Data Shows that Negative Remarks Lead to Fewer Followers

Continuing my series of TweetPsych based data points, this is based on analysis of over 100,000 accounts and looks at the “Negative Remarks” category. Negative remarks include things like sadness, aggression, negative emotions and feelings, and morbid comments.

As it turns out, nobody likes to follow a Debbie Downer accounts with lots of followers don’t tend to make many negative remarks. If you want more followers, cheer up!

Read More

Data Shows That Social Behavior Gets More Followers

If you like this post, or any of my work, please, nominate me for a Shorty Award.

The linguistic analysis engine behind TweetPsych has given me a bunch of cool data points to analyze, so I’ve begun to look at various factors and their relationship with follower counts. Using a database of over 30,000 accounts that have been analyzed with TweetPsych, the first dimension I’ve looked at is “Social Behavior”.

The “Social Behavior” category includes inclusive language like “we” and “you”, as well as language that describes relationships and communication. As it turns out, accounts with more followers, tended to be using more social language.

Over the next week or two, I’ll be posting about the rest of the dimensions TweetPsych analyzes and how they’re related to follower numbers, so stay tuned.

If you like this post, or any of my work, please, nominate me for a Shorty Award.

Read More

Introducing the New TweetPsych and TweetPsych for Lists

After I first launched the Twitter psychological profiling tool TweetPsych, some of the most common feedback I got was that it was hard to understand the results. So I designed a new reporting mechanism and design to solve that problem. The new TweetPsych uses “meta dimensions” which are combination of related factors from the two linguistic algorithms (RID and LIWC) the application uses. Each of these comes with a description and is represented on a bar graph. Each user’s profile is compared against the average user and the report explains which dimensions occur more or less frequently than the average.

I also launched a new feature for the site. TweetPsych for Lists allows you to do the same kind of psychological profiling, but of entire lists. Curious to know what the inside of Zappo’s employees’ heads looks like? Here you go.

If you have other ideas on how to make TweetPsych even better, let me know.

Read More

Weekends and Afternoons Show the Highest Twitter CTRs

Want more clicks? My new data suggests that you should Tweet your links in afternoons, evenings and on weekends.

Continuing the study of Twitter clickthrough rates I started last week, I added over 100 more of the most followed Twitter accounts to my database and indexed click data on over 20,000 bit.ly links Tweeted by those accounts. In all of the data below, I measured CTR as the number of clicks a link received, divided by the number of followers the sending account had on the day it Tweeted it. As I noted in my other post, this number can be over 100% due to ReTweets that may use the same bit.ly link.

The graphs below shows the percentage of difference in CTR at each hour or day from the specific average for each account. I did it this way to account for the wide variation in CTRs between accounts (some accounts have much higher rates than others).

The first data point I analyzed is time of day (EST). It showed the expected afternoon/evening preference seen in my other Twitter stats.

Next I looked at days of the week, which showed a much less expected weekend preference. I believe this is due to the “link fatigue” present during the weekdays, where there is a much higher level of activity and many more links are posted.

Read More

Modeling ReTweet Dynamics

Earlier this year I read a paper called “Modeling Blog Dynamics” in which they propose a method of modeling the spread of links through the blogosphere using zero-crossing random walks and exploitation vs. exploration applied to a logical flowchart model:

The authors suggested that the model could be used in influence maximization algorithms which aim to identify key, influential individuals in a given social network for the purposes of viral marketing. I was intrigued by the possibilities and have been tossing around a possible flowchart model of how individuals decide to ReTweet specific Tweets since reading that paper. Here’s my first attempt:

There are three steps in the process where a marketer can increase the chances of a specific Tweet being ReTweeted. The first step indicates that a user must be following the sender of the target Tweet; the second step means that they must actually see the Tweet in question (try to imagine what percentage of your friend’s timeline you actually see). Step three is where the user must find some motivation to ReTweet it.

Maximizing the number of followers the Tweet’s original sender has is fairly straightforward, and most of my Science of ReTweets data has explored the ReTweet motivation percentage. I had not put much effort into analyzing statistics around the attention problem, but I’ve begun to.

Because there is no way to exactly measure what percentage of followers will actually read a given Tweet, the next best metric we have is click through percentages, so that is what I’ve been working with. You can expect to see more work to that end in the next few weeks.

My work has been concentrated on maximizing the contagiousness of ideas, whereas much of the aforementioned academic work focuses on the people involved in spreading ideas. So you can also expect to see me advance the concepts of “ReTweetability” I began a few months ago with the purpose of identifying influential users.

Read More

Want More Clicks? Tweet Less

Tweet Much? Don’t Expect a High CTR. New data I’ve been working on seems to indicate that the more frequently you Tweet links, the fewer clicks you’ll get.

I’ve been working towards a statistical model of how an individual makes a decision to ReTweet a specific Tweet and in that process, I came across an interesting problem: before someone ReTweets something, they have to notice it. If you’re anything like me, you’re only able to actually read a small percentage of the total activity in your friend’s timeline, which means that very few of the Tweets I’m technically “exposed” to ever even have the chance of being ReTweeted.

As a measure of “attention,” I started looking into click-through data. The wonderful thing about bit.ly is that it has an API that allows anyone to view the stats on any bit.ly link. I grabbed as many of the bit.ly-containing Tweets of several of the most followed and link-heavy Twitter accounts as the Twitter API allows (it imposes a limit of 3,200 total Tweets accessible per user) and the number of clicks each link had gotten. For the time of each Tweet, I also pulled the number of followers that account had and calculated a followers-to-clicks conversion rate. I’ll call this rate CTR for simplicity’s sake. I was able to get this information for about 2000 Tweets. It is important to note that ReTweets of a bit.ly containing Tweet (if the ReTweeter does not change the link) also count toward the total number of clicks, so it is possible in some cases for a link to have a CTR of over 100%.

