Studies Link Social Media Data with Personality and Health Indicators

twitter-292994_1280[This post was originally uploaded on January 27, 2015. It has been updated below with new information on March 20, 2015 and February 26, 2018.]

Reports of two new studies were issued recently describing meaningful connections between the predictive value of Facebook Likes and personality types, and next the parsing of language in Tweets to forecast the likelihood of heart disease. This presents us with an opportunity to examine two highly similar human health indicators that were identified by sophisticated analytics applied to massive troves of data generated by two of the world’s leading social media platforms. Where is all of this leading and what issues arise as a result? I will first summarize some parts of these two reports, add some links and annotations, and then pose some questions. I also highly recommend clicking through for a full read of both of pieces.

The first report was posted on NewScientist.com on January 12, 2015 with the concise title of What You ‘Like’ on Facebook Gives Away Your Personality by Hal Hodson. According to this article, researchers working at Stanford University and Cambridge University have developed an algorithm that, based completely upon what people “Like” on Facebook, can be determinative of a user’s personality. The data for this was gathered in a survey of 86,000 people who filled out personality questionnaires that were then matched against their activity on Facebook. Indeed, the results showed that this new method was more accurate than the determinations of the test subjects’ family and friends.

These characteristics are called the Big Five personality traits and include (as explored in detail in the preceding Wikipedia link):

  • Openness to experience
  • Conscientiousness
  • Extraversion
  • Agreeableness
  • Neuroticism

The article includes comments from David Funder of the University of California, Riverside, who is a researcher on personality, that while this study is “impressive”, it still does not provide a truly deep understanding of an individual’s personality. Funder’s work looks at 100 dimensions, a far larger number than the researchers in the Facebook study who focused upon the Big Five.

Nonetheless, two of these researchers on this new study, Youyou Wu  of Cambridge and Michael Kosinski of Stanford, believe their work is applicable on a global scale and applied in several areas. For instance,  they foresee their new Like algorithm could be used to in hiring operations to search large data files of candidates and identify those who might be most suitable for a particular job. Other possibilities include health and education. Kosinski also acknowledges that this approach would further require appropriate policy and technology considerations in order to address issues such its potential invasiveness.

(In a similar application Facebook Likes and other data from social media sites, universities in the US are now using such information and analytics to locate and pitch to alumni as potential donors as reported in a most interesting article in the January 25, 2015 edition of The New York Times entitled Your College May Be Banking on Your Facebook Likes, by Natasha Singer. Among other things, this story reports on the work and methods of two startups in this area called EverTrue and Graduway.)

The second report linking social media data to a health indicator was Scientists Say Tweets Predict Heart Disease and Community Health by Derrick Harris posted on Gigaom.com on January 22, 2015. In a study authored by researchers at the University of Pennsylvania, as part of their Well-Being Project, entitled Psychological Language on Twitter Predicts County-Level Heart Disease Mortality, they concluded that the vocabulary use by individuals in their Tweets can  predict “the rate of heart disease deaths in the counties where they live”. This phenomenon manifests itself by showing that Tweets concerning more upbeat topics and expressed in more positive terms correlated with lower mortality rates when compared to rates reported by the Center for Disease Control (CDC). Conversely, mortality rates were higher in areas “with angry language about negative topics”.

The accompanying side-by-said graphics of the Twitter data and the CDC data covering the upper right quarter of the US states and their constituent 1,300 counties, dramatically illustrates these findings. The pool of data was drawn from 148 million Tweets with geotags.

These results also provide further support for the accuracy and predictive validity of data from Twitter, notwithstanding any “inherent geographical biases”, and exceeding that of more “traditional polls or surveys”. Indeed, language in Tweets turns out to have a comparatively higher predictive value than other economic or health-related data. The researchers further believe that their findings might be more helpful when applied to “community-scale policies or interventions” rather than to assisting specific people.

My follow-up questions include:

  • Would mapping a statistically significant number of Twitter networks in counties with higher and/or lower mortality rates, a process described in the February 5, 2015 Subway Fold post entitled Visualization, Interpretation and Inspiration from Mapping Twitter Networks, provide additional insights that would be helpful to medical professionals and local policy planners? For example, are many of the negative Twitter posters in each other’s networks such that they become self-reinforcing? Are there recognizable network effects occurring that can somehow be corrected with regards to the degree of negativity and, in turn, public health? Would this pose any legal, policy or privacy issues?
  • For both of these articles, do these types of findings require more rigorous and wider-scale mathematical and scientific analysis before applying them to such critically important mental and physical health matters? If so, should such testing be done by public or private institutions, universities and/or the government agencies?
  • As first expressed in this November 22, 2014 Subway Fold post entitled Minting New Big Data Types and Analytics for Investors, how are the differences in correlation and causation being factored into these studies? Given the skepticism expressed above about Facebook Likes being so indicative about personality, are there other effects and influences that need to be identified and filtered out of these types of conclusions?
  • If the usage and analysis of social media data continues to grow in areas, well, like employment, education and health, what protections, if any, should people be given, by law and/or the social media companies, to protect themselves or opt out in advance of any potentially negative consequences?

