Social Media Research Blog

Community-Driven Moderation in Twitter

Twitter played an important role during the mumbai terrorist attacks. The community that formed around the #mumbai tag, actively discussed how they felt and provided live, uptodate information filtered from different news sources. This was a tipping point for twitter that transforms it from a social tool to a news source. The most important factor here was that the dynamic community that emerged around the #mumbai tag was not constrained to discuss one single topic. Something that News sources struggled with as the developments happened so quickly in this critical event. Most news sources need to stay on a story for at least a few minutes before they can move on to another story.

As #mumbai became popular, trolls showed up on twitter and posted messages with the hashtag only to draw attention to their website or link to other sources of little or no relevance whatsoever to the current crisis. This made me wonder, what if anything could be done in Microblogging environments to restrict users from misusing hashtags. A quick glance over at the current use of #mumbai shows a number of such sources that should probably moderated. I am refraining from naming any particular users but this is something that could be better dealt with by the community as a whole.

One suggestion I have is to create a new hashtag like #ban followed by the user name and the hashtag for which the user should be banned. Once a particular user is #ban tagged by several people from the community -- Twitter can automatically ban the user from further posting on the specific topic. This would be a simple and effective means for a community driven moderation in twitter.

We the Numerati

A quick post: I am almost finished reading "the Numerati" by Stephen Baker. I must say that I had very high expectations from this book and it seems to have come slightly short of it. Dont get me wrong, it is certainly a good book but, it wasn't a very technical book. So many of the topics and ideas presented here might sound quite familiar to someone who is wading in data and algorithms every waking hour. What I really like about the author is the way he treads a fine line between dismissing some of the myths about data miners and highlighting some legitimate concerns in the field. It is a great compilation of interviews and summarizes a number of research topics. A few interesting points/quotes from the book: Be watchful of the fact that in some fields (like analyzing terrorist networks) where lives are at stake, we need to be very very careful. False positives doesnt necessarily mean that it is a non-event. On the other hand, innocent folks can find themselves on terrorist watch lists. Failure can cost lives. From David Sifry's interview in the book -- be cautious of "mistaking correlation for causation". Don't think of privacy filters as add-ons that we can worry about after coming up with the data mining techniques. In Jeff Jonas's words sometimes "repurposing" data can lead to unintended uses. Watch out! Stephen Baker touches upon many different applications and profiles a number of scientists, companies and startups that make up the Numerati. My favorite chapter ofcourse was the "Blogger" and "Terrorist" for its social media and social network related discussions (OK I admit there is a slight bias here :-). And Pranam too is eagerly looking forward to reading the pages that talk about splogs. (I am rather surprised that he wasn't interviewed for this!) Overall, its a good book that caters to a wide audience. But most importantly does a great job at demystifying the Numerati and showing a balanced, informed picture about what we do.

Exploring the Impact of Profile Injection Attacks in Social Tagging Systems

Live blogging from WebKDD 08:

Exploring the Impact of Profile Injection Attacks in Social Tagging Systems
Maryam Ramezani, J.J. Sandvig, Runa Bhaumik, Robin Burke, and Bamshad Mobasher

Explores how folksonomies can be used for social navigation and protect it from 'self-promotion tags'. in profile injection attacks, users create number of identities and add 'tag spam' for malicious intent. Spurl.net is an example of a social tagging system that was inundated with spam and had to shut down.With various entities (resource, tag and users) the profile injection attacks can effect each of the 'navigation contexts' like: related resources, co-occurring tags, recent items etc. The paper goes in depth into the various classes of such attacks. The paper uses del.icio.us crawls for this study that were split into three partitions: low freq, med freq, high freq.

Two main types of attacks discussed:

• attacks on popular tags
• Piggyback attack: force association of a particular resource with another resource to make it look similar.
• Overload attack: associate popular tags with a target URL.
• Focused overload attack: for a specific target users (say those, using the tag coffee) associate the target URL with those tagged as coffee

One interesting point is that piggyback attack is a problem mostly in the Low and medium freq partitions and just 3-5% of fake user profiles injected (using relatively few number of tags) can cause considerable problems in social tagging systems. The authors present various results based on number of tags, number of profiles etc.

I think as tagging systems become more main stream dealing with spam in such environments is quite important. 

Query-log mining for detecting polysemy and spam

Live blogging from WebKDD, 2008:

Query-log mining for detecting polysemy and spam
Carlos Castillo, Claudio Corsi, Debora Donato, Paolo Ferragina, and Aristides Gionis

The paper presents an approach to identify spam from both query logs and usage. The queries are a way to obtain the wisdom of the crowds. This information is used to  tackle spam detection and identify polysemy.

The sources of information used by the authors were:

• Query graphs: query to matched documents
• click graph: query to clicked documents
• view graph : The set of matches that were viewed
• anti-click graph (if the user skipped one of the previous documents from the top 3). This can be thought of as negative feedback.

Further feature extraction  & topics are identified from web directory. The intuition is

"documents that attract queries on many topics and queries have the potential of being spam."

Syntactic features used were: degree of node; the top query terms a document attracts.

Topics are propagated in the click graph using categories from dmoz to queries in the bipartite graph. Two approaches are used for the propagation: weighted avg and topic specific pagerank.The query logs were obtained from Yahoo! and labeled spam collection is WEBSPAM-UK2006 collection.

It was interesting that many polysemous queries were actually country names. For spam detection content + link + usage obtained the best results which was almost same as link+content. 

Public Handle Names and Spam

Well, Techcrunch talks about how the entire MobileMe user email list can be literally scraped off of the site by crawling the public pages for all users. Ofcourse the problem there is that the username is shared publicly (as part of the url) and more importantly, it is tied to the email address, thus making it easy for spammers to collect and accurately compile a list of active email addresses.

This led me to think about a slightly more general problem. Think about your handle name for a second. I go by akshayjava on pretty much every social network, bookmarking site and any and every site that I register at. I am attached to this username and I like it very much. It is very much a part of my online identity. The only problem is that if you know my handle (which is not too hard to find online) you can guess with a pretty good chance that my email address is also tied to the same handle.

I went to my Twitter account and pulled up a list of users who, like me, are fervent Gmail fans. For many of these users Gmail is their primary email address. Of the 15 such folks (close friends/colleagues) I knew at least 12 of their gmail addresses can be matched EXACTLY using their twitter id. And for one person, his friendfeed username can be matched with the gmail id. And one is an uber geek who the only person I know who is THAT paranoid about privacy. 

So I think the problem is that the handle names can be inherently sensitive to spam.

PS: Thankfully, gmail's spam filters do a pretty good job - so much so, that I now forward my official school email to gmail and let it filter all the junk. Due to spam, I have given up on my Yahoo acount totally and declared email bankrupcy there! Yep, you guessed it --- its [email protected]... eat this spammers!