Like lots of other families over the recent Thanksgiving weekend, we made our way to the movies. Our choice: Life of Pi. We’d highly recommend it, and according to the IBM Social Sentiment Index, as applied to Moviegoer Social Sentiment over the holiday weekend, so too would a lot of other folks. It earned a 90 percent positive rating.

IBM has engaged in the social sentiment index pursuit in some other endeavors – using its advanced analytics and natural language processing technologies to analyze large volumes of social media data, it had another recent take on Black Friday, for example. It tallied up that shoppers expressed positive consumer sentiment on promotions, shipping and convenience as well as the retailers themselves at a three to one ratio (see our story here for other takes on semantic tech weighing in on the holiday shopping season).

It’s also applied its social media analysis smarts to studying births of trends (cycle chic is on the rise), and which tennis player was on the hearts and minds of the crowd at the U.S. Open (Novak Djokovic and Laura Robson winning the love, with positive sentiment scores at 90 percent or better).

Read more

Jolie O’Dell of VentureBeat reports that on Wednesday, “Gnip launched its Historical PowerTrack for Twitter, which will give developers the ability to search, find, analyze, and compare all the tweets ever written, even ones written before the developer in question started scraping Twitter. It’s the same level of access the Library of Congress got when it started archiving and storing all Twitter data, but this time, it’s commercially available. ‘There are a handful of companies that have collected some portion of Twitter data,’ said Gnip COO Chris Moody in a meeting with VentureBeat yesterday. ‘We were able to do it because we partnered with Twitter on it’.” Read more

As the opening ceremony for the London Olympics gets underway tonight, sentiment on the event can be gauged nightly in a big way: The EDF Energy London Eye Ferris Wheel, the largest in Europe, will turn colors depending on the sentiment analysis of tweets coming out of the U.K. mentioning the Olympics.

Sosolimited, an art and technology studio helmed by three MIT grads, has written software to capture these tweets and then uses sentiment analysis algorithms to assess their emotional content. SentiStength, a program that itself hails from the U.K., is reportedly the source of the algorithms. During the day, that will be charted on a large LED next to the London Eye, and each night the data will guide the sequence of a visual lightshow around the Eye.  “That data is played back out across full color architectural lighting fixtures around the Eye and with large ground based search beams,” according to a blog posting from founder Justin Manor. It’s been reported that yellow will be the dominant color to express positive sentiment, while purple will showcase negative sentiment.

Expectations: Early on, at least, probably a lot of yellow, even if traffic is a nightmare, from a lot of outraged Brits who want to have their say over Mitt Romney’s comment about how well-prepared the city is for the Games.

Read more

Enterprises using semantic technology often come up against a problem: Not being able to scale their approaches across domains.

“We hear a lot about semantic approaches that work great when targeted to a domain – for example, you can train up an NLP engine for the hotel industry domain that knows ‘thin’ is a bad word when applied to it,” explained YY Lee, chief operating officer at customer intelligence vendor FirstRain at the recent SemTech conference in San Francisco. “But the amount of the business world to be potentially covered by semantic techniques – that limitation to train for specific domains cannot scale.”

Read more

Our own Jennifer Zaino recently reported that semantic social web application Twitris, a program at Wright State University, was tackling coverage of the Occupy Wall Street movement as well as the presidential election. Now Twitris will be busier than ever: “Wright State University has been assigned a patent for core analysis methods used by the Twitris system.” Read more

Russia’s leading search engine Yandex – which is collaborating with U.S. search engine giants in implementing schema.org and which last week partnered with Twitter to post tweets in real-time in search results – has made another deal this week: It’s working with Topsy Labs to enable social search.

Real-time search and analytics provider Topsy’s indexing and live-ranking will help Yandex search in Russia and Turkey identify and extract fresh and relevant results from social media sources. Vipul Prakash, Topsy’s co-founder and Chief Technology Officer, says Topsy’s corpus consists of about 100 billion tweets, and the page links and media referred to in them, all time-stamped and authorship-explicit. It does some amount of synthetic tagging to extract the topic from the tweet to make the topic searchable, as well as performs classification of content, where there’s more text to play with, for links referenced in tweets. It understands that the author is distinct from what is being discussed and who is referring to whom in postings, which feed into its graph of influence that ranks links in search results based on the influence of people talking about those links. That includes a global rank of a user independent of topic and terms and also keyword-level ranks based on what was in a tweet when they got attention for it.

Because it has such histories of people to extract from that a robust understanding of their network credibility, including how they’ve received attention from others in the past, Topsy does a really good job of getting rid of spam, Prakash says. That’s a particularly useful capability to bring to Yandex to weed out suspicious social tweets in advance of the controversial Russian presidential elections getting underway this weekend, as reports have noted that fake Twitter accounts have been created to drown out opposition voices by flooding Twitter’s hashtag service function. “In Russia there is a lot of precedent for political activism like that,” he says. “If something points out a problem with a candidate, they will have people start spamming it so you can’t actually find the real piece of information.”

Read more

Twitter has sold its old tweets to DataSift, a company that plans to analyze the tweets for marketing purposes. DataSift is the first company to get access to these tweets which go back two years. According to one article, DataSift has “launched a product called DataSift Historics, which lets companies extract insights and trends that relate to brands, businesses, financial markets, news and public opinion, a rep says. DataSift will analyze public tweets, not private ones. If you delete a tweet, it’s deleted from DataSift’s archives.” Read more

IBM and the University of Southern California Annenberg Innovation Lab have joined forces to create a new social media analysis project focused on Major League Baseball’s upcoming World Series: “The USC Annenberg Social Sentiment Index is being compiled by students and relies on IBM Social Analytics technology to analyze millions of tweets in order to assess public social media engagement and opinion from sports and film to retail and fashion.” Read more

Johns Hopkins is using semantic analysis to sift through tweets for information about health trends. According to one article, the effort “gives some clues as to how health marketers, especially, can take advantage of consumer sharing habits to inform key decisions – particularly around media spend, shelf placement, and other choices whose optimal resolution can vary significantly between – and even within – local markets. Researchers at that JHU’s School of Public Health analyzed 2 billion public tweets, from May 2009 to October 2010, to determine whether semantic analysis could unearth meaningful information about public health trends.” Read more

The premise of Ad.ly is to be the Twitter advertising network that matches celebrities with brands. The goal is to drive audience click-through to those brand destinations thanks to the conversations carried on by the stars with their followers. So far it’s racked up some 1,000 celebrities, about 150 brands, and 24,000 celebrity-delivered tweets around brand engagements  – tweets that can generate a lot of interest. As head of engineering Chris Testa explained at SemTech this week, a top celebrity like Kim Kardashian can get some 15,000 clicks on a tweet, vs. about 400 on average for a NY Times or Wall Street Journal tweet. For a brand to really talk to people, he says, “it’s good to have a Kim Kardashian tweet, ‘This is what I am into,’ vs. having an ad in the NY Times.”

Interview with Ad.ly’s Chris Testa:

Read more