The debate on Facebook versus Twitter, and which one is in for the long haul will continue. So far, some information nuggets I found particularly interesting include:

Twitter versus Facebook: Should you Choose One?

Twitter Pros: Easy to navigate and update, link to and promote anything, Reach far beyond your inner circle of friends

Facebook Pros: Application mashup; find people, make connections, email, instant messaging, image/video sharing, etc., Most people can quickly grasp the value of connecting with friends, family and established contacts; some people report they use Facebook instead of email and IM

Facebook vs. Twitter: How will you stream your world?

.. Facebook’s advantage is that the revamped news feed can handle different types of content, too: it’ll have actual photos and event listings instead of TwitPic and TinyURL links. Filtering controls won’t require a third-party app like TweetDeck. On the other hand, Twitter is obviously more open-ended. The messages on it are public and accessible, rather than hidden behind a log-in wall. As useful and innovative as the Facebook news feed may be, it’s not searchable–and Twitter clearly hopes that its search feature, which it built in with the acquisition of Summize last year, will be a sort of secret sauce.

Honestly, though, with the amount of buzz about both Facebook and Twitter as the future of real-time information, I give the advantage to whichever one can make all this content less of a mess.

When Do You Use Twitter Versus Facebook?

If I want to connect with someone I don’t know, either for business, social, or personal reasons, I first look the person up on Twitter.

Lets face it, there is nothing quite like Twitter for breaking news.

Twitter could be seen as one massive introduction system, where users recommend other users both through retweeting and mentioning the person using the @username option.

More of my Facebook friends live closer to me geographically than those who follow me on Twitter.

If I am trying to connect with someone that I know, I am more apt to use Facebook, if I know the person uses both Facebook and Twitter.

If I am looking for feedback on an issue, particularly personal, I am more apt to post it on Facebook.

Facebook vs. Twitter (infographic)  (RT? via? flickr)

How can they compare Twitter as a “competitor” of Facebook? They aren’t in the same category! One is a sprawling social network, while the other is just a microblogging tool.

As features converge on these two social networks, these speculative debates, and eventual reality will get really interesting. Though I have my own subjective take on the topic, I decided to get as far as objective I could get, through an experiment on Pickfu via the Amazon Mechanical Turk (AMT). On the AMT sample, as of today:

• 14% of users prefer Twitter, while 86% prefer Facebook (Update: Thanks Matt)
• Twitter is more popular in the older demographics
• Twitter users are more affluent
• Twitter users are better educated

As part of this experiment, I also requested the turkers to comment on their choice, as to why they preferred one over the other. Here’s a tag-cloud of their responses, first for facebook:

and next for twitter:

In general, most of these comments on an aggregate, confirm those seen in blog postings, blog comments, and also studies carried out by large market research firms. Here’s my take-away though: AMT provides an interesting new perspective, for cheap.

Update: The comment below made me dig into raw text responses further. What I uncovered though, again, is the very motivation to computational social media research, and related conferences (see ICWSM 2010). I’ll leave out further analysis as a future exercise, and comment on them in follow-up posts. For now, I highlight a few representative user comments (as-is with misspellings etc.), not all of which I agree with.

Turkers who preferred twitter over facebook, point out the following (in their own words):

• Twitter moves faster and is more about people dealing with events.
• I think twitter is less pretentious and more user friendly
• Gives me an excuse to input limited number of words. Short & Quick!
• easy access and user friendly
• At the moment less malware.
• In my opinion Facebook is just a fad.
• newer, hip, quicker
• It’s  more informative while being less time consuming.
• i like twitter because I follow some shows on tv and radio, thanks.
• I find facebook is quite a commitment and once you’re in, you ‘can’t get out’, so to speak. Twitter is a more relaxed community, and you can leave without being bugged about it.
• Twitter is simpler and has much less dangers associated with it. Easier to use. Does not collect your information as much as facebook does.
• Twitter is more easily accessible to me.  I really enjoy the simplicity of it - don’t feel overwhelmed with all the this and that and the other thing that clutters up facebook.

