Twitter Can Predict Heart Disease, Says Study

Twitter Can Predict Heart Disease, Says Study

Except from this article:

A new study has found that Twitter can predict rates of coronary heart disease better than traditional methods.

…Negative emotional language and topics, such as words like “hate” or expletives, remained strongly correlated with heart disease mortality, even after variables like income and education were taken into account. Positive emotional language showed the opposite correlation, suggesting that optimism and positive experiences, words like “wonderful” or “friends,” may be protective against heart disease.

 …With billions of users writing daily about their daily experiences, thoughts and feelings, the world of social media represents a new frontier for psychological research. Such data could be an invaluable public health tool if able to be tied to real-world outcomes.

Advertisements

Map: What we’re thankful for, according to our Facebook posts

facebook

Excerpt from this article:

We don’t just tell our family what we’re thankful for at the Thanksgiving table anymore. We post our thanks on Facebook, too — and that gives the data analysts at Facebook a trove of data to analyze about what, exactly, we’re grateful for.

Facebook scraped user updates for status updates containing the words “grateful” and “thankful” this past summer, when a few challenges circulated asking users to post about the things they cherished in their lives. And they found, perhaps unsurprisingly, that Facebook users are most thankful for their friends and families.

Intel’s Sharp-Eyed Social Scientist

Excerpt from this article:

Dr. Bell’s title at Intel, the world’s largest producer of semiconductors, is director of user experience research at Intel Labs, the company’s research arm. She runs a skunk works of some 100 social scientists and designers who travel the globe, observing how people use technology in their homes and in public. The team’s findings help inform the company’s product development process, and are also often shared with the laptop makers, automakers and other companies that embed Intel processors in their goods.

Researchers Find That Twitter Can Locate HIV Outbreaks

Excerpt from this article:

Researchers have found that Twitter is a surprisingly useful tool for locating HIV outbreaks. “This study provides the first set of evidence for how real-time social media data might be used for extracting, detecting, and remote monitoring of health-related attitudes and behaviors,” writes the UCLA team. “Results suggest the feasibility of using data from real-time social networking technologies to identify HIV risk-related communications, geographically map the location of those conversations.”

The team mapped over 9,800 tweets with sexual and drug-related themes and found that their locations were a good predictor for established statistics on HIV-prevalence. “Because of the growing amount of social media data, researchers and public health departments will soon be able to build upon these methods to more accurately monitor and detect health behaviors and disease outbreaks.”

Developing a fine-grained look at how digital consumers behave

Excerpt from this article:

Our experience is that within broad consumer movements, small groups of users (often overlooked in cursory analyses) actually drive the economics. Achieving a more refined understanding of who is doing what requires a thoughtful segmentation—incorporating data about consumers’ demographics, household characteristics, usage patterns, spending, attitudes, and needs—supported by “big data” analytics.