About these ads

Twitter to Clean Up Trending Topic Searches – Is This that Reputation Thing?

On Twitter’s blog, they announced an initiative to clean up the spammy tweets that often appear for trending topics. As described from the post:

Today we’re starting to experiment with improvements to trends that will help you find more relevant tweets. Specifically, we’re working to show higher quality results for trend queries by returning tweets that are more useful.

MG Siegler over on Techcrunch and Jolie O’Dell of ReadWriteWeb wonder how this will be accomplished. My guess? Twitter is starting some sort of reputation score for accounts. The lowest-of-the-low accounts in terms of reputation will get shunted aside.

For background on this reputation thing, see a couple earlier posts on this subject:

Included in that second link is this quote from a Rafe Needleman post in May 2009:

Twitter Search will also get a “reputation” ranking system soon, Jayaram told me. When you do a search on a “trending” topic–a topic that is so big it gets its own link in the Twitter.com sidebar–Twitter will take into account the reputation of the person who wrote each tweet and rank the search results in part based on that.

Curious to see how this one plays out.

About these ads

How Should Tweets Be Ranked in Search Engine Results?

Tweet searchAnyone remember when Loic LeMeur had the temerity to suggest Twitter rank its search results by the number of followers people have? His post, with 109 comments and reaction from Michael Arrington, Robert Scoble and many others, clearly struck a nerve.

Fast forward to the past couple weeks. Both Microsoft Bing and Google announced deals to provide tweets in search results. Let me say that again: Google and Bing will be providing tweet search results!

Bing’s version is the first out the gate. In light of the earlier brouhaha, this may come across as insensitive…but I have to ask:

How should tweets be ranked in Bing and Google search results?

I hope your answer isn’t, “I wouldn’t.” Because that’s contrary to what made Google such a global powerhouse used by billions every year. And why Microsoft is working hard to increase Bing’s market share. Google and Bing built their business by presenting search results based on the authority of websites. This system of authority (e.g. PageRank) makes the results relevant to users.

So what about running searches for tweets? Should their presentation be utterly devoid of any authority ranking? Does it make sense to just show the latest tweet containing a given term? After all, that would simply be imitating what Summize (aka Twitter Search) does.

First, a good question to ask is, why do people want to search tweets? How does this differ from web search?

Why Are You Searching Tweets?

To my mind, there are three use cases where people will search for tweets rather than search for websites:

  1. Find people
  2. Find latest on a subject that won’t show up in search engines yet (lack of indexing, lack of authority)
  3. Jump into conversations on something

Find people: You’re interested in a topic, and want to find others who can either improve your knowledge on it or with whom you want to connect. This is using Twitter as people search. The model for all of here is, you are what you tweet. It’s what makes you findable to others.

In this case, my sense is that people will have an desire to find those who would have the most authority on a given topic.

Find latest on a subject: The appearance of an article or blog post in the search engines can take a while. That contributes to the challenge of finding the latest. But the more pressing issue is the display of new articles in the search results. A good article or post on a subject, such as Enterprise 2.0, is likely not going to be ranked very high in the Google or Bing search results. No one links to the article yet, and it competes against a bunch of other incumbent articles in the search indexes.

If something shows up on the third page of Google’s search results, does it really exist?

This issue is even more pernicious for current events. The San Francisco Bay Bridge has been closed for several days now. It seems every estimate about when it will reopen has been wrong, meaning we all have to scramble to figure out our commute for the next day. To get the latest on the Bay Bridge, I searched Google, including the aggregate news results. Everything was too old when I did that, reflecting previous pronouncements. I needed what people knew right now. I went to Twitter, and found tweets that told me the latest status. Very helpful.

To find the latest on topics, I think there is a role for leveraging some sort of authority. People who have established credibility can be good first filters on what’s relevant and useful. For Enterprise 2.0, what is Dion Hinchliffe tweeting? For the Bay Bridge, I most trusted the KTVU tweet I saw.

