. The team used a variety of dimensions in the analysis:

  • Volume of the chat transcripts across different topics.
  • Web pages where the chat session originated.
  • Location of the customer.
  • Contact center agent who responded.
  • Duration of the chat session.
  • Products or initiatives mentioned within the text.

In addition, North Carolina State University’s Institute for Advanced Analytics began to use the chat data for a text analytics project focused on sentiment analysis. This partnership between the university and SAS helped students learn how to uncover trends in positive and negative sentiment across topics.

The results

After applying SAS text analytics to the chat data, the SAS contact center better understood the volume and type of inquiries and how they were being addressed. Often, the analysis could point areas on the corporate website that needed updates or improvements by tracking URLs for web pages that were the launch point for a chat.

Information from chat sessions also helped tune SAS’ strategy. After the announcement of Windows 10, the contact center received customer questions about the operating system, including some negative sentiment about a perceived lack of support. Based on this feedback, SAS released a statement to customers assuring them that Windows 10 was an integral part of the product roadmap.

The project with NC State University has also provided an opportunity for SAS and soon-to-be analytics professionals to continue and expand on the analysis of chat transcripts. They continue to look at the sentiment data and how it changes across different categories (products in use, duration of chat) to see if there are any trends to explore further.

Today, sentiment analysis feeds the training process for new chat agents and enables managers to highlight examples where an agent was able to turn a negative chat session into a positive resolution.

SAS Sentiment Analysis and SAS Text Analytics, combined with SAS Customer Intelligence solutions such as SAS Marketing Automation and SAS Real Time Decision Manager, allow marketing organizations like SAS to understand sentiment or emotion within text strings (chat, email, social, even voice to text) and use that information to inform sales, service, support and marketing efforts.

If you’d like to learn more about how to use SAS Sentiment Analysis to explore sentiment in electronic chat text, register for our SAS Sentiment Analysis course. And, the book, Text Mining and Analysis: Practical Methods, Examples, and Case Studies Using SAS, offers insights into SAS Text Miner capabilities and more.

==

Editor’s note: This post is part of a series excerpted from Adele Sweetwood’s book, The Analytical Marketer: How to Transform Your Marketing Organization. Each post is a real-world case study of how to improve your customers’ experience and optimize your marketing campaigns.

tags: Adele Sweetwood, contact center, live chat, SAS Text Miner, sentiment analysis, text analytics, The Analytical Marketer

Using chat transcripts to understand customer sentiment was published on Customer Intelligence Blog.

7月 062016
 

When a person feels sufficiently wronged to lodge a complaint with the Consumer Financial Protection Bureau (CFPB), there’s likely to be some negative sentiment involved. But is there a connection between the language they use and the likelihood they will be compensated by the offending company? At the upcoming Sentiment […]

The post Sentiment analysis, machine learning open up world of possibilities appeared first on The Text Frontier.

5月 022016
 

The timeline on the latest season of Netflix’s series House of Cards has finally caught up with the real world, and the current plot line regarding President Frank Underwood’s underhanded dealings to win the Democratic nomination has many parallels with the current US primary election coverage saturating TV and print […]

Does big data spell big trouble on the campaign trail? was published on SAS Voices.

4月 192016
 

Of course everyone has heard all the hype on big data and how it can help business’ become more successful. But have you thought about the different types of big data? How the different types of data can support different initiatives within your business?

Structured versus unstructured data in retail is a key topic to first understand in order to create a successful plan. Structured data is data that sits in a database, a file, or a spreadsheet. It is generally organized and formatted. In retail, this data can be point-of-sale data, inventory, product hierarchies, ect. Unstructured data does not have a specific format. It can be customer reviews, tweets, pictures, and even hashtags.

So now that you know what structured versus unstructured data in retail is, let’s talk about how to use it. Customer reviews are a great way to understand why a certain product is or isn’t working. Word clouds are a tool to visualize large amounts of customer reviews. Finding key words that are continuously being used canRetail-Transaction_50B9900 give insight in to product defects. For example, if ‘fits small’ is frequently used then you can be proactive by adding this to the product description or above the size selection. This will reduce customer returns and money lost on shipping fees.

Unstructured data can also be analyzed for sentiment analysis. This gives insight in to whether the customer’s response is positive, negative, or neutral. A great example of this is being able to analyze your customer’s twitter responses. Let’s say you post a tweet with products you are thinking about buying for your spring line and your brands hashtag. This enables retailers to understand your customers’ response before you even buy the product. This technique can also be used in-season and give insight to merchants on areas of opportunity or risk so that open to buy can be managed. Break down the silos between merchandising and marketing and enhance collaboration.

It doesn’t take a data scientist to use unstructured data analytical techniques either. If you’re looking to use unstructured data in your business process, check out more information on SAS Visual Analytics. Also, take a look at the 2015 Forrester Wave report where SAS was named a leader in Big Data Predictive Analytics Solutions.

tags: big data, predictive analytics, retail, sentiment analysis, unstructured data

Structured Versus Unstructured Data in Retail was published on Customer Intelligence.

