TweetReach Blog

Archive for the ‘News’ Category

Announcing our new reach algorithm

with 2 comments

This post was written by Union Metrics CEO and Founder Hayes Davis. 

We started TweetReach in 2009 with a simple idea: to provide a simple report that showed people the reach of tweets about any topic. Since that time, we’ve grown far beyond that simple reach report and added comprehensive tracking, as well as many other metrics and insights. But reach is still something we care a great deal about, so I wanted to tell you about some changes we’re making to the algorithm we use to calculate reach.

This is a long post, so here’s the executive summary:

  • We’ve built a new and extremely robust model for calculating reach that will replace our current algorithm.
  • Historical reach data won’t change, and newly calculated reach will change only slightly in most cases relative to historical trends.
  • This new algorithm allows us to increase our data limits across all TweetReach Pro plans.
  • These changes go into effect next week.

For those of you who are interested in learning more about how we built our new algorithm, read on.

Setting the stage

Reach is a complex metric with many definitions across vendors and industries, so let me explain how we think about reach on Twitter. For us, reach is the total number of unique Twitter accounts that received at least one tweet about a topic in some period. Knowing this helps you understand how broadly your message is being distributed on Twitter.

For most of our existence we’ve measured reach by using Twitter’s API to determine the actual Twitter IDs of users who received tweets about a topic. From that copious raw data, we then applied a dose of math and lots of computational horsepower to derive our reach measurement. While this brute force method produces a very reasonable estimate for reach, it has some serious drawbacks in terms of meeting the needs of our customers. It slows down our reporting for customers pulling data on ad-hoc periods and – while our data limits are generous relative to our competitors – it meant we had to place stricter data limits than we wanted on our TweetReach Pro plans.

In addition to these increasingly frustrating drawbacks, Twitter has announced a major set of technical changes to their API. Included in those changes are additional restrictions on the API calls we make to determine the raw data we use in our reach calculation. So instead of working around those API limits and continuing with our brute force approach, we decided it was time to get smarter.

Investigating the data

At TweetReach, one thing we have is data – lots and lots of data. This means that we have an extraordinarily large archive of information about how campaigns work on Twitter, which goes back years and is unique to us. From these data and our experience, we know that the reach of a Twitter campaign is essentially a function of the number of unique contributors (users tweeting), how large their follower bases are, and the overall number of tweets. The question is: What are the mathematical parameters of that function?

We started our investigation by looking at what we call the “potential reach” of any conversation on Twitter. This is the maximum possible reach of any conversation if all people who tweet about a topic have no followers in common.  While it provides an upper bound on reach, it’s obviously flawed; the assumption that no one has followers in common just doesn’t make common sense. It is, however, a good starting point, so we put it in a scatter plot to at least see if there was a relationship between potential reach and actual reach:

reach_vs_potential_reach_raw

The way this graph turns upward at the end shows us there’s not a clear linear relationship in this data, but there might be if we plotted this on a log-log graph.

reach_vs_potential_reach_log_log

There is a nice positive linear correlation after all. However, there are also some pretty absurd numbers. In fact, some of those “up and to the right” data points in the first graph show a potential reach above 2 billion (nearly 30% of the world’s population and more than 8x Twitter’s 250 million monthly active users). As it turns out, this is what many in our industry call “reach”. But we knew we could do better.

Enter statistics

Armed with the notion that potential reach had some value, we set out to combine that with other data to build an algorithm that could predict reach. We experimented with many different approaches that we applied to tens of thousands of data points derived from real Twitter campaigns. And after many iterations, we’ve developed an extremely robust model that explains 99.51% of the variance in reach on a Twitter campaign.

Below is another scatter plot (with a trendline) that shows our reach prediction model applied to a test data set.

reach_vs_predicted_reach

The data have a nearly 1:1 positive linear correlation, and there are no crazy outliers. This means we can predict an accurate reach with an extremely high degree of confidence without having to resort to brute-force methods.

What does this mean for our customers?

