The Man Who Isn’t Intimidated By 38 Million Hashtags

When was the last time you had to search for some new hashtags? For example, because you wanted to reach a wider audience, or just to show you’re always in the know about the new trends in your field?

If you’re at all like me, that was not long ago. And again, if you’re at all like me, you feel that having to sift through the millions of hashtags people use these days is a pretty daunting task.

If this is the case, you’ll be glad to meet Hashtagify’s latest hire, the Research Assistant. I introduced him a week ago; you might remember that he boasts of knowing all the 38 million hashtags we classified at hashtagify.me, to be able to find many new targeted hashtags just by taking a look at your Twitter account, and that he’ll start working next week.

I thought you might want to know a bit more about him. He’s a reclusive guy, so, to give a better introduction, I went to his laboratory and interviewed him for you. This is the transcript of our talk.

Assistant

Dan: Hi Assistant. So, the rumors say that you know everything about more than 38 million hashtags. Is that true?

Assistant: Hi Dan. Well, to be honest with you, I don’t actually know everything about those 38 million hashtags. But I know a lot about them. And I’m always on the lookout for new ones to study. As a matter of fact, just during the last 10 minutes, I found 38 more. Right now, the exact number of hashtags I know about is 38,476,189.

OK, the quantity is impressive. But what about the quality? Are all those hashtags really good?

This is an interesting point. Actually, it turns out that lots of hashtags are too generic for any targeted message; others are too loved by spammers; others still were great a few months ago, but now they’re dead in the water. That’s just why I’m always learning new ways to classify and filter them, using information about the hashtag users, associations, languages, timing, and many other interesting signals. It’s no easy task, but they tell me I’m getting better and better at this.

Let’s talk about personalization. After you filter out the hashtags that may look popular, but aren’t really useful, how do you decide which ones are the most targeted for a specific Twitter user?

First of all, I study up to 3,200 of the last tweets that the user sent, and analyze the hashtags they use, the language, and some other technical stuff. I then try to understand if the user has different areas of interest to talk about, using a technique called clustering. For each cluster of hashtags, I then find the most interesting hashtags that the user has never used.

When you say “interesting hashtags”, what do you actually mean? And usually, how many interesting hashtags do you find for a user?

Hashtagify AssistantA hashtag can be interesting for many different reasons. For example, it could be a newly trending hashtag in a related field. It may have a popularity that isn’t very high, but is very targeted. I try to create a good mix and show the user around 200 options to choose from; the user can sort them by popularity, trend, and correlation, and also look at lots of details to better understand the hashtag if it looks interesting. Users can also discard hashtags that they know aren’t good for them; this really helps me to learn and be even more targeted in the future.

Great, I’m sure all our advanced users will like the possibility to start from an already sorted and filtered pool of candidates, and still be able to choose by themselves. But what about beginners? This still looks a bit difficult for them, couldn’t you make things even easier?

Come on Dan! You already know that I’m much better at helping users who already know their way around hashtags. Isn’t that the reason why you also hired Hashtagify Tutor? I just do the analysis; then, for those who don’t want to check lots of hashtags and meddle with all the finer details, he can take over and guide them step by step…

assistant-sharing-300

Dan: Don’t worry, I remember perfectly well our deal. I just thought that this could be the perfect question to finish this interview, and link to our next one with Hashtagify Tutor. So, Assistant, thank you for your time, and I’ll leave you to your analyses now. Maybe, before the great launch next week, you’ll even learn some new tricks!

Assistant: Thank you Dan. You know that I’m a lab rat and I’m not much into interviews, but I really hope I could answer some of our readers’ curiosity about my work. And, while thanking them for staying with us until the end, I’d like to remind them that sharing is caring. And remember… I’m going to read all your tweets!

And The Most Popular Hashtag In The World Is…

…#EMAzing!

Yes, #EMAzing was the most tweeted hashtag in the world last week. Not bad for a hashtag that just entered the top 30 chart; as a matter of fact, if you consider the full last month, #EMAzing was only 8th, left in the dust by #غرد_بذكر_الله, an Arab hashtag that tops the monthly chart and could be translated as “Tweet remembrance of God”.

