Sweet 16 Recap: Nothing Compares to Louisville-Kentucky

As part of the Goizeuta Bracket Buzz contest, we were tasked to determine which of the 8 matchups in the Sweet Sixteen would produce the most pre-game “buzz” on Twitter.  Essentially, we looked at the 24 hour period before tip-off, and collected all tweets that mentioned either team or the match-up in that period.  The Kentucky-Louisville matchup had the most pre-game buzz.  The chart below shows the pre-game buzz for all 8 matchups (it has been indexed with Kentucky-Louisville as 100).

SweetSixteenBuzz

Mike Lewis & Manish Tripathi, Emory University, 2014

Round of 32 Recap: Twitter Sadness in Kansas, Elation in Kentucky

As part of the Goizeuta Bracket Buzz contest, we were tasked to determine which of the 16 matchups in the Round of 32 would produce the most pre-game “buzz” on Twitter.  Essentially, we looked at the 24 hour period before tip-off, and collected all tweets that mentioned either team or the match-up in that period.  The Kentucky-Wichita State matchup had the most pre-game buzz.  The chart below shows the pre-game buzz for all 16 matchups (it has been indexed with Kentucky-Wichita State as 100).  It is interesting to note that two teams in Kansas (Kansas & Wichita State) lost this weekend, and two teams in Kentucky (Louisville & Kentucky) won.  We were interested to see if this had an impact on all (not just basketball related) Twitter activity in each state.  We compared the average sentiment and volume of tweets for the three previous weekends with the sentiment and volume of tweets this past weekend in each state.  There was a 26.5% increase in the volume of tweets in Kansas this past weekend and a 9.7% increase in the volume of tweets in Kentucky.  The sentiment (the mix of positive, negative, and neutral tweets indexed between 1 and 100) of all tweets in Kansas decreased by 4.5%!  The sentiment in Kentucky increased by 1.9%.

Round 3 Pre Game

Mike Lewis & Manish Tripathi, Emory University 2014.

Round of 64 Recap: Duke-Mercer dominates Twitter, Even BEFORE Tip-Off

The NCAA Men’s Basketball tournament is now down to 32 teams, after the conclusion of the Tulsa-UCLA game last night.  As part of the Goizeuta Bracket Buzz contest, we were tasked to determine which of the 32 matchups in the Round of 64 would produce the most pre-game “buzz” on Twitter.  Essentially, we looked at the 24 hour period before tip-off, and collected all tweets that mentioned either team or the match-up in that period.  The Duke-Mercer matchup dominated the other 31 games in terms of pre-game buzz.  This was before Mercer “shocked the world” in an upset that even lead CNN to make the story “Breaking News” on their website (taking headlines away from the plane search story for a few brief minutes).  The pre-game tweets about the Duke-Mercer matchup focused primarily on Duke, specifically on Jabari Parker, Coach K, and final four picks.  The tweets were from all over the country, manifesting that Duke is a powerful national basketball brand.  The chart below shows the pre-game buzz for all 32 matchups (it has been indexed with Duke-Mercer as 100).

Pre-Game Buzz NCAA 64

The Kansas-Eastern Kentucky matchup had the second most pre-game buzz.  Many tweets focused on Andrew Wiggins and the health of other players.  A closer examination of the Duke-Mercer matchup yields some interesting insights.  First, even though Mercer won the game, the majority of the Twitter conversation both during the game and afterwards was about Duke.  The chart below shows the percentage of the Twitter conversation around the matchup that was attributed to each team before the game (24 hours), during the game, and after the game (18 hours).

Duke-Mercer Twittter Conv

Finally, we can also examine the sentiment of the tweets (positive, negative, and neutral).  Shockingly, Duke had a lower positive/negative tweet ratio than Mercer.  A lot of the negative tweets around Mercer, especially after the game, were about how Mercer had “crushed” or “destroyed” people’s brackets.

PosNegDukeMercer

Now, it’s on to the Round of 32 – we will be reviewing those games on Monday.  See if you can predict which matchup will have the highest pre-game buzz!

Mike Lewis & Manish Tripathi, Emory University 2014.

