Sentiment Analysis: ‘A Powerful Tool to Uncover Trends, But Humans Are Still Needed to Dig Below the Surface’
[L to R: Bradley Honan, SVP, StrategyOne; Suresh Vittal, VP and Principal Analyst, Forrester Research; Greg Radner, Global Head of PR Services, Thomson Reuters; Brad McCormick, EVP and Director of Digital, Porter Novelli; Karla Wachter, SVP, Waggener Edstrom Worldwide]
This post was written by Nancy Lazarus, contributor to PRNewser.
At the Sentiment Analysis Symposium in New York on Tuesday, a panel of PR executives weighed the pros and cons of this complex method of evaluating online and social media content.
The panelists agreed that the value of sentiment analysis is enabling the tracking of a wealth of online conversations. However given its limitations they recommended its use in conjunction with other research techniques.
Bradley Honan of StrategyOne summarized the evolution. “We’ve gone from traditional market research to media monitoring to mining data that helps formulate business and communications strategy.”
Karla Wachter of Waggener Edstrom added, “A while ago the ability to track sentiment was limited and we had to guesstimate, but today mountains of data are available. Sentiment analysis is a key part of the toolkit, and it’s a hybrid approach involving both automation and humans.”
Brad McCormick provided a case example of how Porter Novelli used sentiment analysis for one of their clients, who had invested heavily as one of Tiger Woods‘ sponsors. Their client asked the agency to analyze the sentiment associated with the golfer after he became involved in a sex scandal.
McCormick said, “Many tools showed negative sentiment spiking, but our client was reluctant to let it go at that. Around the same time, sympathy for Tiger’s situation started to rise, and this led to the assumption that there could be a comeback. This shift allowed the company to maintain the relationship with Tiger.”
One of the potential drawbacks of sentiment analysis is the level of accuracy, which has widely been estimated to range between 70 to 90 percent. Greg Radner of Thomson Reuters said, “Beyond 80 percent, the law of diminishing returns sets in as it becomes more costly. We also use it to understand the outliers, long term trends and the macro view. As an example, we are now showing sentiment feed tracked against the stock price.”
McCormick echoed that opinion, and said, “One of our tools measures to 90 percent, but we need huge amounts of data to get to that threshold, or 150 conversations per day. One of the only times we were able to do that was for mentions of the Iraq war in the New York Times.”
Another issue is that only part of the audience is being reached through sentiment analysis. Honan said, “We’ve moved beyond the early adopters who are posting online, but we’re still not at 50 percent participation for those who are actively engaged there. What you’re picking up now in online conversations are partisans who are intensely positive or negative, but it’s still important to understand their opinions.
For example, you’re unlikely to go to TripAdvisor to rate your hotel stay last night unless you had an amazing night or were bitten by bedbugs. If sentiment analysis was your stand-alone tool you’d miss key parts of your brand’s audience.”
The panelists forecast sentiment analysis evolving to other areas in the future.
Radner sees the method “Heading holistically across the investor relations space to include online analyst reports and transcripts.”
McCormick would also like to see call center and customer service information included in the data that is analyzed.
They would all like to solve the difficult challenge of applying the method internationally. As Wachter said, “Global sentiment analysis is a pain point from a business perspective. Online conversations are happening in every part of the world and our ability to capture them is critical.”