On the other-side, turkers preferring facebook over twitter, say:

• I don’t like twitter’s concept, I don’t care about reading people’s statuses. I’d rather see photos and have more of an interaction than unnecessary details on a person’s day.
• There is more to do on FB than twitter.
• More friends there.
• I like seeing more info on facebook, and can still ‘chat’ there.
• I use facebook to keep in contact with friends at different colleges, but I have no use for twitter
• Facebook has more functionality
• Because they layout is prettier and it seems like their are more options and gadgets to play around with all on one site.
• My network of friends is mostly on facebook, not twitter.
• It’s older so I’m more used to Facebook than to Twitter, plus it has more applications.
• I use Facebook quite often. I have never used Twitter and most likely won’t because Facebook offers the same service as Twitter and so much more.
• There is more to do on Facebook.
• I preface facebook because it’s more personal. Twitter seems more “gossip oriented” and focused on boring details that I don’t care about.
• I don’t usually post my own statuses.
• I hate Twitter, I think people on it think the are too self important. No one cares what you are dong at all times.
• Twitter is basically status updates - not interested. I prefer seeing people’s photos and like facebook better for staying in touch.
• fcaebook has a lot of things to do and is more entertaining than twitter
• there is more to read on facebook
• Facebook has more features, and more people I know are on facebook than twitter, though I love twitter’s simplicity, and would hate for it to become more complicated.
• Less irrelevant junk, i.e. I am going to mow the lawn today. Better pictures.
• Its a social netwirk with more informative info and the best way to search and communicate with friends and family
• At least with facebook you get to see pictures of your friends too.
• Facebook is more interactive than twitter.
• You can communicate more often and more information with Facebook.
• I like this site because I can show pictures.
• more personilized
• More to do on facebook - I like seeing my friends’ photos and profiles rather than just following celebrities, which doesn’t really interest me.
• I never use twitter at all.  The whole concept of twitter is just plain dumb.
• Because it is not limited to status updates.
• I prefer Facebook because you can have a more detailed profile.
• Facebook provides me varios applications and surveys which are very funny and intresting
• I am more likely to connect with old friends and family members who live far away. Twitter is good for marketing and networking. Facebook is better for maintaining relationships.
• It helps me keep in touch with my friends — more of them are on Facebook than Twitter.
• my friend use this site.
• Because most of my friends are on Facebook, they don’t use Twitter, and I get charged for every text message.
• I like the mutlitude of applications therein.
• It is more established, I am more used to using it, and everyone I know has an account on it
• Most of my friends use facebook and it also has a lot more features like photos and communities.
• I only know 2 people on twitter whereas almost all my friends have a facebook account.
• I am simply more familiar with facebook and find it easier to use.
• I like its functionality and i have more friends at facebook
• I understand more about how it works, and I’m not interested in minute by minute byplays of someone’s day.
• I find the interface quite user friendly as compared to twitter
• It has more number of features than on Twitter and is more user-friendly. People get to interact more in facebook than in twitter.
• I prefer facebook over twitter because I have more friends on facebook.I also like the apps. i can send to friends on facebook.
• Most of my friends, school mates and most of the people i know use facebook to keep in touch with each other. And plus they had nag me to join facebook for a very long time.
• Facebook doesn’t limit the length of posts. I still get to keep up on my friends.  Twitter seems….narcissistic.  Nobody is so fascinating I need to know what they are doing umpteen times a day.
• I like both sites, but I mainly use Twitter for news updates and Facebook for social interaction.  Because you can see the comments directly linked to people’s posts it is more user friendly than twitter.
• I dislike the concept of divulging personal information on the internet, but facebook seems more secure than twitter and does not overwhelm me with useless information about the day to day lives of people. Twitter is just TOO much. I would rather not know the little unnecessary details about peoples lives.
• I prefer facebook because it allows for more depth as far as information that can be about me and my friends. Twitter is very shallow.
  because it can satisfide me rgarding c0mmunicating my friends, and i can enjoy it well.
• Twitter seems entirely self-involved and mostly inane. Facebook at least makes it easy to share interesting links, pictures, have longer discussions, etc.
  I prefer the interaction I can have with other people on FB (in comparison to just commenting on someone’s twitter update), am too busy, and not interested enough to comment on my every move (via Twitter), and I don’t know enough people who actually use Twitter to find in necessary to have an account with.
• Most of my friends and relatives are also on facebook where we all share photos.
• More established and already around a while.  Twitter still seems like an overhyped product.  Facebook also seems more ‘warm’ where Twitter seems more laden with commercialism and restaurants offering coupons for saying they are good.
• Facebook offers much more ways of communication with friends.
• I like them both, actually. I use facebook for work and family (mostly family and friends) and twitter for work.
• Twitter is more for self-absorbed, egotistical people (elebrities) who really think everyone cares about what they’re doing every minute of the day.  FB offers more to do and more ways to communicate with friends
• I prefer Facebook as I can do much more with my account. I can poke my friends, challenge them to a quiz etc.