For the vast majority of our customers there will be very little noticeable impact to reach. Most of you won’t see any change at all. But a few of you will see some small changes. We will not be altering our reach calculations for historical periods, so some of you may notice your future reach increase or decrease slightly when compared to historical levels. And since no model is absolutely perfect, a small set of customers may see somewhat larger increases in reach for certain campaigns. If you have any questions at all about a change in your reach, don’t hesitate to contact our support team and we’ll be happy to take a look!

But best of all, these changes bring some significant benefits to our TweetReach Pro subscribers. The first benefit is that viewing ad-hoc periods within a TweetReach Tracker will now be much faster than before. The second, much more exciting benefit, is that we’re now able to increase our data limits for TweetReach Pro plans.

TweetReach Pro tweet volume limits

We’ll be rolling these changes out next week and we’ll be communicating with you along the way. We’re extremely excited to share the results of this work with you – our customers! If you have any questions, please let us know.

Written by Hayes D

February 28th, 2013 at 3:43 pm

Posted in News

Tagged with , ,

Join us for a webinar this Wednesday, 2/27 at 11am PST!

without comments


Interested in more comprehensive, ongoing tweet tracking with TweetReach Pro? Sign up for a short demo webinar, where we’ll show you how it works, what’s included, and answer any questions you have. We look forward to to seeing you on the 27th, at 11am PST sharp!

Register here.

Got questions? We’ll answer them!

(Photo credit: US National Archives)

Written by Sarah

February 25th, 2013 at 10:45 am

Posted in News

Tagged with , , , ,

TweetReach Product Survey

without comments

Hey friends and fans, got a quick minute? We’d love it and be much obliged if you could take our product survey and let us know how your experience has been.

The feedback will help us keep making things better for you. Thanks!

-The TweetReach Team

Written by Sarah

January 21st, 2013 at 9:44 am

Posted in News

Tagged with , ,

Announcing ‘Plugged In To Gnip’ partnership

without comments

We’re excited to announce that we are Plugged In To Gnip with Gnip’s official partnership program! Gnip makes it possible for us to provide our customers with tools built on the full firehoses of both Twitter and Tumblr data. This ensures we have top quality data so you never miss a tweet or a post.

In addition to full-fidelity firehose access to Tumblr for our new Union Metrics for Tumblr engagement analytics and to Twitter for real-time tracking with TweetReach Pro, this also includes the ability to reach all the way back to 2006 with our new TweetReach Historical Analytics, through which we can access any tweets from the entire Twitter archive. You can learn more about how we use Gnip’s Historical PowerTrack for Twitter in our case study with them.

What else does this partnership mean? It means a number of things, but what’s most important to you – our valued customers – is that all our social analytics products are built on the highest quality, most comprehensive and reliable social data. We are committed to bringing you the data that you need to be successful with social media and our partnership with Gnip helps make that possible; full coverage, high-quality data is at the heart of all our analytics solutions.

We’re proud to be Plugged In To Gnip, and we’re working hard to bring you new and amazing things all the time. Check back often!

Written by Sarah

December 4th, 2012 at 9:30 am

Posted in News

Tagged with ,

Announcing Union Metrics for Tumblr public availability

without comments

Last month, you may remember us announcing our first non-Twitter analytics product. Today, we’re excited to share that Union Metrics for Tumblr is now publicly available!

We’ve partnered with Tumblr as their preferred analytics provider to deliver full-fidelity analtyics built on the entire Tumblr firehose. With our new tool, you can analyze any blog or any topic on Tumblr. If you’re using Tumblr to spread your message and want to know what’s really happening with your content, then Union Metrics for Tumblr is for you.

Union Metrics for Tumblr

Quickly get insight into your post volume and engagement. Understand what posts are working and how the conversation is spreading.

What is Union Metrics for Tumblr?

Union Metrics for Tumblr can measure activity and engagement for any blog or any topic on Tumblr. We make it possible to get in-depth analytics on all the interesting content that’s being shared on Tumblr.

Similar to what you’ve come to love from TweetReachTrackers, our new Tumblr reporting includes:

  • Beautiful, interactive trackers to continuously monitor your Tumblr presence
  • Post and note volume to show overall engagement levels and trends over time
  • Top contributors and curators to help identify key influencers
  • Analysis of posts and tags to surface most popular posts
  • Post engagement details, including the full reblog tree and interactions over time
  • Full data export for further analysis

What does it cost?

