Trends and Outliers
TIBCO Spotfire's Business Intelligence Blog
Category Archives: Text Analytics
2012
Is Sentiment Analysis a Subset of Text Analytics?
Typically, industry analysts lump sentiment analysis and text analytics together, particularly when they talk about how to find value from social media conversations.
But is that the right way to view these two technologies? Is sentiment analysis a component of text analytics or is it an application on its own? And either way, what about the human element?
Recently, analytics visionary Seth Grimes (@sethgrimes) indicated that sentiment analysis draws on, but isn’t a subset of, text analytics. “Strong sentiment analysis relies on semantic analysis — on application of natural-language processing (NLP) techniques to identify sentiment objects (entities, topics, and concepts), opinion holders, and the sentiment, attitudes, and emotions that the opinion holders attach to the sentiment objects. But sentiment can also be inferred without any semantic analysis. For instance, the Consumer Confidence Index (CCI) and the Michigan Consumer Sentiment Index.”
In a post earlier this week, Grimes continued to break down why sentiment analysis doesn’t depend on text analytics.
Continue reading »
2011
An Overview of Predictive Analytics World
As of yesterday, all of the heavyweights in predictive analytics are gathering to talk, learn and make predictions about the future of analytics at the Predictive Analytics World Conference in New York City.
Attendees can pick from three levels of predictive analytics tracks including beginner/everyone, analytics expert and a special emphasis for people interested in financial services applications. The goal of the conference is to showcase the impact that predictive analytics can have on business, according to a conference press release.
Continue reading »
Filed under: Predictive Analytics, Text Analytics
2011
Text Analytics Summit 2011 – A Twitter Recap
Last week, another event lit up the Twittersphere – the Text Analytics Summit #TAS11. This event sparked some interesting conversations around adding semantics and nontraditional data to the analytics mix plus over 300 Tweets.
You can see the data visualization here:
Presented by chairman Seth Grimes, the Text Analytics Summit is in its seventh year. Alongside Grimes, who is considered the leading analyst in the field of text analytics, presenters included a number of analysts, social media directors and VPs, CMOs, researchers and vendor representatives. You can see the entire speaker list at this link.
Highlights
Text analytics is a hot field. According to Grimes, the attendance for the Text Analytics Summit was up 30 percent from 2010. Additionally, he reports that it’s taking a $835 million share of the $11 billion BI market.
Seth Grimes kicked off the event with an overview of where we are with text analytics and where the industry is going. If you missed the summit, you can see his presentation slide deck here. Grimes also gave a more in-depth look at the text analytics market and solutions in a workshop format at #TAS11. You can find all 79 of the presentation slides here.
Grimes is known for his witty Twitter commentary, and he doesn’t disappoint with this event’s best Twitter quote:
Seth Grimes: “Text analytics is like a dancing bear. You don’t care how good it is, you’re just amazed it works at all.” (approx) @Kurtis_Williams #TAS11
A couple more related to Grimes:
- John Blossom: “Emotional, ethnicity and cultural clues being harvested from speech analytics - @SethGrimes #tas11 More Second Web #tech.”
- Seth Grimes: ”@TomHCAnderson Sentiment/semantic is an artificial, idiosyncratic distinction that seems meant to create market differentiation. #TAS11.”
Chris Jones, senior manager of text analytics at Zynga (the company behind social games such as Farmville and Mafia Wars) received many Twitter accolades on his presentation: How to Operationalize the Voice of the Customer in Your Company.
Some of the best Tweets:
- Nicole Laskowski: “Chris Jones (Zynga): Text analytics can distance you from customers. Don’t forget to meet, talk to, shake hands with customers. #tas11.”
- Lee Feigenbaum (VP of Technology Services at Cambridge Semantics): “Chris Jones (Zynga) — link it together — text analytics data + other enterprise information #tas11 #semanticweb.”
- Tom H.C. Anderson (CEO of Anderson Analytics) : “Zynga talking about Farmville “There are 2 million farms in US. We have 30 million farmers on Facebook” #TAS11 #NGMR.”
A view of the experts. Topsy.com gives you the ability to search the hashtag #TAS11 and return all the Web resources related to the event. You can sort by Web, Blogs, Tweets and Experts. Here’s an experts list related to the Text Analytics Summit.
The Twitter Leader Board
- Seth Grimes – Grimes Tweeted more than anyone else by more than 6 percent. His Tweets accounted for more than 16 percent of the event’s Twitter Traffic.
- Jon Blossom – president of Shore Communications – a research firm specializing in marketing content and technology. Blossom accounted for just over 10 percent of the Tweet volume.
- Samir Batla – principal product manager at EMC Consulting. He Tweeted just under 10 percent of the Tweets. He also appeared on the Spotfire blog recently to discuss putting content in context.
- Shantanu Godbole – a researcher at IBM in New Delhi, India. He provided just under 8 percent of the real-time updates on TAS11. He also wins best Twitter handle with @solzaire.
- Nicole Laskowski & Deborah Balme. Laskowski is the new editor for business analytics and BI at TechTarget. She tied with Balme, associate director at OgilvyOne (advertising) specializing in analytical and data solutions. Both Tweeted just over 5 percent of the total TAS11 updates, respectively.
Here’s a convenient “Follow the Experts” list for you:
@SethGrimes
@TomHCAnderson
@LeeFeigenbaum
@Kurtis_Williams
@jblossom
@sabatla
@solzaire
@TT_nicole
@dbalme
Subscribe to the Trends & Outliers Blog for more insights on text analytics and what’s happening in the Twittersphere.
Amanda Brandon
Spotfire Blogging Team
2011
Text Analytics – What To Do With The Other 80% Of Your Data
Continue reading »
It is commonly estimated that 80% of enterprise data exists as text and other unstructured data. Text is everywhere – in emails, documents, reports, forms, call logs, press releases, blogs, tweets and more. Text analytics, or text data mining, is the process of automatically extracting concepts, topics, facts, sentiments, relationships and other information from text. It can be used to classify documents, automatically route emails to the right person, identify specific quality or service problems, monitor the competitive marketplace and better understand the “voice of the customer.”
2011
5 Tips For Getting Started With Text Analytics
If you’re just getting started with text analytics, you have the advantage of learning from others who have taken on a similar task. Here are five tips to keep in mind:
- 1. Start Small
Those more experienced with text analytics recommend starting with a pilot project so that you can demonstrate ROI, get management buy-in and use the knowledge and experience you gain through the pilot to expand into other areas. If your objective is to enhance brand and product image in the market, create competitive strategies from competitive analysis, develop actionable items from the customer feedback and improve customer service, that’s probably too much to take on. Start with a smaller, focused, realistic goal.
Continue reading »
Recent Comments