Collective Intellect » 2008

Entries Tagged as ''

CI’s tonality algorithm performs linguistic and statistical analysis on each post to determine its overall sentiment

Matt Dickman at Techno//Marketer has recently been posting about how sentiment is determined in online conversations while pointing out the difficulty posed with language and mentions Collective Intellect.

“Part of their analysis is of language within conversations and the sentiment that is displayed there. The sentiment is then tracked over time and can be a key metric in the success of a campaign. Their formula for extracting the sentiment is not publicly accessible so I am not sure how they calculate it.”

His question prompted our own response to explain how we determine sentiment. What follows is our current working approach hot from those that know.

Sentiment = The Collective Intellect tonality algorithm performs linguistic and statistical analysis on each post to determine its overall sentiment (positive, negative, or neutral). The CI algorithm is designed to operate effectively across a broad range of domain areas. The algorithm has been tested on several standard sentiment datasets (such as movie reviews) and consistently performs at a level close to human inter-rater accuracy.

And if you are wondering what human inter-rater accuracy is, here is that definition.

Human inter-rater accuracy (really correlation) is a measure of how well a set of independent raters correlate on rating a test set. For example, for a particular test set, if the sentiment ratings of a set of 4 human raters only correlate at 70% (on average) then that is the best accuracy level any automated system could hope to attain on that test set.

Clearly, there is a lot more to discover here, but that is a good reason why you should stay in touch with the social media strategy and activation experts at Collective Intellect.

Tags: Blog Analysis, Social Media Analytics, Social Media Organization by Michael Conti
1 Comment »

A natural floor for social media tonality certainly exists

Paul Gillin’s recent thought-provoking comments on whether and if a negative sentiment “floor” exists for Dell obscures a larger point - never give up! Using social media tools to further understand the negative sentiment associated with the “floor” helps build a business case (for or against) further marketing strategy and outreach. My response:

—-

A natural floor for social media tonality certainly exists, and no doubt varies by industry topics. However, as an employee for a company whose mission is to both interpret and effect change within the social media arena , I’d be remiss if I didn’t point out that Dell has a unique opportunity to dive deeply into the negative commentary that constitutes the “floor”. Put another way, understanding tonality sets the stage, understanding content provides further opportunity for outreach. If the themes around negative content are inconsistent from month-to-month, a case can be made for a “floor” of constantly churning negative activity that it doesn’t pay to try and influence. However, if the themes emerging from negative social media activity are consistent, and no outreach has been attempted that leverages “the message” of this consistent negativity, the case could be made to further reduce the floor by testing different types of social media outreach. Dell may certainly have recognized this and have attempted the outreach (or decided that an ROI case can’t be made for it) – but it’s worth mentioning!

—–

Collective Insight helps marketers understand the “face” behind the social media buzz and can use that knowledge to connect in a relevant and timely fashion.

Tags: Blog Analysis, Social Media Analytics, Social Media Metrics by Dean Westervelt
No Comments »

CI announces first international agreement with RBC Direct Investing

Collective Intellect, the leading social media analytics company helping businesses track, understand and use social media, today announced the company’s first international agreement with RBC Direct Investing, the brokerage division for the Royal Bank of Canada. Under the terms of the arrangement, the RBC Direct Investing website is hosting a customizable Collective Intellect application that “scrapes” relevant real-time information on customers’ investments from millions of English language blogs and message boards.

Collective Intellect specializes in comprehensively tracking, filtering, ranking, and analyzing social media content for a wide array of businesses. By using advanced artificial intelligence algorithms to identify and analyze social media, Collective Intellect tracks discussions on specific topics and produces reports that shows share of voice and tonal sentiment. Collective Intellect also develops special widgets for companies who want to find instant industry-related blog posts, and measure community sentiment.

“Successful businesses today understand the importance of paying close attention to online conversations,” said Don Springer, Founder and Chief Executive Officer for Collective Intellect. “We’re excited to partner with Canadian-based RBC Direct Investing, the online brokerage firm of internationally recognized financial institution, RBC. RBC Direct Investing recognizes the explosive growth of social networking and how our patent pending technology finds just those nuggets of information that can help their investors make more informed decisions about their trading strategies.”

Said Mr. Doug Coulter, president and CEO, RBC Direct Investing: “We are pleased to include, as part of our latest round of site enhancements, the new Community page supported by Collective Intellect technology. This new feature enables our clients to more easily access sought-after information that will help them make their investment decisions with increasing confidence.”