The CIKM organization recently released their accepted papers from 2009. The full list is here. There appears to be an increase in the number of papers from information retrieval, especially search ranking, and hence the regression problem.

Some papers I am looking forward to include:

• A Unified Relevance Model for Opinion Retrieval — Xuanjing Huang (Fudan University), W. Bruce Croft (University of Massachusetts Amherst)
• Mining Data Streams with Periodically Changing Distributions — Yingying Tao (University of Waterloo), M. Tamer Ozsu (University of Waterloo)
• Fast Shortest Path Distance Estimation in Large Networks [PDF] — Michalis Potamias (Boston university), Francesco Bonchi (Yahoo! Research), Carlos Castillo (Yahoo! Research), Aristides Gionis (Yahoo! Research)
• Adaptive Relevance Feedback in Information Retrieval — Yuanhua Lv (University of Illinois at Urbana-Champaign), ChengXiang Zhai (University of Illinois at Urbana-Champaign)
• Detecting Topic Evolution in Scientific Literature: How Can Citations Help? — Qi He (The Pennsylvania State University), Bi Chen (The Pennsylvania State University), Jian Pei (Simon Fraser University), Baojun Qiu (The Pennsylvania State University), Prasenjit Mitra (The Pennsylvania State University), Lee Giles (The Pennsylvania State University)
• What Happens after an Ad Click? Quantifying the Impact of Landing Pages in Web Advertising — Hila Becker (Columbia University), Andrei Broder (Yahoo! Research), Evgeniy Gabrilovich (Yahoo! Research), Vanja Josifovski (Yahoo! Research), Bo Pang (Yahoo! Research)
• Personalized Social Search Based on the User’s Social Network — David Carmel (IBM Research Lab in Haifa), Naama Zwerdling (IBM Research Lab in Haifa), Ido Guy (IBM Research Lab in Haifa), Shila Ofek-Koifman (IBM Research Lab in Haifa), Nadav Har’el (IBM Research Lab in Haifa), Inbal Ronen (IBM Research Lab in Haifa), Erel Uziel (IBM Research Lab in Haifa), Sivan Yogev (IBM Research Lab in Haifa), Sergey Chernov (Leibniz University)
• Characterizing and Predicting Search Engine Switching Behavior — Ryen W White (Microsoft Research), Susan T Dumais (Microsoft Research)
• Improvements That Don’t Add Up: Ad-Hoc Retrieval Results Since 1998 — Timothy G. Armstrong (The University of Melbourne), Alistair Moffat (The University of Melbourne), William Webber (The University of Melbourne), Justin Zobel (The University of Melbourne)
• Joint Sentiment/Topic Model for Sentiment Analysis — Chenghua Lin (University of Exeter), Yulan He (The Open University)
• Graph-based Transfer Learning — Jingrui He (MLD SCS CMU), Yan Liu (IBM Research), Richard Lawrence (IBM Research)
• Terminology Mining in Social Media — Magnus Sahlgren (SICS), Jussi Karlgren (SICS)
• Generating Comparative Summaries of Contradictory Opinions in Text — Hyun Duk Kim (University of Illinois at Urbana-Champaign), ChengXiang Zhai (University of Illinois at Urbana-Champaign)
• Practical Lessons of Data Mining at Yahoo! — Ye Chen (eBay Inc.), Dmitry Pavlov (Yandex Labs), Pavel Berkhin (eBay Inc.), Aparna Seetharaman (Yahoo! Inc.), Albert Meltzer (Yahoo! Inc.)

If you are an author of one of these papers, please share a PDF when available.