March 20, 2015 Update:

Providing some very worthwhile additional insight and analysis of the University of Pennsylvania study covered in the initial post above, Maria Konnikova has written a very engaging article entitled What Your Tweets Say About You that was posted on The New Yorker website on March 17, 2015. I highly recommend clicking through and reading the entire text. I will sum up just some of the key points, add some links and pose several  additional questions.

The research study (linked to above), was conducted by a team led by psychologist and Professor Johannes Eichstaedt. Their main conclusion was that the collection and subsequent linguistic analysis of tweets proved to be validly predictive of locations with higher concentrations of fatalities from cardiovascular disease. The inverse was also true that geographic clusters of tweets with more positive content had lower death rates from the same cause. It was not that the population tweeting had heart disease, but rather, there is a discernible correlation between angrier content and a higher incidence of the heart disease within an area.

This “correlation is especially strange” due to the fact that Twitter users are generally younger that individuals who perish from heart ailments. Citing a January 9, 2015 study from the Pew Research Center entitled Demographics of Key Social Networking Platforms (also, imho, well worth a click-through and full reading), which, among other things tabulates the ages of the users of all of the leading social media platforms. Just 22% of US Twitter users are more than 50 years old. However, the relative risk of heart disease does not begin to rise until decades later.

How, then, to analytically connect younger people in a particular area who are posting negative tweets with their older neighbors who face higher chances of developing heart disease? The researchers theorize that the tweets “may be a window into the aggregated and powerful effects if the community context”. The overall health of people living in a particular area that is “poorer, more fragmented” and not as healthy as those residing in “richer, integrated ones”. As a result, the angrier tweets of someone in their twenties are likely reflective of an area with higher life stressors that, in turn, later result in more heart-related deaths.

Nonetheless, another renowned expert in this field of linguistic analysis of text, James Pennebaker, recommended caution in drawing any connection based upon this data. He urges further study of the data and posing additional questions about causation. Currently, in his own work, he is examining Twitter data to see how family and religious factors evolve.

There is also value in studying social media content of individuals. For example, Microsoft has previously studied 70,000 tweets of people with depression and then used this data to construct a “predictive index” to identify “other users who were likely depressed based on their social-media posts”.

Eisenstaedt’s team is continuing their work by looking at Twitter data for individuals and communities over time periods, rather than a “snapshot” data set. They are also adding Facebook profiles to their work.

Finally, Pennebaker believes that social media may also generate positive effects on mental health based on his previous studies on the benefits of keeping a personal journal. This may be so despite the private nature of a journal and the very public access of social media and its interactivity.

My additional questions are as follows:

  • Will additional discreet language patterns be discovered and validated that will indicate concentrations of other medical conditions within communities? Are we only at the beginning of using textual analysis of tweets as a metric of the states of local health?
  • Given that there is a lag time of years between negative tweets and the appearance of heart disease, should interventions be undertaken within a community at higher risk and, if so, by whom and at what cost?
  • Are other negative online behaviors such as cyberbullying indicative of some form of identifiable illness that can be treated on a community-wide basis or must this be dealt with on an individual in a case-by-case manner?

February 26, 2018 Update: Using social media activity data to diagnose and treat possible health conditions has advanced in a number of new systems and studies as reported in today’s New York Times in an article entitled How Companies Scour Our Digital Lives for Clues to Our Health, by Natasha Singer, dated February 26, 2018. 

The Advent of Social TV: Commercial and Creative Impacts of Using Twitter Activity Metrics Upon What Audiences Now See

Image by Arti Dandhu

“Sensory Overload”, Image by Arti Sandhu

[This post was originally uploaded on July 31, 2014. It has been updated below with new information on December 19, 2015 and then on March 11, 2015.]

July 14, 2014 Post:

Nielsen is a long-established and industry leading firm in measuring, analyzing and reporting upon media deployment, usage and audiences. Their services also include a similar range of sophisticated services concerning consumer behavior and products.

A fascinating new report appeared on their sites Newswire section on June 2, 2014 entitled This TV Season’s Biggest Moments on Twitter that chronologically mapped which US TV shows from September 2013 through May 2014 generated the greatest volume of traffics and postings on Twitter. The categories included:

  • Greatest Reach
  • Most Tweets
  • Greatest Activity and Reach
  • Most Impressions
  • Most Tweets Per Unique
  • Most Tweets and Tweets Per Minute

Each of these data points is clearly explained and includes the names of the shows, their corresponding data generated by these massive amounts of Twitter activity, and the hashtags and handles involved. In a single screen, this data visualization is a terrific example of how to present so much information that is belied by its elegant and informative design.