We currently have three plan levels perfect for larger brands and agencies, starting at $499 per month. They all come with a 7-day free trial. TweetReach Pro subscribers will receive 30% off these prices, so if you’re currently using TweetReach Pro, just let us know if you want to subscribe to Union Metrics for Tumblr.

We love Tumblr and we especially love the diversity and creativity that goes into making it the wonderful place that it is. And we know that not everyone works at a company with the budget for these plans. So we’re working on more analytics offerings for everyone, including a version for anyone interested in measuring their personal blogs. That’s coming soon, so stay tuned!

Written by Jenn D

November 29th, 2012 at 1:11 pm

Posted in News

Tagged with ,

TweetReach 2012 holiday support hours

without comments

The TweetReach support team will be around to answer all of your questions throughout the final weeks of 2012. However, please allow them a little extra time to return your calls and emails on the following dates, as they might be stuffing themselves with holiday treats and spending time with their families.

Thursday, November 22 – Friday, November 23
Saturday, December 22 – Tuesday, December 25

On these days, we will return all non-urgent requests within 24 hours and urgent requests as soon as possible. As always, you can get in touch with us in many ways. Email is the fastest way to get through to us during the holidays (aren’t smart phones great?).

Happy holidays!

Written by admin

November 21st, 2012 at 11:06 am

Posted in News

Tagged with ,

Introducing Union Metrics for Tumblr

with one comment

We’re thrilled to announce Union Metrics for Tumblr! This is the very first measurement product designed specifically for Tumblr that provides analytics based on their entire firehose of data. That includes more than 100 million Tumblr events per day. And, to add to the excitement, Tumblr has officially named us their preferred analytics provider!

For more details, head over to the Union Metrics blog.

Or, if you’ve heard enough, sign up for an invitation here!

 

Written by Dean Cruse

October 4th, 2012 at 11:30 am

Posted in News

Tagged with , ,

Announcing TweetReach Historical Analytics: Analyze any tweets ever posted

without comments

Today, we’re announcing our brand new TweetReach Historical Analyticsall the in-depth TweetReach analytics you’ve come to love, now for any tweets ever posted, dating back to March 2006. This is the first product of its kind to offer comprehensive historical analytics for any topic from the full Twitter archive and we couldn’t be more excited to share it with you.

While real-time analysis of Twitter activity is crucial, it’s only part of the Twitter story. Historical analytics make it easy to measure today’s performance against past trends or dive into an event that wasn’t tracked in real-time. With TweetReach Historical Analytics you can use powerful queries to extract anywhere from a few hours to a few years of the data that matter to you.

On top of the extensive Twitter archive, we provide our in-depth analytics, including all the metrics available in TweetReach Pro – reach, exposure, tweet volume, contributor and tweet details, URL and hashtag analysis, and so much more. This opens up so many possibilities for your Twitter analysis! For example, our premium historical analytics are great for:

  • Twitter emergencies – Did something come up suddenly or unexpectedly?
  • Recurring annual or monthly events – Need to track trends over time?
  • Competitor and share of voice analysis – What are people saying about others?
  • Benchmark data – Want to compare new tweets to older tweets?
  • Research – Curious about what people thought about a past event or topic?

You can use our Historical Analytics to backfill a new or existing Tracker, or purchase a one-time analysis any time you need it. You can customize the time frame down to the minute, so we can analyze tweets from just a few minutes all the way up to a few years. There’s more detailed information about our historical analytics on our helpdesk. We have this historical tweets access to the full archive of tweets through Gnip’s new, fully compliant Historical PowerTrack for Twitter.

If you’re looking for in-depth, full coverage analysis of any campaign, event or topic any time in the past, then our new TweetReach Historical Analytics is just what you need. Pricing starts at $149 and you can get started here.

And as always, please let us know if you have any questions.

Written by Jenn D

September 19th, 2012 at 12:00 pm

Posted in News

Tagged with , ,

Union Metrics selected by DataWeek 2012 as top Twitter data innovator

without comments

We’re excited to announce that Union Metrics was selected as the Top Innovator in the Twitter Data category for the upcoming DataWeek 2012 Conference & Festival!