But the real news, for us, is that starting today you can easily keep an eye on the top 30 hashtags for last month, last week, and just breaking out, and for 35 different languages: We just published hashtagify.me Popular Hashtags Charts, a new free feature for all those interested in hashtags.

Want to know which were the top 30 hashtag during the last week in, say, French? Just go to hashtagify.me, and click on our new Popular Hashtags menu

popular_hashtags_menu

Next, click the language selector and pick French

popular_hashtags_language

Last, click the Last Week tab

popular_hashtags_period

You can now see the top hashtags, with their rank (and rank change), their popularity, their popularity trend, and their main language – ie, the language that’s most commonly used with that hashtag.

As a matter of fact, a hashtag that is the most used in French tweets can be also used in other languages – and, like in the example above with #EMAzing, it can be used mostly in English. This is interesting, because it allows you find out which of the top hashtags are “native” to the language you’re checking.

So, this is how you can find the top hashtags in many languages. The data is updated daily – and, for the “breaking out” hashtags, in real time. We really hope you’ll enjoy this new free feature. And, if you like it, please, don’t forget to share your likes with your friends!

 

 

 

 

Tracking Hashtags By Language

photo credit: zinjixmaggir via photopin cc

Since we released our Hashtag Intelligence tool, the most requested addition has been the possibility to track tweets for an hashtag only for a given language. This is helpful both for hashtags which have different meanings in different languages, and for common hashtags where you only want to focus on users for a given language.

Today we’re glad to announce that this feature has been added to CyBranding Hashtag Intelligence. When you choose to track an hashtag, you can now choose to filter only tweets that are written in a given language. If you do so, trends, influencers and correlations will be computed considering only tweets that use that hashtag AND are classified by Twitter as written in the chosen language.

One caveat though: If a tweet doesn’t contain any word that allows Twitter to recognize the language, that tweet will be excluded from the analysis.

If you’re interested in getting intelligence about an hashtag only for one language, you can try hashtag intelligence now.

Hashtagify Pro private beta

Lately I’ve been hard at work on Hashtagify Pro, a new tool that lets you track a specific campaign or subject (not limited to hashtags) on Twitter and analyze which influencers are impacting it and how.

Today is a big day: We are ready to start a private beta!

You can go to pro.hashtagify.me and take a look at the new website, where you can also find a Demo/Tour that shows the kind of analysis you can do with Hashtagify Pro.

If what you see interests you, you can apply for a free beta account using the link in the home page. Beta accounts will be activated as soon as there are free resources on the server.

We’re also very interested in your feedback: Comments, glitches, ideas, suggestions. Hashtagify Pro is still in evolution and your suggestions now can have an important impact.

So, let us know what you think!

PS: Hashtagify Pro works best with a recent browser. IE only works with version 9.

Top influencers: The new visual exploration tool (beta)

Influencers graphDid you even wonder who the top influencer about the #debt crisis is on Twitter? Is it a Republican? A Democrat? An independent – maybe an official news source?

I did, and to answer that question – and countless more about other hashtags – I just published on hashtagify.me the first beta version of a new “top influencers” feature.

With this feature, when you visually explore Twitter hashtags, following their relationships, you can also see up to 6 of the top influencers for the selected hashtag. These users are listed by name, ranked by their estimated influence, and shown on a graph where you can also see their relative influence (y-position), how specialized they are on that hashtag (x-position), and how many followers they have (bubble size).

This feature is still in beta and the hashtags usage data is still being collected: This means that, especially for the less used hashtags, the influence estimate isn’t very precise. Still, while I’m working on augmenting the data collection rate for this kind of data, you can already get an idea about the influencers on your topics of interest. And a similar feature is in the works about the top websites for an hashtag: Stay tuned!

Oh, and by the way: It looks like the top influencer about #debt is @MikeBloomberg, the Republican mayor of New York, followed by @WestWingReport, an independent White House journalist – you can see it for yourself here. Where are the Dems??