Moreover, the value of this data must be highly significant in a multitude of ways to, among others, advertisers, entertainment companies, media planners and producers, content strategists and marketers, and demographers in assessing their respective audiences and clients.

December 19, 2014 Update:

For me, the best story told on TV during the 2014 season was – – in a fictional world where “brains” take on an entirely different significance – –  The Walking Dead on AMC in terms of the extraordinary number of tweets about ongoing adventures Sheriff Ricky and the Grimes Gang. This was covered on Nielsen.com on December 15, 2014 in a post entitled Tops of 2014: Social TV.  TWD averaged twice as many tweets as its next competitor in the ongoing series category. As I read scores of TWD tweets on the mid-season finale myself, everyone will miss you, Beth.

March 11, 2015 Update:

We are now experiencing the emergence of what is being called Social TV, a phenomenon where Twitter and other social media traffic and sentiment data and metrics are exerting significant influences upon on-air advertising campaigns, audience perceptions and creative choices. Just to cite another example of this is the contemporaneous two-screen experience audiences can now join on shows such as The Walking Dead.

Scientific support for the relevancy, accuracy and scalability of Twitter data and metrics on individual TV shows continues to grow. Persuasive new evidence was released on March 9, 2015, in a report authored by Nielsen entitled Social TV: A Bellwether for TV Audience Engagement. An informative article on this report was also published in yesterday’s edition of The New York Times entitled Social Study of TV Viewers Backs Twitter’s Claims to Be Barometer of Public Mood by Vindu Goel. I will sum up, annotate and comment on this article and supplement this with a look at the Nielsen report itself. I very highly recommend clicking through and reading both of them in their entirety.

Nielsen used 300 people in a study of their brain activity while they watched eight selected shows in an effort to find the level of correlation to their volume of tweets about the same content. The results showed a significantly close correlation. The Nielsen report contains a concise graph of the data that  visually  charts this point at 79.5%.*

As a result, researchers can now accurately assess the level of a particular show’s “depth of engagement” of its audience with the events as they unfolds on the small screen. Moreover, this is not only for the show itself, but on a more granular level on a scene-by-scene basis. Thus, this study and report reaffirms Twitter’s assertions that its data accurately represents its platform’s real-time engagement of its users in real-time during a show’s broadcast, as well as a show’s “popularity”.

Most importantly, this data and its interpretations can be used to sell ads to advertisers looking to best maximize their expenditures in their efforts to most effectively reach the audiences they are seeking for their  services and products.

Twitter data and metrics can also be used for predicting potential audiences for new shows even before they premiere, according to a report Nielsen released on January 15, 2015 entitled Must See TV: How Twitter Activity Ahead of Fall Season Premieres Could Indicate Success.

Nonetheless, neither Nielsen nor Twitter have addressed the key issue of the degree to which the volume of Twitter traffic actually increase the size of the viewing audience.

Nielson is planning another study to evaluate the impact of Twitter activity concerning TV ads upon the audiences who view them. (Might I suggest starting with this current TV ad about Mountain Dew Kickstart that has been viewed nearly 6.5 million times on YouTube and makes me laugh out loud every time I see it!)

_________________________________

*   Issues concerning the distinctions between correlation and causation were raised in two recent Subway Fold posts on November 27, 2014 entitled Minting New Big Data Types and Analytics for Investors and then on January 27, 2015 in a post entitled Studies Link Social Media Data with Personality and Health Indicators.

Does Being on Law Review or Effective Blogging and Networking Provide Law Students with Better Employment Prospects?

12239536886_856aa1cdc4_m

Image by Marcela Palma

[This post was originally uploaded on November 12, 2014. It has been updated below with new information on March 5, 2015.]

Oceans of ink and an unlimited quantum of bits have been expended in the past several years reporting, analyzing and commenting upon the fundamental changes to the legal profession in the US following the recent Great Recession. Among many other things, there has been a significant drop in the number of applicants to many law schools and a declining number of available jobs law students upon their graduation. This is a very complex situation with no easy answers for the law schools and their students.

It is traditional practice at most US law schools for students who finish in the top 10% of their class rankings based upon their grades, to be invited to join the school’s law review. This is always considered to be a significant accomplishment and an academic honor. The member of the law review (also called the “law journal”), write in-depth and heavily annotated legal analyses about developments in the law and concerning specific decisions.