Goizueta Bracket Buzz Contest

bracketbuzzIn support of the Goizueta Marketing Communications Group, Manish and I have been asked to predict the game that generates the most “buzz” for each round of the NCAA tournament.  By buzz we mean the most pre-game (the period 24 hours before tip-off) social media noise.  From a marketing research perspective, this is an interesting endeavor.  Social media has great promise as a marketing research tool as it provides a source of organic and unconstrained data on consumer opinion.

During each round, Manish and I will identify the game that we expect to generate the most fan interest and provide some logic for our choices.  For example, in the first round my pick is the Kentucky-Kansas State matchup.  From the UK side, I think this game will generate the most noise because Kentucky has probably the most unhinged and irrational fans (a nicer man would say passionate) in all of college basketball.  These fans should be especially eager given last season’s early exit from the NIT.  Kansas State also has a deep tradition, and the fans are likely to find the UK matchup intriguing.  The matchup also includes coaches that embody the best and worst of college basketball.  Manish’s first round pick is the Ohio State-Dayton matchup.  Dayton basketball had the most loyal fan base among the non-major conferences in our previous study.   The Ohio State University has a large following, and this is a matchup of two schools in the same state.

To assess buzz, we will use a social media monitoring tool called Topsy Pro to track all of the pre-game mentions on Twitter for each game.  Click here to learn more about the buzz contest.

Twitter Analysis: Which NFL Markets Are Most and Least Receptive to Michael Sam?

Top Twitter Michael SamMichael Sam’s announcement has engendered several reports in the media regarding how accepting NFL management and players would be to an openly gay player.  We were interested in looking at how the fans in NFL cities feel about Michael Sam.  In order to do this, we collected all tweets mentioning “Michael Sam” in the 31 NFL markets for the past 2 days (2/9 morning – 2/11 morning).  The tweets were sorted by market, and analyzed for positive, negative, or neutral sentiment.  Looking at the ratio of positive, negative, and neutral tweets allowed us to compare Twitter sentiment for Michael Sam across NFL Markets.

We present the top ten and the bottom seven markets in the NFL.  It is interesting to note that a lot of the tweets in St. Louis and Kansas City that mention Michael Sam also reference the University of Missouri.  The most negative Twitter sentiment toward Michael Sam seems to be in the Nashville market. Worst Twitter Michael Sam

Michael Lewis and Manish Tripathi, Emory University 2014

Building Your Personal Brand: The Twitter Impact of National Signing Day

Edited NSD TwitterBuilding a Twitter following can be seen as a mechanism for developing an individual’s personal brand.  Athletes are investing in growing their personal brands at a young age.  We find evidence for this phenomenon in an examination of the young men who signed letters of intent for college football yesterday.  The table above presents a Twitter profile for the top thirty high school senior football players according to ESPN (we were not able to locate a Twitter account for Juju Smith & Dalvin Cook, so they have been excluded).   In addition to the overall total Twitter followers for each student, we also looked at the Twitter activity for each student in the last seven days.  We collected all tweets that included the student’s Twitter handle (e.g. @JabrillPeppers) over the last seven days.  The tweets were classified as having positive, negative, or neutral sentiment.   A few observations:

1)      Each student on the list has over 1,000 Twitter followers.  The median is just above 5K followers. 

2)      Students that waited until National Signing Day to announce their decision, tended to have more tweets overall and more negative tweets.

3)      The majority (85%) of the tweets over the last seven days occurred on National Signing Day.

This is just a snapshot of the top thirty, but we plan to study a larger pool of student-athletes over time, to analyze how their decisions and performance impact their personal brands.

Mike Lewis & Manish Tripathi, Emory 2014.

 

The Day After: Super Bowl XLVIII Ads Twitter Analysis

The Super Bowl ended less than twelve hours ago, and while it will take a while to understand the long term online impact of the Super Bowl ads (if there is one), it is always interesting to understand the type of online buzz created by brands in the immediate aftermath of the Super Bowl.

