Following on from my previous post that introduced some of DCMS’s capabilities; in this post I want to showcase the analytical capabilities that it provides. Let’s revisit our Singapore Mobile Phones example and focus on the Google Phone for the first two weeks of March 2009.
Let’s imagine that I want to study the chatter for Google phone. First thing on my mind would be, how is its buzz and sentiment? The Story Line chart in DCMS provides an overlay of two charts; the buzz and the sentiment. You can see this in the chart below, where the bars are associated with the axis on the left and the sentiment line is associated with the axis on the right. With sentiments the DCMS scores it in the range from -100 (most negative) to 100 (most positive). For this two week period, there is a slight decrease in the buzz towards the end with slightly negative sentiments.
The next two charts below reflect the trend of both the buzz and the sentiment. Here we are displaying the actual values and the 10-days moving average. In both cases, you can observe that the trend is moving towards less buzz and becoming more negative.
Next thing on my mind now, is to compare against other brands. How does the Google Phone compare with Apple iPhone, Nokia and Samsung? The charts below plot comparisons between Google Phone, Apple iPhone, Nokia and Samsung; one for buzz and the other for sentiments. This is very useful to make intuitive comparisons.
The above charts show separate features that are based on buzz and sentiments but we have several properties such as influence, sentiment and buzz. What about combining them? Now, based on all these three properties, how does Google Phone compare against the others? The next chart below is what we call the Social Media Equity Chart. It uses the three mentioned properties and lays it on the chart to give you and intuitive indication of where your product/brand stand. Where you want your product/brand to be, is on the top right as possible with the biggest bubble. This is because, moving upwards give you an indication that more influential people are making posts, moving right gives you an indication that posts are more positive and the size of the bubble is indicative of more buzz.
So far, I’ve mentioned mostly about buzz and sentiment, making comparisons and the like. Now, what if I want to do some advertising on a forum. Where should I put it? And ensure that its the most relevant. In DCMS with have a chart that shows you the top 10 buzziest channels. This is illustrated below. Not only do we show you the buzz but also the sentiment of the buzz in that individual channel. This will allow you to find suitable target channels to advertise where there is more chatter, at the same time you have an indication if the forumers are for or against you.
To further aid the case of advertising at the right channel. The chart on top 10 channels with the most number of unique voices would come in very handy. This chart will indicate to you the number of forumers that have generated your buzz. The difference here is that we are talking about the unique voice/person. So you have an indication that you can reach that estimated number of voices within the channel if you choose to advertise there.
While we are on the topic of voices, what if you want to know specifically who are making up your buzz count; voices that are making posts about your product/brand. This information is also available in DCMS. The data grid below shows you how you can uniquely identify the voice, his influence, as an author or commenter, the channel he is found, the number of posts, on average his sentiment and also list out all his posts that was made.
In addition to all the charting capabilities, DCMS offers a lot of transparency to the information that is used. In almost all of our charts, you can go right down to the posts that was used, to even the actual details of the posts that includes the thread for context. With every post, we also include a reference to the original source with a URL link.
In summary, I’ve gone through several of the analytic features that DCMS have to offer. I hope it gives you a much better insight into how it can aid in your analytical processes. If you have any further question, always feel free to drop me a note or leave a comment. For one of my upcoming blog entries, I will do a case study on the performance of mobile phone brands in Singapore to look at how much buzz they generate and how’s their online sentiment like.
Ever used the Internet to do your research for making your next purchase? I would say most of us do. It could either be looking for a new phone or checking out what the latest gadgets have to offer. This is just two of the typical scenarios that as consumers is where we would normally want more information. The question then, is how do we look for for it? There is typically, Google Search of course! Yes, most of us would just rely on Google’s returned results and start from there. For the more hardcore folks, there are known forums that contain enthusiastic forumers that will do reviews, share complaints, questions and answers and so on. These forums offer a lot more insight into various good as well as the bad from real users.
From a company’s perspective, wouldn’t you want to know where all this information is residing? You would want to protect your brand or get some immediate feedback on your product. Wouldn’t you want to know if your investment in all that marketing and advertising paid off? To do so, you would probably need to go through the same process of finding the information manually, using search engines or browsing through known forums. This will take a lot of time and effort, and I mean a lot! To consolidate all the information manually will become very tedious and cumbersome; not to mention how often you do it to ensure that everything is up to date? It will be an uphill task without help.