Despite the “New Normal” ¹ in today’s legal marketplace, any law student who is on the law review and/or in the top 10% of their class, will find themselves in a buyer’s market for their academic and writing distinctions. Nonetheless, what can – – what we used to be called the “top 90%” when I went to law school – – do to improve their marketability in such a difficult market?

They can blog, network and build their online presence according to a most interesting post by attorney, legal marketing expert, and renowned legal blogger Kevin O’Keefe in a post entitled Law Blog More Valuable Than Law Review in Landing Job on November 5, 2014 on his blog Real Lawyers Have Blogs. To briefly recap, he describes how Patrick Ellis (@pmellis), while attending Michigan State University College of Law, used his blog and networking skills to eventually land a job as an associate attorney with a top law firm in Detroit. I highly recommend clicking through and reading O’Keefe’s informative and inspiring story about Mr. Ellis.

This post also asserts that such blogging presented opportunities that would have otherwise been foreclosed to Mr. Ellis. Moreover, that the traditional entre afforded by law review as well as moot court participation and “who you know”, have now been surpassed by the effective of using blogs and networking to find jobs in today’s challenging environment. Indeed, as O’Keefe so concisely states “… networking online requires law students to listen, engage, curate and create content with their own point of view.” Bravo and kudos to both O’Keefe for writing about this and Ellis for implementing this innovative legal  job search strategy.

Is effective blogging and networking now an equivalent, if not advantage, over being a member of the law review? Well, as many lawyers are often inclined to initially reply to some questions, I believe it depends. What about these scenarios:

  • Law student X is invited for a recruiting interview at the ABC Law Firm. If he is both on law review and has a strong online presence, nowadays which one more likely got him the interview or was it both?
  • Law Student X is on law review while Law Student Y has a terrific blog and network. Will ABC only invite X or Y, or both based on the candidates’ merits?
  • ABC recognizes that they are lagging in their own online presence and marketing skills. Will they invite X and/or Y for interviews and why? Should the interview for X and Y be different and, if so how?
  • Should alternative career paths be developed by ABC for X and Y? Should both tracks be towards eventual partnership consideration?
  • If X and Y are both hired, should Y expressly help Y in building his or her online presence in some form of buddy system?
  • Will X’s and Y’s skills be differently evaluated in performance reviews? How will this possibly affect ABC’s compensation and bonus structure for associates?

Finally, I additionally suggestion that law students engaged in a search should consider applying some personal network mapping software to identify the people who are “hubs” and “spokes” in your network. The hubs are those members with the highest degrees of connectedness and might thus turn out to be more helpful resources. (see also The Subway Fold posts on February 5, 2015 about mapping Twitter networks and this one April 10, 2014 on mapping LinkedIn networks.²) A Google search on these applications will produce many possibilities.

___________________________
1.  See this excellent ongoing column of the same name on the ABA Journal’s web site covering a multitude of important topics on this tectonic technological, professional and economics shifts.

2.   LinkedIn has recently removed their networking mapping tool.

March 5, 2015 Update:

Following up on Kevin O’Keefe’s very informative post discussed above, he published another enlightening blog post squarely on point for this topic entitled Emory Law School Gets Students Blogging Early with Innovative New Class on February 12,, 2015. This spotlights Professor Jennifer Murphy Romig’s new class on legal blogging at Emory University School of Law. I will again briefly summarize, annotate and comment upon Mr. O’Keefe’s interview with her. I highly recommend clicking through and reading it in its entirety for all its details and insights.

Besides my own very strong interest and involvement in the efforts of law schools to provide their students with the latest business skills, this immediate got my attention because I am a proud alumnus of Emory Law.

Professor Romig’s new course is called Advanced Legal Writing: Blogging and Social Media. It’s listed as Course 851 on the right-hand side of the law school’s Course Descriptions page under Spring 2015 Courses. (Please click on the link for a full description.) The interview with her covered the following topics:

  • Origin:  The administration was supportive of the original proposal, looking to expand student’ skills in “public legal writing”, as distinguished from other traditional first year legal writing for client/matter-specific work. The professor had previously launched her own blog called Listen Like a Lawyer that turned into a very positive experience for her to communicate and network within the legal community. As a result, she sought to bring blogging skills to law students for use in the workplace and to “build marketable skills”.
  • Value: During their job searches, law students will, in all sizes of firms, find potential employers with blogs or else those who might be interested in launching one. Thus, if asked to do so, they will then have the skills to write, post offer strategy on blogs. As well, it provides students with a “creative outlet” where they can choose their own topics.
  • Curriculum: This is divided into thirds including 1. The “ethics”,  “history” and “methods of blogging”. 2. Studying blog writing to present their “legal analysis” and “voice and style”. As well, they will work in groups to revise a WordPress* theme and explain their changes, and give presentations on other topics involving formatting and content. 3.  Creating and critiquing their own WordPress blogs which, at their option, can be used to present their blogging skills to potential employers. Distinguished guests from the world of legal blogging will also be participating.
  • Results: The benefits of effective blogging include improved writing skills in practice and online, as well as the generation of interactivity on other social platforms and personal networking. The trends include introducing students to “different styles” of lawyers’ usage of social media platforms, and providing them with the means to track and adapt to the latest trends in social media.
  • Recommendations: 1. Begin on a small and secure legal blog among a “supportive community”. 2. Use blogging as  an “opportunity to be creative” where students can test out formats and functions. 3.  Find issues that are important to each blogger to pursue in their writing.

