Likes before 03/04/2016 - 0
Views before 03/04/2016 - 5036
This is a guest blog from Chris Thomas - Solution Architect for Big Data and Analytics - CTO Team, Software Group, Europe. He can be contacted on Twitter @cwt99, or email him on email@example.com.
Saturday 1st of February saw the opening matches in the 2014 RBS Six Nations Rugby Championship - an annual competition between the national teams of England, Ireland, Scotland, Wales (the four "Home" nations), France and Italy. Following the work that I did analysing the social conversation on Twitter around the Wimbledon Championships in 2013 I thought it would be interesting to see how a different sport with a somewhat different "structure" and timetable would figure in social media.
Figure 1 shows the profile of the Twitter volumes across the weekend with the match times being picked out on the X-axis. The area colour shows the Tweet sentiment which is generally neutral to moderately positive. The pre-match championship build-up is obvious on the Friday evening and the last minute win by France over England drives the Twitter volumes for that particular match higher than those seen for the closely fought game between Wales and Italy.
The reduced Tweet volumes on the Sunday can be explained by the single match being played on that day and the possibility that many people will have expended both their rugby and Twitter energy during the opening Saturday. It will be interesting to see if this profile is repeated over the following weekends where the timetable is repeated. Lessons to be learned - if you want to get your message across to the largest audience pick your timing well. Equally - a quiet moment may be the right time to stand out from the "noise". It pays to understand your target audience and the "event" to ensure your message is best received.
The championships are obviously international by their very nature and should attract a broad audience from at least the competing nations. As IBM Content Analytics (ICA) fully indexes the Tweets it's very easy to explore the language being used. Figure 2 demonstrates the broad range of hashtags that supporters used to identify the Championships in their Tweets. In this analysis I've not used case to discriminate results so #6Nations and #6nations are grouped together. As a result of this information I've extended the scope of the Tweets I'm collecting for the second weekend - it will be interesting to see if it makes a material difference to the nature of the collection. It's clearly very important to understand the language used by your customers - more so in an international context. Use the wrong selection criteria and you can miss a whole section of your audience. It's also important that your collection and analysis strategy adapts as you learn - this can help you optimise the volume of data that you collect and more accurately target the people you want to listen to.
I was interested to see how the score-line might influence the volume of Twitter chatter so I charted the volumes by minute across both Saturday matches. Figure 3 shows the number of Tweets by minute with the change in the score-line highlighted at key points. While there is some correlation between score change and Twitter volume for the Wales-Italy match it isn't particularly strong. This probably indicates that the audience are focussed on the play at hand and that the match was, for the most part, progressing as expected. For the France-England match there is a much stronger correlation between events on the pitch and Twitter volumes. This is most likely driven by the closeness of the match and the last-minute winning French try generates a huge increase in Twitter volumes.
Regardless of the degree of correlation it was interesting to see that the response was normally within 1 or 2 minutes of the trigger event. Clearly, those people who were motivated to Tweet obviously felt the need to do so soon after the event. This just goes to show that Twitter can be an extremely valuable tool for organisations and companies to sense the mood of their customers at events or following important announcements.
Wimbledon demonstrated that it was a global event with relatively large volumes of Twitter traffic across several continents. How much chatter would a rugby tournament between six European countries generate in comparison? Figure 4. shows the global distribution of Tweets using the #6nations tag. While it's not surprising that the bulk of the chatter was from Europe it was easy to spot which other countries also have an interest in rugby. I'll explore how use of hashtags in different languages influence this map in a future article. Although Australia and New Zealand both have a strong rugby heritage they did not figure on the map. This could be due to the difference in time zone - but I also have a suspicion that take-up of Twitter is lower in these countries as we also saw a similar outcome with Wimbledon.
The next map shows a closer view of the UK mainland and Ireland. At this level of detail you can start to pick out the cities within the UK which have a strong rugby heritage.
Remember that most Smartphone users rarely give Twitter access to their GPS location so these maps are based on approximately 5.5% of the Tweets containing the #6nations hashtag. Nevertheless, as long as you take this into account, it can provide useful information on the scope and location of your potential audience.