Now, allow me to demonstrate how Brandtology’s Digital Conversation Management System (DCMS) can help. Let’s look at a scenario where as a corporate personnel of company ABC and I’m interested to gauge the online buzz/chatter for the Google phone in the Singapore. For illustration purposes, in this example I’ve identified over 80 channels in Singapore that relates to the mobile phone industry, where their sites include: ChannelNewsAsia, GameAxis, Hardwarezone Forum, SGClub, SgForums, SingaporeBikes, Stomp, Electric Newpaper, VR-Zone and YoungNTUC.
Focusing on the month of February 2009, the chart from DCMS below illustrates an overview of the various subjects that I am looking at. Apple iPhone came up top with the highest buzz at 1796 posts and Nokia in second at about 568 posts with Google Phone at 514 posts. The colors in the chart depict the sentiment ratings, for example with Google Phone, it had 218 very positive, 30 positive, 213 neutral, 11 negative and 42 very negative posts. (Light Green = Very Positive, Dark Green = Positive, Blue = Neutral, Orange = Negative and Red = Very Negative).
Next, we would want to know generally what is the online chatter about. With our focus on Google Phone, from the Buzz Cluster in DCMS we observe the following.
The green colors reflect a positive sentiment towards those phrases mentioned. Light green represents very positive and the darker green represents positive. The size of the font represents the frequency; the bigger the font the more frequent its being mentioned. Some of the key phrases give you clues into the posts. For example “SingTel HTC Dream”, “Better than iPhone”, etc.
Next, let’s look at the Buzz in February for the Google Phone. A reference point to note here is that Channel News Asia featured an article that SingTel was bringing the Google Phone to Singapore on the 20th Feb. It is obvious that the chatter or buzz on the online media space has increased on the 20th and hit a high of 47 for the 21st Feb. This shows a correlation between the announcement and sparking off interest amongst the online forumers. The benefit of this Buzz chart is that you can use it to gauge if an event or announcement is successful at generating buzz amongst online media users.
The ability to determine the buzz only gives you an overall picture in its totality. That may be enough for some, but what if you want to drill down into its details? The next chart below illustrates how DCMS can breakdown where the buzz come from. From here you can see that the channel with the most buzz is from Hardwarezone’s forum “Smart PDA, PDA phones and GPS SIG” followed by “Eat Drink Man Women”. The intelligence you get here can be used for targeted advertising; choosing the channels that has the most relevant buzz.
So far, I’ve mentioned about buzz, how about the number of bloggers/forumers? You may have a lot of buzz, but it could just be from one or two bloggers. At times, you may want to know the number of unique bloggers that have mentioned your product or brand. This is where you can gauge the “viral growth” or spread in online media. The diagram below is DCMS’s Voice Growth chart. It shows the number of unique new voices for each day and the cumulative number of voices over the February time period. Like the Buzz chart, you can see that there was a significant number of new voices that grew from the 20th to the 22th after the announcement from SingTel on the 20th. If the announcement was actually a promotional event, this is a very good indicator to determine its success in spreading the word.
In summary, I’ve shown you briefly several features of DCMS’s capabilities and I hope it gives you an insight on how it can help you. For my next blog entry I’ll demonstrate further its analytical capabilities and how it provides transparency in the online media information we gather.
Eddie Chau, CEO of Brandtology, was recently in Sydney to officiate the launch of Brandtology Australia office.
From Left: Alex Feher, Eddie Chau and Rob Irving
During the launch,the Brandtology Australia team took the opportunity to highlight the buzz of Australian politicians in selected Australia social media channels.
If you are wish to contact Brandtology Australia office, please email alex.feher(at)brandtology.com
We have come a long way since we started our humble beginnings of building our first prototype in my apartment. I remembered the days and nights we spent experimenting with various techniques and solutions to be able to deliver what we set forth to do. We got our first prototype done successfully which convinced us that we are able to proceed with a viable business. Followed by more sleepless nights, Version 1 of the Digital Conversation Management System made it to public view. This allowed us to obtain a lot of feedback and constructive criticisms from clients, we listened and with a lot of hard work from the team, we came up with Version 2.0 at the start of this year. But we didn’t stop there, again we listened and look at areas that we could evolve …..