Jump into conversations: This is Twitter as water cooler. You know something is going on. But how do you connect with people? Searches are good for this. Hash tags for conferences or big stories. Take the recent fraudulent #balloonboy story. It definitely captivated everyone. But even now, you’ll see tweets like this:

Watch top quality streaming Movie -> Up here http://cli.gs/dpNT5N Make $ From Home #mileycomeback #balloonboy

What is that? That’s someone taking a popular hash tag and polluting the search stream with spam. Again, a case where adding some authority to the tweet search rankings will help.

Tweet Authority Criteria

Keep in mind that “authority” is used in the context of Google and Bing searches. Of course web searches miss many authorities on subjects, but they work pretty well for giving relevant information.

I categorize the bases of authority in three buckets:

  1. Relevancy of tweet stream to a subject
  2. Crowdsourced signals of authority
  3. Effectiveness in providing relevant content

As a point of reference, Bing’s initial measure of relevance was reported to be the number of followers a person has. Let’s look at the three categories of authority.

Relevancy of Tweet Stream to a Subject

The first basis for authority should be…does someone tend to post about a given topic? Frequency of posts are a good marker that a person has something of interest to share. If someone is going to be deemed an authority on a subject, I’d expect a fair number of tweets related to it.

One twist that would make this better. A semantic basis for linking terms. For example, if some one searches on Foo Fighters, consider people whose tweet streams include posts about “music” frequently as having higher authority.

Crowdsourced Signals of Authority

What does the crowd think of a given person or tweet? Let’s start with a single tweet. If someone posts something on a given topic, and it gets retweeted a lot, that should count hugely in terms of its authority for a given topic.

OK, now for the general stats. How many followers does someone have? Yes, it’s getting gamed. So the presence of a high number of followers isn’t an automatic definition for authority. But it does have relevance in constructing authority.

The benefit of computing this for users is that the authority of those who follow a person can be an input into his or her own authority.

Next… Twitter Lists. Number of followers is not the end of the story. Lists have two characteristics that can be used to compute authority. First is the number of Lists one is on. Tim O’Reilly is on over 2,500 Lists. No surprise – he really made ‘web 2.0′ ubiquitous in our culture.

But an even better indicator of authority is embedded in Lists. How does the crowd characterize a person? Those Lists are valuable for granting higher authority for a given topic.

Effectiveness in Providing Relevant Content

When someone tweets, how do people react? Robert Scoble has a good take from his blog post:

  1. Number of retweets of that tweet
  2. Number of favorites of that tweet
  3. Number of inbound links to that tweet
  4. Number of clicks on an item in Twitter search

I particularly like that #4 item – number of clicks. Once these tweets are in the Google and Bing search results, the clicks can be measured. These are powerful bases for measuring someone’s authority.

I’d add a measure for how often a shared link is clicked; say bit.ly’s click information. While the actual number of clicks tracked by bit.ly is wrong, let’s assume it’s wrong in a similar fashion for everyone. So the bit.ly clicks counts can give a measure of relative effectiveness in providing content.

What Do You Think?

That’s my somewhat exhaustive description of inputs for ranking tweets in Google and Bing search results. There’s more that would be needed. I can think of incorporating some element of time decay in how tweets are presented as well. But this post is long enough.

What do you think? How would you rank tweets in the big search engines?

Use Your Company Blog to Catch Search Term Typos

If your company or product name can be misspelled, this is for you.

At Spigit, a prospective customer related this to us recently. A few months ago, they had heard of Spigit in one of the usual ways – reading, word of mouth, etc. At some point, they decided to learn more. It probably went something like this…

“What was that innovation software company again? Oh yeah, SPIGOT.”

Notice the typo there. Or maybe Spigit is better termed the typo.

Anyway, first they tried http://www.spigot.com. But that leads to someone sitting on that domain for quite a while. Confused, they did the next logical thing. They searched on variations of SPIGOT:

  • spigot software
  • spigot idea management
  • spigot innovation management
  • spigot gumbo

Unable to find Spigit, they moved on with their life. Until last week, when the prospect was talking with one of our customers, who mentioned SPIGIT. Ding! The prospect remembered their interest, got the right spelling and we are talking, several months later.