DataWeek is a week-long conference and festival showcasing innovations around the use of data. The founders of Techweek in Chicago and the Data 2.0 Summit in San Francisco are organizing this, the first annual event from September 22-27 in San Francisco, CA. There will be over 200 speakers from Google, Twitter, IBM, Cloudera, CitrusLeaf, Dun & Bradstreet, and hundreds of other data-centric companies during the 4-day conference along with a week-long series of data events, workshops, hackathons, hiring mixers, and meetups.

And, if you’re attending, please join our co-founder and CEO, Hayes Davis on Wednesday, September 26 at 2:00pm as he will be speaking on a panel entitled: “Does Social Influence Score Affect My Job Prospects or Price of my Consumer Goods?“.

Use discount code DataWeek25 at Dataweek.eventbrite.com for 25% off!

Written by Dean Cruse

September 7th, 2012 at 9:15 am

Posted in News

Tagged with ,

Union Metrics SXSW 2013 panels

without comments

The team here at Union Metrics proposed a number of great panels for next year’s South By Southwest conference. They’re all listed below. If you think any of these would be interesting presentations at SXSW, please give us a vote!

Getting started with social data at scale

Featuring these speakers:

  • Ken Little, Director of Engineering, Tumblr
  • Rob Johnson, VP of Product Strategy, Gnip
  • Hayes Davis, CEO, Union Metrics

Answering these questions:

  1. What social networks offer access to social data and how do they provide that access?
  2. What issues should you be aware of in order to maintain compliance with the Terms of Service from different providers?
  3. What are the technical challenges inherent in consuming, storing and analyzing large amounts of social data?
  4. While social data is often treated as the answer to all kinds of marketing and branding questions, it does have plenty of limitations. What are some useful business questions social data can answer?
  5. What tools and techniques are available to get started analyzing social data?

The art & science of social media movie marketing

Featuring these speakers:

Answering these questions:

  1. Why do fans share film-related content online?
  2. What are studios and networks doing to engage their audiences in and out of the theater?
  3. What marketing tactics work best to market a movie on Facebook? On Twitter?
  4. What social media metrics are the most important to measure during a film release?
  5. Can social media predict a film’s success at the box office?

On Tumblr: Case studies, best practices, analytics

Featuring these speakers:

Answering these questions:

  1. What are examples of successful brands on Tumblr?
  2. What are examples of clever Tumblr campaigns and strategies?
  3. How is the community on Tumblr different from Twitter and Facebook?
  4. What kind of content resonates on Tumblr?
  5. How can you measure a Tumblr campaign? What metrics matter?

Designing for sales

Featuring these speakers:

Answering these questions:

  1. How do you balance company and product information on your home page versus a clean, simple design to drive more conversions?
  2. By the time users make it to your Plans and Pricing page, they should have a basic understanding of your offering. What are some best practice examples of Plans & Pricing pages that convert?
  3. How can data and infographics be used to tell simple stories that encourage users to act?
  4. Are you ever done iterating? How do you avoid analysis paralysis and start implementing and testing quickly and continually?
  5. Everyone has an opinion and sales, marketing, and design all want to make sure their ideas are incorporated into the final product. What are some tips for avoiding design by committee?

Call Me SOA, maybe?

Featuring these speakers:

Answering these questions:

  1. Why do we care about service-oriented architectures? What are important concepts in a SOA?
  2. What are the advantages of using an SOA? What are the pitfalls?
  3. How do I know I need an SOA?
  4. How can we get started with SOA today?
  5. What are some awesome SOA technologies?

How Twitter has changed how we watch TV

Featuring this speaker:

Answering these questions:

  1. What is social television?
  2. How has Twitter changed how we watch TV?
  3. What are some examples of effective TV-related Twitter campaigns? What shows are doing the best (and the worst) on Twitter?
  4. What role do second screen apps play in TV viewing?
  5. What are some predictions for the future of Twitter and TV?

Written by admin

August 15th, 2012 at 10:49 am

Posted in News

Tagged with , ,