Today I’m very proud of what we have achieved and very pleased to announce the release of Version 2.1 of the Digital Conversation Management System.
Some of the new features in this release include:
Simplified chinese version.
Enhancements made to the graphical interfaces.
All charts are exportable to PDFs.
All data grids are exportable to EXCEL.
Buzz clusters are now color coded to reflect sentiments.
Identified conversations can be tracked and displayed.
Improved search functionalities.
Ability to custom select channels for flexibility in analysis.
We sincerely hope these new features will delight our clients and as always we are constantly listening, so do let us know if you have any questions or suggestions on how we can help you further.
PS- To find out more about our Technology, please click here
barcampsg 3 took place last Saturday, Feb 28 2009, at Ngee Ann Polytechnic.
Brandtology was a sponsor for the event and we chose to make use of this opportunity to network with the participants and speakers.
My colleagues Kelly Choo and Erwin Seah focused on the networking while I chose to twitter, qik and blog about the event at my personal blog.
I felt, however, that “live” blogging can be tedious and hard for me to concentrate on the topics being discussed. Hence, I decided to do “live” twittering instead.
With my Omnia mobile phone and QIK installed, I decided to do short video interviews with speakers, organisers and participants of the event.
The beauty of QIK is that the video gets posted online immediately and all you need to do is embed the video onto your blog.
Jeremy Synder from Twinity highlighting what he will be discussing about virtual worlds
Preetam Raj, one of the organisers of barcampsg3, giving a lunchtime update of event
Twitter seems to be quite popular with those at barcampsg3. We decided to analyse the chatter from Twitter to what was being said on this microblogging medium.
With Twitter as the selected channel, we group the keywords “barcampsg”, “barcampsg3” and “#barcampsg3” under the subject “Barcampsg3” to analyse the chatter for the buzz and sentiment level.
However, these Tweets were only analysed by the machine so there is a possibility that the sentiment value might be wrong. Brandtology has identified the importance of having to have our Social Media Analysts to view posts because of the conversation language used directly in social media channels. Posts that contain sarcasm will be rated as positive unless a human re-checks the sentiments, which is what we provide as a service.
Overview by subject
We found there were a total of 96 tweets made regarding the keywords mentioned above. Of the 96 posts, 8 were deemed as very negative (represented by the red bar), 57 neutral (represented by the blue bar) and 31 very positive (represented by the light green bar).
I have to highlight again that the sentiment level of the Tweets is measured by our in-house multilingual sentiment analysers which look at selected keywords pre-defined in our dictionary. Hence, the very negative tweets have to be taken in context of words deem as negative by the analysers.
The Storyline of barcampsg3 from 18 Feb 2009 to 02 March 2009
There was a first Tweet about barcampsg3 as early as 18 Feb 2009, 10 days before the event. It was by @claudia10 highlighting what she had to prepare for the presentation.
The number of Tweets grew gradually and spike on the day of the event itself. There were about 5 very negative Tweets, 36 neutral Tweets and 20 very positive Tweets. We believe there would be more than these amount of Tweets on event day itself.
This is because I asked the team to do a back search of Tweets on barcampsg3 two days after the event. We found that to accurately analyse Tweets on Twitter, it is important to analyse it on an ongoing basis rather than for the past.
The importance of having human analysis is highlighted greatly in this Twitter iteration.
Details of negative post
One of the Tweet that was deemed very negative by our machines was this one by @nazroll.
@nazroll tweeted “watching n listening to why film producers are so nasty.#barcampsg3”
The red font represented the negative word determined by machine intelligence and the blue font represent to the keyword.
This Tweet is neutral to the context of the subject “barcampsg3”. As such, you can see why human intelligence to analyse the Tweet is most important when it comes to analysing sentiments. Having done research in this fields, we have found that no technology can ever be close to even 90% accurate.
If you have any questions about this iteration, please share with us your comments. If you would like to find out more about Brandtology, email me at aaron.koh(at)brandtology.com or kelly.choo(at)brandtology.com