I am very grateful to Professor Romig for all of her work in launching this course at Emory Law. I was indeed even more proud of my alma mater after reading about this.

I want to suggest these additional suggestions:

  • Following up and showcasing among students those instances where their blogging has had an impact upon their job searches, legal matters, social movement initiatives, and networking. I would gather these instances and analyses into a report full of embedded inks, to be shared with fellow students and the administration. Perhaps some form of meta-blog where students can post and actively discuss their blogging experiences and techniques.
  • Using the blogging course as a recruiting tool for potential law students. Consider making this an expressed advantage of Emory Law in that the school will provide and enable students with the most modern tools they will need to communicate, market and practice law.
  • Encourage live-blogging of events and presentations at the school in order to open another new media channel to publicize them as well as to refine contemporaneous blogging skills. Again, collecting and archiving these blog posts might be worthwhile on the school’s website.
  • Has Emory Law ever considered holding a legal hackathon? It might also bring in some positive support from the local legal community and be a worthwhile event to live-blog and webcast.

___________________________

*  WordPress is the hosting service used for The Subway Fold.

2015 Super Bowl TV Advertisers are Evaluating the Data Generated from Their Twitter Hashtags

Image by Ken Varnum

Image by Ken Varnum

A remarkable moment in modern advertizing occurred during the 2013 Super Bowl when the power temporarily went out at the Superdome stadium in New Orleans. Oreo cookies quickly put out a tweet with an accompanying photo that read “Power Out? No problem. You can still dunk in the dark.” It has since been widely heralded as a spontaneous stroke of genius and proved to be incredibly effective across the Twitter-verse. The story of how this happened, including the actual tweet and graphic, were told in a concise report on CNET.com entitled  How Oreo’s Brilliant Blackout Tweet Won the Super Bowl by Daniel Terdiman on February 3, 2013. The story was widely reported elsewhere in traditional and social media venues.

Two years later, the 2015 Super Bowl itself ended in incredible drama. Neither any sports writer nor the NFL itself could have scripted a more improbable ending. Discussions of the final minute of the game broke out instantly across social and traditional and will likely continue on for years afterwards.

In addition to the hard lessons learned here about football strategy, about half of the sponsors of the game have also gained valuable troves of insightful data and the resulting analytics from the Twitter hashtags they included in their TV commercials. A very interesting and instructive report on this process was posted on SocialMediaToday.com on February 15, 2015, entitled How Advertisers Are Tracking Their Ad Dollars Using Hashtags: Lessons from the Super Bowl, by Tukan Das. I will recap, add some links, and commentary to this article. I suggest clicking through and reading it in its entirety for its detail and helpfulness. This story also tracks well with two other Subway Fold posts about the applications of Twitter data and analytics to  marketing and business development entitled New Analytical Twitter Traffic Report on US TV Shows During the 2013 – 2014 Season (July 31, 2014), and then Is Big Data Calling and Calculating the Tune in Today’s Global Music Market? (December 10, 2014).

For additional information on this topic, I recommend an earlier article entitled Half of Super Bowl Ads Had Hashtags by David Goldman was posted on CNN.com on February 2, 2015.  It contains an itemized list of all of the hashtags that were used. As well, just two days prior to the game, an article on AdWeek.com entitled Infographic: Will Super Bowl Advertisers Put Hashtags and Facebook URLs in Their Spots? on January 29, 2015 by Christopher Heine. The infographic it presents by StarStar, a mobile services company, depicts what value and audience reach advertisers get in return for purchasing a 30-second Super Bowl ad for $4 million. (See also the January 30, 2015 Subway Fold post entitled Timely Resources for Studying and Producing Infographics.)

