Author: Arvind Padmanabhan
Visualizations in R and their discussion
Two days ago I was thinking of starting a new meetup group in Bangalore but in the process I asked a few questions. I wonder how many meetup groups are there in Bangalore? I wonder many of these are really active? Which are the big ones? How many members are there in total? To answer these questions and satisfy my curiosity, I downloaded some data from Meetup.com and analyzed the same.
In fact, Meetup offers an API to make this process easier but the API has its limitations. You can only look at the details of a group after you have joined it. So I adopted a manual approach since I was interested in only high-level metrics. I copied some overview data manually from the web browser. Subsequently, individual group information was obtained by web scraping. The language of choice for this and subsequent visualization was R. So, here are the findings.
It’s almost incredible that there are so many tech meetup groups in Bangalore with a combined membership of over 3.6 lakhs. We must keep in mind that many folks are members of multiple groups. They will be counted multiple times. Hence this number does not equate to unique individuals.
As I suspected, the groups are not equally popular. In fact, popularity is quite lopsided. One-third of all membership is concentrated in only top 4% of groups. This top 4% translates to 23 groups, each having at least 3000 members.
The next step was to analyze these top 23 groups. IoTBLR and Big Data Introduction are clearly far more popular than the rest of the pack. This gives an indication of technologies that are hot at the moment.
I then looked at the histogram to know the distribution of membership. Two-third of all groups have membership less than 500. It’s easy to start a group but to get a big fan following is not easy.
In fact, the bottom two-third can be analyzed further. Considering all meetups, about 50% (0.66*0.70) of all groups have 200 members or less. So if I do start a meetup group, I should target to get 200 members first and then rise up to 500 members.
Membership is one thing but how active is a group is quite another thing. I filtered the data to those groups that organized at least two events per month on average. I found that out of all 543 groups only 28 groups made the cut. That’s only 5%! In fact the number is less. Some groups (such as ICPCIT 2015) claim to organize meetups so frequently but in fact they don’t. Such groups have configured their accounts to automatically schedule meetups on a regular basis but they don’t actually have those meetups. Among the popular groups (by our definition, those with >=3000 members), only three of them are seen to organize at least two meetups per month.
Focusing this analysis on the popular groups, we see that there are some big groups who don’t actually meet that often: Scrum Bangalore, Salesforce Developer, Hadoop Meetups. If there’s no suitable alternatives to these groups, perhaps it’s a good idea to start a competing meetup. The important thing is to meet regularly to give value to members. The two biggest groups are doing okay, organizing more than one meetup a month on average.
Taking the analysis from the specifics of popular groups to the aggregation of all groups, we look at a histogram. Astonishingly, 152 groups (28%) have not met at all! We find that 15% of all groups meet only once a year or less. Two-thirds of all groups meet at most four times in a year.
How does one run a popular meetup group? Does it depend on how long it’s been around since the date of creation? Or how many events are organized? Perhaps it has to do more with the topic chosen. Anyway, we attempt to see if there’s any correlation.
Finally, we look at the keywords in the names of meetups. By picking keywords that occur frequently and grouping them into suitable topic names (this process is manual) we can count how many groups fall into such topics. The resulting graph gives us an indication of hot technologies and community interest. Note that a meetup group can fall into multiple topics at the same time. Coding is too general but can be considered as being more popular than Testing. The popular topics apparently are ML/AI, DataAnalytics, Cloud and BigData.
Author: Arvind Padmanabhan
Arvind Padmanabhan graduated from the National University of Singapore with a master’s degree in electrical engineering. With more than fifteen years of experience, he has worked extensively on various wireless technologies including DECT, WCDMA, HSPA, WiMAX and LTE. He is passionate about tech blogging, training and supporting early stage Indian start-ups. He is a founder member of two non-profit community platforms: IEDF and Devopedia. In 2013, he published a book on the history of digital technology: http://theinfinitebit.wordpress.com.