Digging into this data, I started to notice an interesting trend: the higher the number of links an account Tweets in a given timeframe, the lower the CTR on each individual link. If you want your Tweet to get noticed and ReTweeted, you should slow down your posting rate.

First, I looked at this data hourly, by graphing the CTR of Tweets over the number of other Tweets posted in the same hour. The first graph below shows individual lines for each account measured; the second graph shows an average for all those accounts.

Then I looked at the numbers by day. The CTR fall-off in these graphs seems to be slower than those above, but the trend is still prominent.

I’ve got a bunch more stats and analysis to run on this dataset to isolate some factors that lead to increased CTR, and therefore increased attention. I’d also love your feedback on data points you’d like to see.

Read More

To #SaveReTweets, Make Sure Everyone Knows How to ReTweet

I wrote a little while ago about how Twitter’s plans to mangle ReTweets with its Project ReTweet, and the danger that poses to the crowd-invented functionality. After having several conversations on the topic and wondering what we could to do save ReTweets, I’ve come to the conclusion that the only thing to do is make sure that everyone knows how to ReTweet the original way. Then, once (or if) Twitter goes ahead with Project ReTweet, we can all continue to use the old format. If you like ReTweets, help save them by spreading this post around to ensure that everyone understands the commonly accepted method.

What is a ReTweet?

Normally, when you post a Tweet, only those people who are following you will see it. ReTweeting occurs when one of those followers copies your Tweet and posts it to their timeline. At that point, all of their followers will also see it. I’ve created an image below that explains this process.

How do I ReTweet?

The simplest way to ReTweet a post is to copy it from the original poster and paste it into the update box on your Twitter homepage. Here’s an example:


There are a few different ways people format ReTweets, but the most common way is this:

“@UserName” would be the username of the person who originally posted the Tweet you are ReTweeting and “original Tweet” is the text of that Tweet.

You can also add your own opinion of the content after the “original Tweet” text or before the “RT.” This is one of the most important things  the new Project ReTweet format is going to prevent.

Some people also use “h/t” (which stands for hat tip, from blogging) or “via.” Both of these standards are generally used when you are posting a link you found from someone else’s Tweet, but changing the text of the Tweet itself. RT is typically reserved for verbatim copies.

Many websites feature a little green and gray box (like the one at the top of this post) with a number and a button to “ReTweet.” If you’re reading something that you think your Twitter followers would like, just click the green button to share it with them. This isn’t a ReTweet in the sense described above, but the format is the same.

How do I ReTweet in a Third-Party Client?

You’ll also notice that down the right-hand-side of this post are screenshots from a variety of popular desktop and mobile Twitter applications. Each image shows you the app’s built-in one-click ReTweeting functionality. As you become a power user of Twitter, you’ll probably switch from using the Twitter.com web interface to one of these clients.

Want to Learn More?

If you’re interested in learning more about ReTweets, I’ve posted about ReTweet etiquette and the science behind how to get more ReTweets.

And remember: the only way to save ReTweets is to make sure everyone knows how to ReTweet.

Read More

Twitter’s Deal With Search Engines? I Called That.

News broke yesterday that Twitter is talking to major search engines (Google and Microsoft) about licensing Twitter’s full firehose API. Over the past few months I’ve been seeing signs leading to exactly this kind of thing; here’s why Google will jump on this data.

When Twitter announced their intentions to completely re-engineer how ReTweets work, I took a strong stance against the move, mostly because it means that 3rd party researchers will no longer be able to index and analyze ReTweets in the same way we can today.

I speculated about the reason behind the move:

By taking out the “RT @username,” Twitter is making it impossible for users to search for retweets themselves, says Zarrella. “They’re limiting how much you can analyze retweets.” Zarrella speculates as to whether the retweet button might have been created so that, down the road, Twitter can charge for different features, such as extensive tracking of retweets.

And more specifically, in a tweet, I noted an interesting relationship between Project ReTweet’s lead, Zhanna and Google (her LinkedIn profile says she works for both Google and Twitter):

Does @zhanna work for Twitter or Google? http://tinyurl.com/oa355k

And over the summer at SES Toronto, I gave a presentation, which I’ll be giving again at PubCon Vegas, that detailed the reason and the way Google should be using the Twitter stream to aid in real time search:

This move was coming. Twitter knows they have a valuable data resource on their hands and they’re starting to reel in the 3rd party developers and researchers who’ve been using it for free. I’m just glad I’ve got my 60 million plus ReTweets already indexed.

Read More

The Science of ReTweets Report

After putting together the most recent version of my “Science of ReTweets” presentation and putting it up on Slideshare, I got a lot of great feedback, including that it’s a little hard to understand without my explanations along with each slide.

So I pulled all the data together (including some I’ve never published on this blog) with the basic transcript of the talk I give for each slide into one 22 page PDF. That report has already been featured on Fast Company and if you want to get a copy of it, all you have to do is subscribe to my blog, either by RSS or email:

Once you’ve subscribed, you’ll see a link at the end of each post (including this one) that you can click to download the report.

And if you liked this, don’t forget to buy my book.

Read More

New TweetPsych Feature: Top Lists

Now that there are over 80,000 users indexed by TweetPsych, I’ve added a new feature that ranks users by specific characteristics. For the select traits listed below, you can see the 20 users who scored the highest.

Please remember that this is for entertainment purposes only and that the codes are linguistic terms from LIWC and RID that may not be similar to their normal, English language meanings.

Read the original post for more information about TweetPsych, or read this post for more information about its matching functionality.

Read More