According to the report on SocialMediaToday.com, the virtual “water cooler discussions” that occurred on Twitter around the advertisers’ hashtags embedded in their TV ads showed that users are now employing multiple screens to experience the game (the television screen and then at least one other computing device’s screen). These additional screens can be used to track and analyze the value per ad dollars spent while the advertisers evaluate their social media data in real-time rather than traditionally having to wait for TV viewing data to arrive. By further adding specialized demographic data into the mix, the advertisers can thus more deeply assess their data, scaling from in the aggregate level all the way down to the individual level. This gives advertisers the opportunity to observe and assess individuals “interacting with their brand” and pinpoint the “influencers” on Twitter among them. Furthermore, they can overlay an additional layer of data onto their contemporaneous hashtag analyses by using prior Twitter exchanges involving their audience in an effort to illuminate “brand affinity, preferences, and attitude changes over time”.

My questions are as follows:

  • What calculations and considerations are used when advertisers select their hashtags for advertising on TV and other media? Does Brand X use one hashtag for a certain media platform and/or audience than they do for another? Does Brand Y in the same market sector use a similar or different approach?
  • How, if at all, do geographic factors affect the choice of advertising hashtags? Will viewers and readers from one area of the US respond differently than another area to the same hashtag? Is there any difference in hashtag strategy from country to country or does the global nature of TV and the social media eliminate such considerations?
  • If a particular hashtag worked well for 2015’s Super Bowl, should it automatically be re-used for next year’s game or should marketing and content strategists re-evaluate their hashtag formulation and selection process?
  • Are advertising hashtags usually devised by a company’s internal marketing and analytics staff members or do they more often engage outside consultants for assistance with this?

 

 

 

Visualization, Interpretation and Inspiration from Mapping Twitter Networks

6871711979_bbe5b1ae1f_z

Image by Marc Smith

[This post was originally uploaded on September 26, 2014. It has been updated below with new information on February 5, 2015.]

Have you ever wondered what a visual map of your Twitter network might look like? The realization of such Twitter topography was covered in a terrific post on September 24, 2014 on socialmediatoday.com entitled How to Create a Visual Map of Your Twitter Network by Mary Ellen Egan.

To briefly sum up, at the recent Social Shake-Up Conference in Atlanta sponsored by SocialMediaToday, the Social Research Foundation created and presented such a map. They generated it by including 513 Twitter users who participated for four days in the hashtag #socialshakeup. The platform used is called NodeXL. The resulting graphic of the results as shown in this article are extraordinary. Please pay particular attention as to how the “influencers” in this network are identified and their characteristics. I strongly urge you to click through to read this article and see this display.

For an additional deep dive and comprehensive study on Twitter network mapping mechanics, analyses and policy implications accompanied by numerous examples of how Twitter networks form, grow, transform and behave, I also very highly recommend a report posted on February 20, 2014, entitled Mapping Twitter Topic Networks: From Polarized Crowds to Community Clusters by Marc A. Smith, Lee Rainie, Ben Shneiderman and Itai Himelboim for the Pew Foundation Internet Project.

I believe this article and report will quite likely spark your imagination. I think it is safe to assume that many users would be intrigued by this capability and, moreover, would devise new and innovative ways to leverage the data to better understand, grow and plot strategy to enhance their Twitter networks. Some questions I propose for such an analysis while inspecting a Twitter map include:

  • Am I reaching my target audience? Is this map reliable as a sole indicator or should others be used?
  • Who are the key influencers in my network? Once identified, can it be determined why they are influencers?
  • Does my growth strategy depend on promoting retweets, growing the population of followers, getting mentioned in relevant publications and websites, or other possible approaches?

What I would really be like to see emerge is a 3-dimensional form of visual map that fully integrates multiple maps of an  individual’s or group’s or company’s online presence to simultaneously include their Twitter, Facebook, LinkedIn¹, Instagram and other social networks. Maybe a platform like the Hyve-3D visualization system² could be used to enable a more broadly extensible and scalable 3D view. Perhaps this multi-dimensional virtual construct could produce entirely new planning and insights for optimizing one’s presence, marketing and influence in social media.

If so, would new trends and influencers not previously seen then be identified? Could tools be developed in this system whereby users would test the strengths and weaknesses of certain cross-social media platforms links and relationships? Would certain industries such news networks³ be able to spot events and trends much sooner? Are there any potentially new opportunities here for entrepreneurs?

February 5, 2015 Update:

A very instructive and illuminating example of the power of mapping a specialized Twitter network has just been posted by Ryan Whelan, a law and doctoral student at Northwestern University. It is composed of US law school professors who are now actively Tweeting away. He posted his methodology, an interactive graphic of this network, and one supporting graph plus four data tables on his blog in a February 3, 2015 post entitled The Law Prof Twitter Network 2.0. I highly recommend clicking through and reading this in its entirety. Try clicking on the graphic to activate a set of tools to explore and query this network map. As well, the tables illustrate the relative sensitivities of the data and their impact on the graphic when particular members of the network or the origins and groupings of the followers is examined.