One of our papers, “Ensembles in Adversarial Classification for Spam”, was accepted as a short paper. The work was primarily carried out by Deepak Chinavle, with supervision from Prof. Tim Oates, and drew out from some of my work during graduate studies.

This paper improves on our understanding of adversarial classification and concept drift. We show that explicitly tracking mutual agreements of base classifiers within an ensemble, can be beneficial to reduce re-training frequency. Though this can be somewhat gleaned from the concept drift literature, we further show that our method works well even in the absence of new labeled examples. This has important practical benefits.

From our abstract:

The standard method for combating spam, either in email or on the web, is to train a classifier on manually labeled instances. As spammers change their tactics, the performance of such classifiers tends to decrease over time. Gathering and labeling more data to periodically retrain the classifier is expensive. We present a method based on an ensemble of classifiers that can detect when its performance might be degrading and retrain itself, all without manual intervention. Experiments with a real-world dataset from the blog domain show that our methods can significantly reduce the number of times classifiers are retrained when compared to a fixed retraining schedule, and they maintain classification accuracy even in the absence of manually labeled examples.

Coverage on CIKM 2009, elsewhere:

• LoOP: Local Outlier Probabilities accepted at CIKM’09
• CIKM 2009 Statistics of Titles and Institutions
• Papers from Maarten de Rijke et al

the site, is now online.

Labs cover efforts across Yahoo!, with a theme of both core and applied research:

Yahoo! Labs is pioneering the new sciences underlying the Web. As the center of scientific excellence here at Yahoo!, we deliver both fundamental and applied scientific leadership, publish research and create new technologies that power Yahoo!’s products.

We’re responsible for big inventions—and our goals are nothing short of inventing the future of the Internet and creating the next generation of businesses for Yahoo!.

The labs is head by Prabhakar Raghavan, with a leadership across verticals. The publications page is a good place to start.

Abstracts of all accepted papers is now online [PDF only - why?].

Cursory: Some interesting papers I am looking forward to:

• Ossama Abdelhamid, Behshad Behzadi, Stefan Christoph and Monika Henzinger. Detecting The Origin Of Text Segments Efficiently
• Yue Lu, ChengXiang Zhai and Neel Sundaresan. Rated Aspect Summarization of Short Comments
• Ziv Bar-Yossef and Maxim Gurevich. Estimating the ImpressionRank of Web Pages
• jong wook kim, K. Selcuk Candan and Junichi Tatemura. Efficient Overlap and Content Reuse Detection in Blogs and Online News Articles
• Aleksandra Korolova, Krishnaram Kenthapadi, Nina Mishra and Alexandros Ntoulas. Releasing Search Queries and Clicks Privately
• Fan Guo, Chao Liu, Tom Minka, Yi-Min Wang and Christos Faloutsos. Click Chain Model in Web Search
• Xing Yi, Hema Raghavan and Chris Leggetter. Discover Users’ Specific Geo Intention in Web Search
• Paul Bennett, Max Chickering and Anton Mityagin. Learning Consensus Opinion:Mining Data from a Labeling Game
• Jérôme Kunegis, Andreas Lommatzsch and Christian Bauckhage. The Slashdot Zoo:  Mining a Social Network with Negative Edges
• Meeyoung Cha, Alan Mislove and Krishna Gummadi. A Measurement-driven Analysis of Information Propagation in the Flickr Social Network
• Wen-Yen Chen, Jon-Chyuan Chu, Junyi Luan, Hongjie Bai and Edward Chang. Collaborative Filtering for Orkut Communities: Discovery of User Latent Behavior

Check out my first version, based loosely on PageRank.

Yahoo! Labs, the organization I am part of, has just announced the Key Scientific Challenges Program.

This is your chance to get an inside look at the big challenges Yahoo! research scientists are working on while driving your research forward. Learn more about the real-world problems facing our industry, then focus on and solve these fundamental challenges alongside the top minds in the field.

As a part of the Yahoo! Key Scientific Challenges Program, you’ll receive $5,000 seed funding, exclusive access to Yahoo! research scientists and select datasets, and an invite to the Key Scientific Challenges Graduate Student Summit.