Obviously, this presents something of a problem. How to catch those people actually searching for SPIGIT, but typing SPIGOT? We do maintain Google AdWords covering this. But what about in the search results themselves?

At first blush, two options are apparent. One, use the word SPIGOT on our website. But that would be confusing to visitors. It would look like we don’t know how to spell our own company name, or maintain a typo-infested website. Two, take advantage of those meta tag keywords, adding SPIGOT to them. But Google recently confirmed that those meta tag keywords have no effect on search results. None.

But there was one other way to do it. Why not take advantage of our search engine-indexed blog? Publish a blog post specifically designed to include the misspelled company name, along with additional relevant search terms. That way, there will at least be something in the search results for people honestly trying to find your company.

So I wrote this post, Spigot Innovation and Idea Management Software Platform

The post is intended to let searchers know why it exists, and redirect them to the website home page:

Spigot blog post

I’m no SEO expert – honest, check my Twitter bio! But I figure this may help get the attention of those using SPIGOT to find SPIGIT.

Another use for the company blog.

Three Reasons You Need to Be on FriendFeed *Now*

FriendFeed Triple PlayFriendFeed has got to be one of the most innovative companies around these days. It seems every week, it’s hatched something new with its service. That alone makes it worth being there.

Then there’s the interactions. When those are rocking and rolling, it’s a lot of fun. Even a few Likes and comments are worth the experience. Of course, not everyone is engaged enough on the service to fully benefit from that. Which is something I completely understand, by the way.

I’ve got three reasons you should be on FriendFeed now. Not for the conversations. Not for the real-time experience. But three reasons that will be valuable to you personally.

The FriendFeed triple play.

#1: Google Juice

You likely know the background of much of the FriendFeed team – Google. Yeah, these guys know search. Even more importantly, they know something about how Google manages search.

So it comes as no surprise that FriendFeed can rank pretty highly in Google search results. Here’s a favorite example of mine.

Alex Scoble (yes, Robert’s brother) is planning his wedding reception. One candidate location for the reception was the Hillsboro Cultural Arts Center. But the managers of that location were not very flexible in working Alex and his fiance. On FriendFeed, Alex posted about the Hillsboro Cultural Arts Center, with some comments explaining why he was not going to use them. It’s not a flattering portrayal of the Center.

Well, check out what a search on the Center’s name returns: Alex’s FriendFeed entry is the #6 result.

Not something that Center wants in their search results, but a great way for Alex to let others know about his experience with the Center.

FriendFeed’s Google prowess shows most strongly in name search results.

On this FriendFeed discussion, Mark Trapp noted that his FriendFeed account always ranks higher than his personal site. Well, if you run a search on mark trapp, you’ll also see that his FriendFeed account is ranked #1, ahead of some attorney named Mark Trapp. Without FriendFeed, that attorney would own the #1 search result.

And FriendFeed member Brian Chang noted this back in January: “I just discovered that my FriendFeed comes up on the first page of Google search results for my name. I think that’s the first time something of mine has actually done that.” A quick search on brian chang reveals he’s not on the first page, but he’s still there, among a lot of brian chang sites.

FriendFeed shows up #3 on a search of my own name.

#2: Personal Content Database

Let’s assume you participate in more than one social media site. Maybe Twitter, Del.icio.us, blog and Flickr. FriendFeed, of course, lets you pipe all of that into its site. If nothing else, having one place where you can search for all your content easily is reason enough.

Returning to the search pedigree of the FriendFeed team, there’s a really good reason to have your Twitter account piped in. It makes it easy to find your tweets. As Louis Gray noted last week, it’s much easier to find tweets in FriendFeed than it is with Twitter’s search. On FriendFeed, you’ve got an archive of all your tweets. On Twitter, you don’t.