Super Bowl 2014 Total TweetsFor our analysis, we only examined brands that advertised during the Super Bowl; thus the #EsuranceSave30 campaign and JC Penny’s “rogue” tweeting is excluded from this study.  Our methodology was straightforward.  We used Topsy to collect all tweets that mentioned the advertised brands from 6PM EST on Sunday, February 2nd to 8AM EST on Monday, February 3rd.  The tweets were then characterized as having positive, negative, or neutral sentiment.  Brands that received less than 5,000 total tweets were also excluded from the analysis.Super Bowl 2014 Positive Negative

Budweiser created the most mentions on Twitter.  There were a lot of tweets around the “cute” puppy in the commercial.  David Beckham appearing semi-nude seemed to create the second most number of tweets.  Coca-Cola and Doritos rounded out the top four.

Next, we looked at the ratio of positive to negative tweets mentioning the brand.  The higher this ratio, the more positively the brand was viewed in the Twitterverse.  Radio Shack had the best ratio, followed by Budweiser, Oikos, and Wonderful Pistachios.  It should be noted that Radio Shack and Budweiser clearly outdistanced themselves from the pack with regards to this metric.Super Bowl 2014 Negative Positive

In our observation window, there were actually more negative tweets mentioning Coke than positive tweets.   There seems to be a large negative reaction to using languages other than English in “America the Beautiful”.  However, after the large initial backlash, there has been a wave of support for the commercial.  The automobile brands seemed to get the highest ratio of neutral tweets; these ads did not appear to evoke positive or negative emotions in the tweets.Super Bowl 2014 Neutral Total

We will be looking at the long-term online impact of these ads in future studies (as we have already done for the 2013 Super Bowl Ads).

Mike Lewis & Manish Tripathi, Emory University 2014.

Despite Media Efforts, Twitterverse Loves Beast Mode

Marshawn SentimentThere has been a lot of discussion about Seattle Seahawks RB Marshawn Lynch’s reluctance to speak with the media.  He spoke only for six minutes on Media Day (January 28th).  The appearance was dubbed as “Least Mode”.  Sites like Deadspin have documented the reaction of football writers to Mr. Lynch’s behavior, and it seems a lot of the reaction has been negative.  However, as the chart above shows, since Media Day, there has been a surge in positive tweets about Marshawn Lynch.

Related Articles:

Are They Really Mad Bro? Twittersphere Reaction to Sherman’s Post-Game Interview

U MAD BRO? Twitter Sentiment for NFL Teams In and Out of Their Markets

Mike Lewis & Manish Tripathi, Emory University 2014. 

Pre-releasing Super Bowl Ads: Tease or Full Monty?

sodastreamIn the last few years, the trend of releasing Super Bowl ads online in advance of the Super Bowl has been well documented.  Super Bowl advertisers can choose to pre-release a full ad, preview an ad, or wait until the Super Bowl to unveil their ad.  There is a belief among many advertisers that previewing or fully releasing a commercial online before the Super Bowl will generate online exposure and buzz at a much lower cost than running the ad on TV during the Super Bowl.  Since the majority of the pre-Super Bowl advertising activity is being done online, we decided to study 2013 Super Bowl ads using Twitter.  We realize that we could also look at online views of an ad, but we believe that tweets do a good job of capturing the buzz around an ad.  We were interested in investigating how the decision to preview or fully pre-release a Super Bowl ad impacts the pre-game online buzz.   Also, we wanted to determine the difference in long-term online impact of previewing or fully releasing a Super Bowl ad online in advance.  Our key insights from this study were:

1.    Previewing or teasing a commercial online increases the pre-game “buzz” at higher percentage than revealing the entire commercial online.

2.    Releasing the full commercial beforehand seems to have a long-term effect on online exposure, whereas previewing the commercial does not.

Now, for some more details on our study.  First, we coded each of the advertisers for the 2013 Super Bowl as releasing the full commercial in advance (Full), previewing the commercial (Preview), or doing neither (Neither).  We then used Topsy Pro to collect all tweets that mentioned the advertised brands for a period two months before and after the Super Bowl (February 3, 2013).  We summed up the total number of tweets mentioning a brand on a daily basis.  We averaged the number of daily tweets per brand over several different time periods.

Pre-Game Chatter of Brand

Pre-Game Twitter BuzzThe first thing we examined was how the pre-releasing of Super Bowl ads online affects the pre-game tweeting regarding the advertised brand.  The key metric we examined was the percentage increase in average daily mentions of a brand in the two-week period before the Super Bowl (the time period in which the advance release typically occurs) as compared to the two weeks before that.  We pool the data across the three types of ads: Full, Preview, and Neither.  The chart on the right displays the average percentage increase in the three categories.