I think you find it inspiring in thinking about what situations such a network map might be helpful to you in work, school, special interest groups, and many other potential applications. Mr. Whelan presents plenty of information to get you started off in the right direction.

I also found the look and feel of the network map to be very similar to the network mapping tool that was previously available on LinkedIn and discussed in the August 14, 2014 Subway Fold post entitled 2014 LinkedIn Usage Trends and Additional Data Questions.

My questions are as follows:

  • What effects, if any, is this network and its structure having upon improving the legal education system? That is, are these professors, by being active on Twitter in their own handle and as members of this network as followers of each other, benefiting the professor’s work and/or law students’ classroom and learning experiences?
  • Are the characteristics of this network of legal academics any different from, let’s say, a Twitter network of medical school professors or high school teachers?
  • Would more of a meta-study of networks within the legal profession produce results that would be helpful to lawyers and their clients? For example, what would Twitter maps of corporate lawyers, litigators and public interest attorneys show that might be helpful and to whom?

___________________________
1.  See the April 10, 2014 Subway Fold post entitled Visualization Tool for LinkedIn Personal Networks.

2 See the August 28, 2014 Subway Fold post entitled Hyve-3D: A New 3D Immersive and Collaborative Design System

3.   See also a most interesting article published in the September 23, 2014 edition of The New York Times entitled Tool Called Dataminr Hunts for News in the Din of Twitter by Leslie Kaufman about such a system that is scanning and interpolating possible news emerging from the Twitter-sphere.

Updates on Recent Posts Re: Music’s Big Data, Deep Learning, VR Movies, Regular Movies’ Effects on Our Brains, Storytelling and, of Course, Zombies

This week has seen the publication of an exciting series of news stories and commentaries that provide a very timely opportunity to update six recent Subway Fold posts. The common thread running through the original posts and these new pieces is the highly inventive mixing, mutating and monetizing of pop culture and science. Please put on your virtual 3-D glasses let’s see what’s out there.

The December 10, 2014 Subway Fold post entitled Is Big Data Calling and Calculating the Tune in Today’s Global Music Market? explored the apps, companies and trends that have become the key drivers in the current global music business. Adding to the big data strategies and implementations for three more major music companies and their rosters of artists was a very informative report in the December 15, 2014 edition of The Wall Street Journal by Hannah Karp entitled Music Business Plays to Big Data’s Beat. (A subscription for the full text required a subscription to WSJonline.com, but the story also appeared in full on Nasdaq.com clickable here.) As described in detail in this report, Universal Music, Warner Music, and Sony Music have all created sophisticated systems to parse numerous data sources and apply customized analytics for planning and executing marketing campaigns.

Next for an alternative and somewhat retro approach, a veteran music retailer named Sal Nunziato wrote a piece on the Op Ed page of The New York Times on the very same day entitled Elegy for the ‘Suits’. He blamed the Internet more than the music labels for the current state of music where “anyone with a computer, a kazoo and an untuned guitar” can release their music  online regardless of its quality. Thus, the ‘suits’ he nostalgically misses were the music company execs who exerted  more controlled upon the quantity and quality of music available to the public.

Likewise covering the tuning up of another major force in today’s online music streaming industry was an August 14, 2014 Subway Fold post entitled Spotify Enhances Playlist Recommendations Processing with “Deep Learning” Technology. This summarized a report about how deep learning technology was being successfully applied to improve the accuracy and responsiveness of Spotify’s recommendation engine. Presenting an even stronger case that you-ain’t-seen-nothing-yet in this field was an engaging analysis of some still largely unseen developments in deep learning posted on December 15, 2014, on Gigaom.com entitled What We Read About Deep Learning is Just the Tip of the Iceberg by Derrick Harris. These include experimental systems being tested by the likes of Google, Facebook and Microsoft. As well, there were a series of intriguing presentations and demos at the recent Neural Information Processing Systems conference held in Montreal. As detailed here with a wealth of supporting links, many of these advanced systems and methods are expected to gain more press and publicity in 2015.

Returning to the here and now at end of 2014, the current release of the movie adaptation of the novel Wild by Cheryl Strayed (Knopf, 2011), has been further formatted into 3-minute supplemental virtual reality movie as reported in the December 15, 2014 edition of The New York Times by Michael Cieply in an article entitled Virtual Reality ‘Wild’ Trek. This fits right in with the developments covered in the December 10, 2014 Subway Fold post entitled A Full Slate of Virtual Reality Movies and Experiences Scheduled at the 2015 Sundance Film Festival as this short film is also scheduled to be presented at the 2015 Sundance festival. Using Oculus and Samsung VR technology, this is an immersive meeting with the lead character, played by actress Reese Witherspoon, while she is hiking in the wilderness. She is quoted as being very pleased with the final results of this VR production.