Here’s an example. I’ve tweeted a few times about “friendfeed” and “search”. On Twitter, I get one result when searching my tweets for those words. On FriendFeed, I get many, as I’ve actually written those two words in a number of tweets. See the screen shots below, which show only a portion of the FriendFeed search results:

FriendFeed vs Twitter search

Remember when the bookmarking service Ma.gnolia lost all its users’ data? If you had saved your bookmarks there, you were out of luck. There was no recourse to getting that data out. In a post here, I noted that bookmark service Diigo lets you save to De.licio.us simultaneously. The idea being that you needn’t rely on just one service, in the wake of Ma.gnolia’s data loss.

Well, that same notion of mitigating your risk carries over to FriendFeed as well. I pipe all my Diigo bookmarks into FriendFeed. So now I have my bookmarks in three places: Diigo, Del.icio.us and FriendFeed. And when I need to look up one of my bookmarks, where do I usually search? FriendFeed.

#3: Tracking Web Content about What Interests You

Probably my biggest use case for FriendFeed is as a tracking platform for various topics I care about. I’ve got a room to track Enterprise 2.0, which I augment with following 70+ individuals from that world. I’ve got a room for tracking my company Spigit, its competitors and the innovation management field.

The importance and value of tracking the Web this way is something I’ve discussed here many times. You can visit those prior posts for greater detail on how and why.

But I’ll say this. Whenever I need to get up to speed quickly on something, setting up these FriendFeed Rooms and Lists is one of the first things I do. You’d be amazed at how effective they are. And unlike a lot of social media monitoring programs, FriendFeed doesn’t cost you a thing (although some would pay for these features).

Wrap-Up

Those are three powerful reasons you should be on FriendFeed. Right now. They don’t require you to get in there and apply Likes and comments to entries if that’s not your thing (that’s powerful in its own right, but more the province of social networks). But you will immediately start benefiting from what the service offers.

Know anyone holding out or just unaware of FriendFeed? Send ‘em this post.

My Ten Favorite Tweets – Week Ending 030609

From the home office in Damascus, Syria….

#1: Twitter has another huge growth month in February, per compete.com: http://bit.ly/aJ0p

#2: It always cracks me up when people say Twitter is nothing more than glorified IRC (http://bit.ly/KD3H6). Most people I know never used IRC

#3: A lot of posts like this lately: “Twitter destined to replace Google Search” http://bit.ly/14G7nn Some truth, but overstated.

#4: On Enterprise 2.0: “There is a big difference between an integrated user experience and a suite.” ReadWriteWeb http://bit.ly/6Njb

#5: Flashes of insight cannot be willed, they are spontaneous – Willam Duggan, Strategic Intuition

#6: Visa commercial uses Smashing Pumpkins “Today” as its theme. Visa gains some cool points.

#7 Anyone remember the Nestea Plunge? I have this game with my 4 y.o. son where I catch him falling backwards. Call it the Nestea Plunge.

#8: Just want to note for the record…last night’s ’24’ was great. The show is strong this season.

#9: I miss the plastic bags we’d get from grocery stores here in SF. They were perfect for the little trash cans around the house. #ecoprogress

#10: My 4 y.o. son Harrison is a huge fan of the PBD Kids website http://pbskids.org/ Well done, incl. games with his fave PBS characters.

My Ten Favorite Tweets – Week Ending 020609

From the home office in Victoria, Australia…

#1: Interesting convo w/ colleague. Is there any risk to tweeting that you’re traveling on vacation? Burglars searching for such tweets?

#2: Guy was turned down for a job because he switched majors his freshman year of college. Say what? Details: http://bit.ly/23yHBT

#3: FriendFeed continues to roll out the powerful features. Latest? Much more granular search options, very helpful: http://bit.ly/VNYX

#4: I’m impressed w/ Yammer’s hustle. If you’re doing an internal preso on it, they’ll help you with the preso. Smart. E.g.: http://bit.ly/PR1A

#5: RT @beccayoungs I really do think the Amazon Kindle will be a game-changer. Check this out – Kindle to be a $1B product http://tr.im/eflz

#6: RT @barconati Oh no! Yahoo briefcase is closing. Believe it or not I still use it. More out of habit than anything else http://tr.im/e88z

#7: Mike Gotta on the rise of employee social profiles inside companies: http://bit.ly/135Vz Benefits and advice w/ nice Connectbeam shout-out

#8: Check out http://www.socialwhois.com/ Lets you search for people on based on keywords in their lifestreams. Very cool.