Interestingly, it is not the full commercials, but the teased commercials that show the largest percentage increase in online chatter.  It’s possible that the full commercials get more online views, but the teasing nature of the previewed commercial might be building up some excitement, that is being captured through the increased Twitter activity.

Short Term Effects

Two Week Before and AfterNext, we wanted to look at how the actual airing of the Super Bowl ad on TV interacted with the pre-release decision of the firm.  The key metric we examined was the percentage increase in average daily mentions of a brand in the two week period after the Super Bowl as compared to the two week period before the Super Bowl.  The firms that teased their commercials beforehand experienced the largest increase in the two-week period after the Super Bowl as compared to the two-week period before the Super Bowl.  The increase is compounded if you consider that the same type of advertised brands experienced the largest growth in tweets in the two-week period before the Super Bowl!

Some of the brands that experienced the largest increase in tweet activity in this two week post Super Bowl period included Skechers & E*Trade.  While all three categories understandably experienced dramatic growth in online chatter, brands that had released the full commercial in advance had the least growth.  There are several potential explanations for this phenomenon, including less of a surprise factor, since the full commercial was already known to consumers.

Longer Term Effects

Long Term Twitter IncreaseTo better understand the lasting impact of a commercial, we decided to compare the average daily mentions of a brand for a three-week period a month AFTER the Super Bowl with a three-week period a month BEFORE the Super Bowl.  Looking at these periods would hopefully remove some of the short-term buzz, and allow us to see if there was a more permanent level of change to the Twitter activity surrounding a brand.  We realize that there could be other actions that could influence tweet activity besides the Super Bowl.  However, surprisingly, there is relatively low level of variability within members of the three types of advertisers.

Only the companies that showed the full ad before the Super Bowl manifested a “long” term increase on average in tweets mentioning the brand.   The two big winners with respect to long-term impact were SodaStream and Speed Stick.  Perhaps it was the repeated exposure to the full commercial that left a longer lasting impression on consumers.

2014 Super Bowl

So, what does this mean for the 2014 Super Bowl?  Our study only looked at data from one Super Bowl, but it will be interesting to see if commercials follow a similar pattern this year.  We are seeing more companies release their full commercials in advance this year.  We are also seeing firms with multiple spots preview one spot and fully release another spot.  The brands showing the largest increase in pre-game Twitter activity include: SodaStream, Squarespace, Oikos, & Butterfinger.

Mike Lewis & Manish Tripathi, Emory 2014.

2014 Pro Bowl: A Twitter Success

NFL-Pro-Bowl-Draft-2014The Pro Bowl decided to change its format this year, ostensibly to boost interest in a game that according to many has been on a decline over the last few years.  We were interested to see how this year’s Pro Bowl did in terms of Twitter activity compared to the Pro Bowl last year.  Specifically, we wanted to capture the “Twitter Share of Voice” of the Pro Bowl.  This is simply the number of tweets that mention the Pro Bowl divided by the total number of tweets over a given time period.  We believe this is a better metric than comparing the year over year number of tweets mentioning the Pro Bowl, since overall activity on Twitter is growing over time.

Pro Bowl 2014 Share of VoiceWe did not expect a large growth in Pro Bowl Twitter Share of Voice, largely because this year (unlike last year) the Pro Bowl was on at the same time as the Grammy Awards.  As anyone on Twitter can attest, it seems every other tweet last night was about the Grammy Awards.  Thus, we were surprised when we found a 100% increase in Twitter Share of Voice for the Pro Bowl as compared to last year!  Our study looked at a 24 hour period starting at 10am EST on the day of the Pro Bowl.  The overall sentiment of the Pro Bowl tweets remained unchanged from last year (A 3:1 ratio of Postive to negative tweets).  It should be noted that there were still more than fifteen times the number of tweets mentioning the Grammy Awards than the Pro Bowl.  The chart on the right breakdowns the top 10 Twitter Share of Voice for the 2014 Pro Bowl at the state-level.

 

Mike Lewis & Manish Tripathi, Emory University 2014.