Having recently completed a Ph.D. myself, I can strongly attest to the value of this program, and to the practicality of challenges listed as Search Challenges, among others. If this is you, and interested in actively contributing to important scientific solutions, definitely consider participating.

Apps like these are why information retrieval, search, and social media continue to fascinate researchers, and users.

Jeff Clark, has created an effective search perspective for twitter, which he calls Twitter-Venn. The tool, uses Venn diagrams as the underlying visualization and:

..supports investigation into the relationship between how words are used within the messages of all the people using Twitter.

And, as Jeff humorously notes:

In the context of tweets that mention ‘Christmas’ the santa to jesus ratio is about 4:1 .

Before uncloaking to a wider audience, would be nicer to, at the minimum:

• improve display, and refresh performance
• enable easy screen-capture

I definitely see this turning into a very effective trend mining tool. Impressive. (via Matt)

I have been looking around for startup communities within India for quite a while now, without much luck. Web searches returned results that didn’t really refer me to what I wanted. This content vertical (within India) is rather young, and the community is yet to promote their best of the best online sources. So finally, I relied on old school word-of-mouth (thanks Girish!), which landed me at proto.in.

Proto.in is driven by this underlying philosophy:

Proto.in is the startup event that happens in India, inviting entrepreneurs from within and around the subcontinent to participate, share, discuss and draw strength from the growing entrepreneurial demand and knowledge base that is created, in an effort to create world-class product leaders from the region. Proto is about celebrating entrepreneurship, and encouraging it where it matters the most - at the startup level!

1. To Showcase Innovative technology products borne out of India
2. To Encourage, grow and create entrepreneurial awareness
3. To create a community of startup entrepreneurs, who can grow in strength and numbers, drawing wisdom from each other.
4. To act as a bridge between well-established companies, veteran entrepreneurs, venture capitalists, analysts, journalists, professionals and grass-root entrepreneurs.

..and is run by Vijay Anand, with the help of a large, and growing volunteer base from all around India. The format is similar to BarCamp, DemoCamp (one of which I attended), and in some sense, to the HackDay’s hosted here at Yahoo!

Navigating through the site, the two most useful sources of information include their blog, and the hosted event pages (2007-1, 2007-2, 2008-1). Much of this, however, get hidden within the main site, including the highly valuable company profiles, which I am yet to deep-dive into.

The next startup event is to be hosted at Bangalore (my hometown!), in January 2009, with nominations closing Dec 10, 2008.

The charter of the community is highly encouraging. Having made some key initial contributions, they promise to continue being an important online (and offline) hub for startups in India.

Siri might just turn out to be a perfectly timed AI startup. Via hchen1.

Siri is a new Silicon Valley start-up that attempts to change to the way people use the internet. I joined Siri in Sept. 2008, but I was unable to talk about it until this week. Siri (previously known as stealth-company.com) is an SRI spin-off company armed with $8.5M VC funding. The company inherits  technology innovations resulted from many years of AI research (e.g., the DARPA-funded CALO project).

I am quite excited by a recent sneak preview.

HYPERTEXT 2009, will be held at Torino, Italy between June 29th and July 1st next year. Perhaps, the evolution of HYPERTEXT conference reflects the increasing scope and influence of the Web over the past decade.

The Web, the Semantic Web, the Web 2.0, and Social Networks are all manifestations of the success of the link. The Hypertext Conference provides the forum for all research concerning links: their semantics, their presentation, the applications they have been put to, the knowledge that can be derived from their analysis, and their effect on society.

Main themes in HYPERTEXT 1996 included:

• Spatial Hypertexts
• Autonomous Hypertext Systems and Link Discovery
• Hypertext Rhetoric and Criticism
• Models of Hypermedia Design and Evaluation
• Open Hypermedia
• Navigation in the World-Wide Web
• Systems and Infrastructure
• Extending the World-Wide Web

With many of the above questions, now answered, researchers are moving towards the more "social aspects". HYPERTEXT 2008 themes included:

• Information linking: new models and techniques for interacting with information, automating the "trailblazer"
• Social linking: link inference, analysis and modeling, similarity and retrieval, applications
• Hypertext, culture, and communication
• Applications of hypertext

Submission deadline is February 2009. If you are interested in this area, please consider participating.