A solid text-analysis software platform can mine insight from a lot of different things, but not a stack of actual paper. For that, you still need a human being.[/caption] Every day, progressively more data floods into organizations around the world. Analyzing all that information is a daunting task, to say the least, even for companies with the latest analytics platforms and the most highly-caffeinated data scientists. All that data can also create an intimidating signal-to-noise ratio: sure, you can view a week’s worth of Twitter and Facebook feeds via a customized dashboard, and perform a sentiment analysis to see how those Tweets and postings collectively feel about your latest product. But mixed in with that “good” information is quite a bit of useless material, which can make the process of analysis that much more difficult. SAS is trying to cut through all that noise with its enhanced version of SAS Text Miner for text and other unstructured data. The app can help analysts trace relationships between documents, embed text analytics results directly into platforms such as Excel, and predict future trends based on the text filtering through the system; features include visualization of results, integrated document filtering, and the ability to define entities for fact and event extraction. By using the software to pore through logs, for example, a company could earn a finer picture of its customer base. "SAS Text Miner helped us analyze detailed call center notes, and we achieved a much more granular understanding of callers than we had before," Greg Hayworth, Scientist for Humana's Provider Network Operations, wrote in an Oct. 8 statement. "Other projects include comparing the authorizations from nurses who review medical claims to the medical services that were provided and, another, analyzing free responses in surveys of our health care providers. Reading each note was inefficient.” Other SAS modules allow analysts to determine sentiment expressed in everything from Websites to internal files; link text repositories using semantic relationships; and identify dual documents. Various IT vendors have stepped forward with tools for analyzing text, particularly in a social media context. Over the past few months, Salesforce, Oracle, and Google have all purchased social-engagement startups whose assets, once baked into the larger firms’ software portfolios, will allow for the analysis of all those posts and Tweets swarming through the Web. Still other firms market analytics for enterprise documents, scouring thousands or millions of pages of in-house text for insight; lawyers and attorneys, for example, have turned to predictive coding as a way of speeding up e-discovery, which usually involves a time-consuming dig by humans through giant document troves. Image: BortN66/Shutterstock.com SAS Updates Text Analysis Software
[caption id="attachment_5057" align="aligncenter" width="500"] A solid text-analysis software platform can mine insight from a lot of different things, but not a stack of actual paper. For that, you still need a human being.[/caption] Every day, progressively more data floods into organizations around the world. Analyzing all that information is a daunting task, to say the least, even for companies with the latest analytics platforms and the most highly-caffeinated data scientists. All that data can also create an intimidating signal-to-noise ratio: sure, you can view a week’s worth of Twitter and Facebook feeds via a customized dashboard, and perform a sentiment analysis to see how those Tweets and postings collectively feel about your latest product. But mixed in with that “good” information is quite a bit of useless material, which can make the process of analysis that much more difficult. SAS is trying to cut through all that noise with its enhanced version of SAS Text Miner for text and other unstructured data. The app can help analysts trace relationships between documents, embed text analytics results directly into platforms such as Excel, and predict future trends based on the text filtering through the system; features include visualization of results, integrated document filtering, and the ability to define entities for fact and event extraction. By using the software to pore through logs, for example, a company could earn a finer picture of its customer base. "SAS Text Miner helped us analyze detailed call center notes, and we achieved a much more granular understanding of callers than we had before," Greg Hayworth, Scientist for Humana's Provider Network Operations, wrote in an Oct. 8 statement. "Other projects include comparing the authorizations from nurses who review medical claims to the medical services that were provided and, another, analyzing free responses in surveys of our health care providers. Reading each note was inefficient.” Other SAS modules allow analysts to determine sentiment expressed in everything from Websites to internal files; link text repositories using semantic relationships; and identify dual documents. Various IT vendors have stepped forward with tools for analyzing text, particularly in a social media context. Over the past few months, Salesforce, Oracle, and Google have all purchased social-engagement startups whose assets, once baked into the larger firms’ software portfolios, will allow for the analysis of all those posts and Tweets swarming through the Web. Still other firms market analytics for enterprise documents, scouring thousands or millions of pages of in-house text for insight; lawyers and attorneys, for example, have turned to predictive coding as a way of speeding up e-discovery, which usually involves a time-consuming dig by humans through giant document troves. Image: BortN66/Shutterstock.com
A solid text-analysis software platform can mine insight from a lot of different things, but not a stack of actual paper. For that, you still need a human being.[/caption] Every day, progressively more data floods into organizations around the world. Analyzing all that information is a daunting task, to say the least, even for companies with the latest analytics platforms and the most highly-caffeinated data scientists. All that data can also create an intimidating signal-to-noise ratio: sure, you can view a week’s worth of Twitter and Facebook feeds via a customized dashboard, and perform a sentiment analysis to see how those Tweets and postings collectively feel about your latest product. But mixed in with that “good” information is quite a bit of useless material, which can make the process of analysis that much more difficult. SAS is trying to cut through all that noise with its enhanced version of SAS Text Miner for text and other unstructured data. The app can help analysts trace relationships between documents, embed text analytics results directly into platforms such as Excel, and predict future trends based on the text filtering through the system; features include visualization of results, integrated document filtering, and the ability to define entities for fact and event extraction. By using the software to pore through logs, for example, a company could earn a finer picture of its customer base. "SAS Text Miner helped us analyze detailed call center notes, and we achieved a much more granular understanding of callers than we had before," Greg Hayworth, Scientist for Humana's Provider Network Operations, wrote in an Oct. 8 statement. "Other projects include comparing the authorizations from nurses who review medical claims to the medical services that were provided and, another, analyzing free responses in surveys of our health care providers. Reading each note was inefficient.” Other SAS modules allow analysts to determine sentiment expressed in everything from Websites to internal files; link text repositories using semantic relationships; and identify dual documents. Various IT vendors have stepped forward with tools for analyzing text, particularly in a social media context. Over the past few months, Salesforce, Oracle, and Google have all purchased social-engagement startups whose assets, once baked into the larger firms’ software portfolios, will allow for the analysis of all those posts and Tweets swarming through the Web. Still other firms market analytics for enterprise documents, scouring thousands or millions of pages of in-house text for insight; lawyers and attorneys, for example, have turned to predictive coding as a way of speeding up e-discovery, which usually involves a time-consuming dig by humans through giant document troves. Image: BortN66/Shutterstock.com 