The next set of analyses and enhancements to our cinematic experience, continuing right along with the September 3, 2014 Subway Fold post entitled Applying MRI Technology to Determine the Effects of Movies and Music on Our Brains, concerns a newly published book that explains the science of how movies affect our brains entitled Flicker: Your Brain on Movies (Oxford University Press, 2014), by Dr. Jeffrey Zacks. The author was interviewed during a fascinating segment of the December 18, 2014 broadcast of The Brian Lehrer Show on WYNC radio. Among other things, he spoke about why audiences cry during movies (even when the films are not very good), sometimes root for the villain, and move to duck out of the way when an object on the screen seems to be coming right at them such as the giant bolder rolling after Indiana Jones at the start of Raiders of the Lost Ark. Much of this is intentionally done by the filmmakers to manipulate audiences into heightened emotional responses to key events as they unfold on the big screen.

Of course, all movie making involves the art and science of storytelling skills as discussed in the November 4, 2014 Subway Fold post entitled Say, Did You Hear the Story About the Science and Benefits of Being an Effective Storyteller?. In a very practical and insightful article in the December 12, 2014 edition of The New York Times by Alina Tugend entitled Storytelling Your Way to a Better Job or a Stronger Start-Up there are some helpful applications for today’s marketplace. As concisely stated in this piece “You need to have a good story.” It describes in detail how there are now consultants, charging meaningful fees, with new approaches and techniques who assist people in improving their skills in order to become more persuasive storytellers. Among others interviewed for this story was Dr. Paul J. Zak, who wrote the recent article on The Harvard Business Review Blog which was the basis for the November 4th Subway Fold post. It concludes with five helpful pointers to spin a compelling yarn for your listeners.

Finally, the best story told on TV during the 2014 season was – – in a fictional world where brains take on an entirely different significance – –  The Walking Dead on AMC in terms of the extraordinary number of tweets about ongoing adventures Sheriff Rick and the Grimes Gang. This was covered on Nielsen.com on December 15, 2014 in a post entitled Tops of 2014: Social TV.  TWD averaged twice as many tweets as its next competitor in the ongoing series category. This follows up directly with the July 31, 2014 Subway Fold post entitled New Analytical Twitter Traffic Report on US TV Shows During the 2013 – 2014 Season.  As I read scores of TWD tweets on the mid-season finale myself, everyone will miss you, Beth.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

As a major fan of TWD, I would like to take the opportunity add my own brief review about the tragic events in Episode 5.8:

I think that in the end, Beth was a form of avatar for the entire show. She traveled many miles from lying on her bed in Season 2 completely unable to function and progressing to Season 5 as a realist concerning herself and the group’s survival. Rather than resigning herself to be held a captive ward in the hospital, she was determined to escape no matter what and was so proud of helping Jonah to escape.

She awakened and arose to be a survivor and a committed member of the Grimes Gang, just as everyone else has done during the past five years. That is, Beth’s journey reflects the entire group’s journey. She, and the Grimes Gang, up to this point have survived all of the threats they faced and endured all of the horrors they have seen. They will all survive but this death with have more serious repercussions than perhaps any other death up until this point. Maggie, Daryl, Rick, Carol and Carl, the core of the GG, will not soon recover from this.

What I still do not understand is why, given that she was finally free in the hospital’s hallway, did she jeopardize her life by going after the lead officer with a scissors. It seemed to be somewhat at odds with Beth’s character as someone who had survived until now on her own determination and close bond with the group. She had nothing to gain by such a reckless act in the middle of a very volatile situation. Was it a sacrifice to save Jonah? Did she realize that the cop was holding a gun at that point? Was she just overtaken by the motivation that desperate times sometimes call for desperate measures?

Consider, too, that she was Herschel’s daughter and her character reflected what she had learned from him: 1. Both learned to see things differently and adapted when the circumstances changed. 2. Both faced sacrifices and danger with great dignity. (Recall Herschel’s acknowledging grin towards Rick right before the Governor murdered the elder of the survivors, and then Beth’s defiant grin when she saw that Jonah had escaped.) 3. Both were resilient insofar as Herschel adapting to the loss of his leg and Beth recovering from her father’s murder. 4. Both sought to comfort others as Herschel stayed with the flu patients and Beth finally drew Daryl out about his terrible family life. Recall also, the three very effective times during her history on the show when Beth’s singing gave great comfort to the others. Indeed, she was a saintly figure but as this story arc wore on, her demise seemed to be foretold.

TWD remains, for me, an absolutely brilliant show in terms of its characters, narrative and presentation.