#9: RT @lehawes w00t! I made the Wall St. Journal today! Page A11 in print edition or online at http://bit.ly/iRcH

#10: After the WSJ coverage…@lehawes blogs about being included in a recent WSJ article: Taken Out of Context http://bit.ly/17aRy

Google Alerts Ain’t Working – Why Don’t They Use Attention Signals?

Do you use Google Alerts?

I do. I’ve got seven of them set up. Generally, they’re pretty helpful. But they often suffer in terms of quality. Here’s a few comments with regard to that:

#1: @VMaryAbraham so am I. Google alerts and blog search have been delivering really bad quality results lately. Old and spam.

#2: Google Alerts actually sent me some useful info today instead of the usual mess of bizarre kitchen sink links from random years and places.

#3: @JesseStay my Google alerts are similarly getting less useful

One of my alerts is for ‘Enterprise 2.0′. I’m doing a pretty good job of staying on top of things in the Enterprise 2.0 Room on FriendFeed, but the Alerts are good back-up. And Google Alerts are the most common keyword notification service that people use.

So this is my question: what determines the links we see in those daily Google Alerts?

I ask this because of a recent experience with a well-received blog post that was not included in the ‘Enterprise 2.0′ Alerts. Compared to another post that did make it in to the Google Alerts, I find myself mystified as to what algorithm Google is using to generate its Alerts.

It’s not to say that Google Alerts don’t deliver some good posts – they do. But they seem to miss the mark pretty often as well, as the quotes at the start of this post show. I’ll relate my own experience below, based on objective factors, as opposed to my own declaration that “It was good post dammit!” ;-)

Tale of Two Blog Posts

I checked the Google Alert of January 18 for Enterprise 2.0. Here’s what I saw (my red highlight added):

google-alert-enterprise-20-011809

The highlighted post is a schedule of Web 2.0 sessions for Lotusphere 2009. If you’re into Lotus, good stuff. One session at Lotusphere was titled “INV101 –   From Web 2.0 to Enterprise 2.0: Collaboration, Productivity, and Adoption in the Enterprise”. Hence, its inclusion in the Enterprise 2.0 Google Alert.

I use that entry as a contrast to a post I wrote on the Connectbeam blog, titled Three Silos That Enterprise 2.0 Must Break. It’s a post that pushed some definitions of what a silo is and where knowledge management needs to move to. It was well-received, with a number of attention signals like Del.icio.us bookmarks and tweets.

And you’ll notice it’s not listed in the Alerts email above, or in any earlier ones. It was included in my ‘Connectbeam’ Google Alert. So I know Google had indexed it in its blog database. But it was not in the ‘Enterprise 2.0′ Google Alert. Which got me to wondering, what does it take for a post to make into the daily digest of Google Alerts?

I put together a comparison of the two posts: the Lotusphere post, and the Connectbeam Three Silos post. I wanted to see where the Connectbeam post falls short. Take a look:

google-alerts-tale-of-the-tape

The table above includes some typical Google attributes: PageRank, term frequency, links. It also includes the next generation of content ranking: comments, bookmarks, tweets and Google Reader shares. On either basis, it’s surprising that the Lotusphere post made the cut, while the Connectbeam post didn’t.

So I’m still trying to figure out what makes the difference here. Clearly, the Three Silos post struck a bit of a chord in the Enterprise 2.0 community. I know this not because of links by other bloggers (although they were there), but by the other Web 2.0 ways people communicate what’s of value to them.

How about it Google? Time to update your algorithms to include attention signals from our growing use of social media?

Follow

Get every new post delivered to your Inbox.

Join 662 other followers