2月 112016
 

This is the first of two articles looking at how to listen to what your customers are saying and act upon it – that is, how to understand the voice of the customer. Over the last few years, one of the big uses  for SAS® Text Analytics has been to […]

The post Voice of the customer analysis (Part 1) appeared first on The Text Frontier.

12月 232015
 

In today’s world of instant gratification, consumers want – and expect – immediate answers to their questions. Quite often, that help comes in the form of a live chat session with a customer service agent. The logs from these chats provide a unique analysis opportunity. Like a call center transcript, […]

The post Come chat with us! appeared first on The Text Frontier.

8月 112015
 

As technology and analytics continue to evolve, we're seeing new opportunities not only in the way that we analyze data, but also in deployment options. More specifically, real-time deployment of analytical algorithms that enable organizations to detect and respond to security threats, offer timely incentives to customers, and mitigate risk by detecting compliance […]

The post Streaming Text Analytics: Finding value in real-time events appeared first on The Text Frontier.

6月 292015
 

Word clouds have been available in SAS Visual Analytics for a while now, but recently, sentiment analysis was added to their functionality.

For those of you not familiar with word clouds, a word cloud, also known as a tag cloud, is a visual representation of text data. You are probably seeing one or more word clouds every day when you peruse the web as they are increasingly being added to web pages. If you look at the right side of this web page that contains this blog, you will see a word cloud (Tags) that shows the most frequent topics. You can see by their size that SAS Global Forum and SAS Administrators are some of the most frequently blogged-about topics.

In the age of social media, blogs, tweets, online reviews, ratings and recommendations, the ability to take unstructured data and analyze it for sentiment is key to a competitive advantage. Being able to analyze this data, understand customer’s opinions about various products and services, filter out the noise and find relevant content that can be acted upon are some of the advantages of using sentiment analysis.

To see how the new sentiment analysis works, let’s start by creating a creating a new word cloud. I’ll use data from our some of our SAS employee blogs at blogs.sas.com to illustrate.

Creating the word cloud

I downloaded a .csv file that contains information on the topics that SAS employees have been sharing with their peers through April 27, 2015. I imported the .csv file into SAS Visual Analytics and created a word cloud in the SAS Visual Analytics Explorer. Because I imported the data, by default, it was loaded to the Public LASR Server, so I made sure to enable the English stop list on the Public LASR Server.

Stop lists.  Stop lists are used in text analysis to remove common words from the analysis and filter out noise. In the Properties tab for the word cloud, I entered 6 for the Maximum topics. Below is the initial word cloud, and you can see that for the first topic (analytics, social, +business, +medium), the words analytics, business, social and medium are the most important terms in the topic. No surprise that they also end up being the terms used to describe the topic!

Stemming. The + sign in front of a topic term indicates that stemming is being used. Stemming consolidates all forms of a word into one term. For example, the terms “make”, “makes”, “made” and “making” would be stemmed to +make). Stemming along with a stop list makes for a more concise word cloud. So this initial view of the word cloud shows us the different topics that were identified, and then within each topic, shows us the most relevant terms within each topic.

Word cloud in SAS Visual Analytics

Enabling sentiment analysis

Now let’s enable sentiment analysis. This task is just a matter of selecting a checkbox on the Properties tab of the word cloud. Here’s the updated word cloud, and you can see that the topic list is now colored by sentiment (green = positive, yellow = neutral and red = negative). In the upper right of the word cloud, you see a reference to how many documents are considered to be positive (406), neutral (1,687) and negative (193) for the selected topic.

word cloud with sentiment analysis

Working with the analysis

If you click on a term in word cloud, the details table opens at the bottom of the Word cloud. It shows each document in the topic that contains the selected term, the sentiment for the document, the relevance and any other fields that you assigned to the Document details role. In the screenshot below, the term business is selected and the details table has been expanded vertically. There are 225 documents that contain the term business.

WordCloud3

Now that the details table is open with the term business selected, we can filter by sentiment just by checking or unchecking the boxes in the upper right of the details table. The screenshot below shows that only the positive box is checked and that there are 33 documents in the topic that have positive sentiment.

WordCloud4

In the real world, by focusing on either the positive or negative sentiment documents, it should become evident what customers like or don’t like about a product. Armed with this information, businesses can either find opportunities for new products or fix issues that customers might have with their products and services. I think you’ll agree that the addition of sentiment analysis within SAS Visual Analytics is another great example of how SAS is democratizing data.

tags: SAS Visual Analytics, sentiment analysis, word cloud

How sentimental of you! Enabling sentiment analysis in a SAS Visual Analytics word cloud was published on SAS Users.

6月 262015
 

Double negatives seem to be everywhere, I have noticed them a lot in music recently. Since Pink Floyd sang "We don't need no education", to Rihanna's "I wasn’t looking for nobody when you looked my way". My own favourite song with a double negative is "I can't get no sleep" - Faithless. This […]

The post Why I’m not worried by double negatives? appeared first on The Text Frontier.

4月 292015
 

We’ve all heard the old saw, “If you torture data long enough, eventually it will confess to something.” But when it comes to spurring real change, how about ditching the dungeon-master act and thinking like a venture capitalist instead? Wouldn’t that pay bigger dividends? That was the tip from Ravi […]

The post Data scientist as venture capitalist appeared first on SAS Voices.