August 2009 Archives

New Papers, 1 September 2009

Phase2 Technology has announced the release schedule for Tattler (app). The open-source monitoring tool, which builds on the earlier BuzzMonitor project, enters private beta in September, with public beta and enterprise-ready releases planned for October and December, respectively. Documentation and an instructional video are now available on the web site.

Related:

Software Updates, 28 August 2009

Recently announced software updates:

  • Clarabridge
    Content Mining Platform 3.3: Performance, embedded reports, classification, sentiment, statistics capabilities, BI/data warehouse support.

  • CyberAlert
    Automated translation, clip publishing widget, Twitter monitoring.

Upcoming Events, 28 August 2009

10 September (London) - MeasurementCamp, 10:00 AM at Dare Digital.

14 September (New York) - Brandhackers, 6:00 at Dewey's Flatiron, 210 5th Ave. Noah Brier will talk about BrandTags.

14–16 October (Portsmouth, NH) - IPR's annual Summit on Measurement

10–12 November (Seville) - 1st International Workshop on Mining Social Media (CFP)

BuzzStream has announced the addition of social media monitoring to their social CRM product for PR, which is currently in beta. The system emphasizes monitoring of individual items and tracking interactions with social media contacts. Contact records include influence scores, which can be used to filter content. Pricing starts at $49/month for a single-user account and $99/month for a business account.

Automation Key to High-Volume Analysis

| 1 Comment

This post introduces a new opinion section on SMA. The opinions expressed are those of their authors, and I invite you to share yours, either in the comments or in your own guest post. In the spirit of the great opinion journals, SMA invites an open discussion of topics that matter.
- Nathan Gilliatt

Machine-based sentiment analysis is key to processing large amounts of data
by Mike Marshall

There has been ongoing debate in the text analytics world regarding accuracy of sentiment as it pertains to automated analysis vs. human analysis. At the very least, customers and vendors can agree on the value of sentiment analysis when applied to unstructured text, but deciding how and when to use automated vs. human methods continues to be up for discussion.

Language is a complex thing. We would never argue that. In fact, sarcasm, irony and sometimes even just simple misspellings can confuse even the most complex automated sentiment systems, leading it to apply the incorrect sentiment to a piece of text. This is the meat and drink of the proponents of the theory that all sentiment analysis should be done by humans, who will gleefully point to the fact that the machine got the sentiment of a document wrong. However, what they are less likely to point out is the fact that humans get it wrong as well and that unlike an automated system, are affected by external factors, such as going out for a few drinks the night before, or having a disagreement with a co-worker. In fact, anecdotal evidence suggests that two human analysts will only agree with each other approximately 80 percent of the time, so one of them must be wrong (if not both), and this is very close to the accuracy rates that the best machine systems will achieve when applied to a large corpus of documents.

The fact that a machine-based sentiment system can process a large document corpus relatively quickly (three or more documents a second per processor) is a big factor in its appeal. It's also important to realize that for many applications—including online search-based web sites—it's the overall accuracy of a sentiment engine across hundreds or thousands of documents that really matters. Another example of this is can found in financial services where sentiment for an individual stock can be measured to help predict the trading range of that stock; the sentiment of an individual story is unimportant, it's how that stock is trending across all the news that actually matters. In these cases, a machine-based system is better than humans because it can scale up to very large volumes of information.

So, what's the moral of the story? As in most things it's somewhere in the middle. The future is probably a combination of human- and machine-based sentiment. Humans bring something very important to the table that machines are never going to have and that is domain-specific knowledge and experience. For instance, in the world of pharmaceuticals, the sentence "the drug killed the tumor dead" is actually a pretty positive thing. A system that enables the human analysts to import that knowledge into the machine and then lets the machine take over the drudgery of actually processing the documents is surely the best of both worlds.

Mike Marshall is CTO of Lexalytics.

Software Updates, 14 August 2009

Recently announced software updates:

Upcoming Events, 14 August 2009

20 August - BurrellesLuce is presenting a free webinar, Twitter 201: Adding Twitter to your Strategic PR Toolbox, 1:00 PM EDT (GMT -4). The session features Johna Burke and Debbie Friez.

20 August - Cision is presenting a free webinar, Walls Coming Down: How Social Media Breaks Down Barriers and Optimizes Communication, 2:00 PM EDT (GMT -4).

10 September (London) - MeasurementCamp, 10:00 AM.

14–16 October (Portsmouth, NH) - IPR's annual Summit on Measurement

10–12 November (Seville) - 1st International Workshop on Mining Social Media (CFP)

BuzzLogic is no longer offering their SMA platform as a standalone product. The change marks the completion of the company's shift from buzz monitoring to online advertising, where influence analysis supports BuzzLogic's Conversation Ad Targeting platform and network.

Upcoming Events, 7 August 2009

13 August - Filtrbox is presenting a free webinar, Get the most out of our your social media initiatives, 1:00 PM EDT (GMT -4). The session features Ari Newman and Rom 214's James Clark on the basics of social media.

20 August - BurrellesLuce is presenting a free webinar, Twitter 201: Adding Twitter to your Strategic PR Toolbox, 1:00 PM EDT (GMT -4). The session features Johna Burke and Debbie Friez.

10–12 November (Seville) - 1st International Workshop on Mining Social Media (CFP)

New Papers, 4 August 2009

Recently released white papers:

Updates in your inbox

Archives