The analysis of the Twitter chatter was carried out using IBM Content Analytics and, by defining a series of rugby related dictionaries, it was an easy matter to investigate topics of conversation. At the end of each rugby international the commentators announce a "player of the match" and I wanted to see if it was possible to predict who these would be. Of course there's no published "formula" for determining player of the match so I had to play around with the data and apply some logic. The results of my analysis for the Wales-Italy match are shown in Figure 6. This is based on positive Tweet mentions for the players during the match and excluding any Tweet which also mentioned a player from one of the other teams.
The eventual player of the match as decided by the BBC Sport commentators was Michelle Campagnaro so I explored the data for Leigh Halfpenny and Michelle Campagnaro more closely to see if I could understand why I'd arrived at a different result. Figure 7 shows the distribution of Tweets for Leigh and Michelle during the match as analysed by ICA for trending. The statistics behind these graphs are too complicated to go into here but all you need to know is the more orange or red a bar the more significant the trend. While Leigh had more Tweets overall his occurred at various points during the match. Michelle's Tweets by comparison were clustered towards the end of the match. So if I'm trying to second guess the experts then volume and sentiment are a good indicator but I also need to look at how the Tweets are distributed throughout the match. Let's see if I can do better this coming weekend.
Of course, what works for rugby may not work for a product launch or a film premiere - but over time you can determine how to "read" the audience that matters for you and then use that information to help drive customer satisfaction and product sales.
Likes before 03/04/2016 - 0
Views before 03/04/2016 - 5036
Tim_Powers 270003F3FN Tags:  leicester maintenance decision-management predictive-analytics business-analytics spss analytics rugby 2,792 Views
Guest post from Erick Brethenoux, Director, IBM Business Analytics & Decision Management Strategy
As the saying goes, �Rugby is a rough sport for gentlemen; football (or soccer) is a gentle sport for ruffians.�
When I played rugby in my younger days in France, I suffered a number of injuries � from a dislocated shoulder to being knocked out to various gashes requiring stitches on my chin and head.
It�s no surprise that a study shows 1 in 4 rugby players will be injuredduring a season since the objective of the game is to take a hit for your teammates and keep the ball moving down the field.
In order to find new ways to keep top players healthy, the Leicester Tigers, nine-time champion of the English rugby union�s Premiership and two-time European champion, are using IBM predictive analytics to help the team better understand and reduce players' injury rates and minimize risk.
After all, losing a key player for an extended period of time can not only hurt the team on the field, it can also result in reduced ticket sales and spectator attendance if the team does not perform up to expectations.
Leicester is looking at important indicators such as fatigue, and threshold and game intensity levels in order to detect hidden patterns or anomalies. Better understanding this information will allow coaches and trainers to prevent injuries for each player by investing in adequate training programs, tailored to players� physical and psychological states.
For example, if a player has a statistically significant change in one or more of his fatigue parameters and the current intensity of training is likely to be high, the data may show that the likelihood of this player becoming injured is 80 percent greater. This type of real-time information will make it possible for the team to alter the player�s training to reduce the injury risks.
It�s basically a human form of predictive maintenance.
In the manufacturing industry, plant managers, maintenance engineers and quality control champions all want to know how to sustain quality standards while avoiding expensive unscheduled downtime or equipment failure, and how to control the costs of labor and inventory for maintenance, repair and overhaul operations.
Through the use of IBM predictive analytics, they can now gather information in real time from a variety of sources, including maintenance logs, performance logs, monitoring data, inspection reports, environmental data and even financial data to determine the areas of greatest risk.
For example, an IBM customer who manufactures helicopters is able to identify and predict equipment maintenance, ultimately increasing customer satisfaction by keeping the helicopters in the air instead of grounded for repairs.
It�s the same way that Leicester is investing in business analytics to uncover the key predictors in the data �scrum� to deliver personalized training programs for players at risk and improve performance.
Now that�s a good �try.�
For more information:
�Read the press releaseon the Leicester Tigers' use of IBM predictive analytics
�Read a previous blogpost describing how other sports are leveraging IBM business analytics
�Downloada whitepaper on predictive maintenance
Likes before 03/04/2016 - 0
Views before 03/04/2016 - 4845