Social Media Research Blog

"Personal Brand" Monitoring Tools

Dr. Finin pointed to this interesting post on "branding yourself with a blog":

“… Certainly personal branding isn’t a new concept, but the future of personal branding could be in at your fingertips—with a blog. One of the first steps in creating a brand for yourself is to make your blog visible. Post meaningful entries, comment on your industry’s top blogs, or simply gain a regular readership. “Visibility creates opportunities,” says Schawbel, a social media specialist at EMC Corporation. He believes that when you brand yourself, the competition becomes irrelevant. “The goal of personal branding is to be recruited based on your brand, not applying for jobs,” Schawbel says. …”

Many brand monitoring startups are helping big companies keep track of what their (potential) customers have to say about them or their products. While the space of corporate brand monitoring is  fiercely competed, one area that is overlooked is that of "personal branding" tools. Most of us are highly interested in knowing what is said about us online. As the TechCareers blog points out:

“You are the chief marketing officer for the brand called you, but what others say about your brand is more impactful than what you say about yourself,” says Schawbel.

Keeping an eye on what others have to say about you is not always easy. I started thinking about these issues and outlined how I try to keep up with this information. Here is my "Personal Brand Monitoring Toolbox":

1. Search Engines: The typical way for me to keep tabs on this is by setting up Google alerts for my name, projects, organization (University/workplace) etc. In addition, I frequently perform "ego searches" to forage for mentions of my name.
2. Statistics and Tools: One very interesting tool that I have found useful is Lijit. It provides you stats on who is searching for you, what keywords were used to reach your blog, etc. In addition I use Google Analytics to know more information about my visitors, most visited pages and time they spent on my site. If you are an academic like me, you would like to know who has cited your papers recently (Google Scholar) and the number of downloads, who has linked to your paper (Google link: search) and/or your blog posts (Technorati searches). Yessss! I admit! I have become a total statoholic! :-)
   
3. Comments and Scraps: Twitter is another important tool in our arsenal for personal branding and your replies say something interesting about you. Finally, the comments on my blog, Facebook messages, scraps and photos are all part of my "brand" and I take interest in replying to them just like I would to an email.

As our information spaces diversify, monitoring "your brand" becomes a part of the everyday online activity. I dont think we have exactly cracked the nut yet -- keeping track of your profile and "your brand " is a highly addictive activity and I think that the tool(s) that make it fun and exciting will enjoy a great deal of popularity.

Leaveraging Web and Social Media for Recommendations

Both Amazon and Netflix's business models rely on effective recommendation systems. The recommendations provided by such systems are based on the purchasing habits of millions of customers. As such, these systems are non-trivial and have evolved out of years of research in both academia and industry.

In addition to mining millions of customer transaction records, for many products there is a vast amount of information available online. While I do not have a lot of familiarity with recommendation systems literature, it seems obvious that the Web and Social Media is a great source of information that could be useful when building such systems.  Bloggers' profile pages, wishlists, netflix queues, book lists and the blog posts themselves are potential clues to learn which two items may be related to each other.

As a simple example, consider the movie "Pulp Fiction", by querying Google for all the inlinks to the IMDB homepage of Sin City Pulp Fiction and counting which are the other movies that are "co-cited" here is a list of five movies that are most likely to be related to "Pulp Fiction":

Most of these look quite relevant. Some critics have claimed similarities between Pulp Fiction and Snatch. One surprise though was LOTR, I wouldn't have expected it to be grouped with Pulp Fiction, but I guess I like them both very much -- so it seems reasonable in my case atleast.

Just for fun, here is another example with "Sin City" another one of my favorite movies.

Unless you have a large index of the Blogosphere or the Web, it would be quite inefficient to mine for such correlations (by passing queries to search engines) on a large scale. I do not know how much of the search engine information is leveraged in recommendation systems built by Amazon or Netflix.  It might also be worth looking into differences in the recommendations produced on the basis of "how people co-cite two products" vs. "how people purchase two products".

Notes from DEBSM Workshop: Inferring Privacy Information via Social Relations

Inferring Privacy Information via Social Relations
Wanhong Xu, Xi Zhou Lei Li (presenter)

The presentation started with a neat quote: "Your social activities tell who you are". Social Networking are part of everyday life and for many of us a primary way in which we keep in touch with friends and family. Privacy is a huge problem in such networks. Li provided some statistics from a recent survey of British social network users: about  62 percent are concerned about the security of their personal data. 31% of the users falsify information to protect identity. This is a huge figure and definitely shows the level of concern.

This paper was motivated with applications for social advertising (which is a 2.2B US market). One can target users based on location, age gender etc. and social advertising allows advertisers to choose their audience. The problem comes up where users do not wish to disclose too much of their information online. The proposed solution is to automatically infer such missing information.

The authors use an undisclosed dataset for this study. The assumption is users fake personal information but not their activities. It is well known in offline-social networks that gender preference exist in friendship. however in online social networks this is not true (Jure Leskovec, WWW,2008). The key question that authors of this paper ask is : "Users may fake their personal information...But what about social activities?"

The insight that this paper offers is that certain group membership gives hints of user gender information. Joining groups has a gender preference. So the way in which one can infer the gender is to use a bipartite graph of users->groups with missing gender information using relation between users and groups. One approach is to use the User*Group matrix and build a classifier. However, they found that Naive Bayes does not work very well. Many social groups in fact dont have any gender preference. This can really hurt the classifier accuracy. So one approach they propose is to choose the discriminating social groups. i.e. groups that dominated by males or females. One major disadvantage that this technique suffers from is that the membership for users that dont join any of these groups can not be predicted. Once you restrict to the set of discriminating groups, now Naive Bayes performs well.

For users that cant be predicted they propose the use of an iterative algorithm to combine discriminative social groups and results from Naive Bayes classifier. Testing is performed by removing or making some data missing and then predicting the missing gender information.

My concern here is that the authors might have been able to avoid this disadvantage if they had used SVD to map the Groups to a set of lower dimensions that way it would automatically "cluster" the groups based on whatever the discriminating factor is (in their case the gender information). Secondly, while the authors had access to "verifiable" ground truth data, in real world how do we know the influence of fake profiles on these discriminative groups?

Cartoonist 2.0 and "Dancin Dubya"!

When returning a book at the library this week, I noticed an interesting talk titled "The Art of Political Satire". The speaker was none other than Kevin Kallaugher (KAL) who is the cartoonist with "The Economist "magazine, London. But more significantly, he is also the artist-in-residence and cartoonist at the Imaging Research Center at UMBC. Kal talks about his life experiences as a cartoonist both in the United States and U.K. His sense of humor is world-class and through a montage of his work over the years, Kal touches upon some delicate issues (911, war, world politics and the struggle to end of apartheid in SA) all while engaging his audience and making them smile.

I think Kal is what I would describe as a Cartoonist 2.0. He really gets the new media and realizes its potential. He talks about the decline in newspaper readership and the print advertising. How the new generation is more about flickr and YouTube and less about buying a newspaper or a magazine. So along with UMBC's IRC, Kal has set out on a journey to explore what it means like to be a cartoonist/journalist/political satirist in a Web 2.0 world. He is planning to take the essential elements of a cartoon strip and blend it with 3D animation and video. Starting from a clay caricature model of our very own Dubya and using motion capture technology, Kal can actually hold real-time conferences with the audience members asking Pres. Dubya Bush some serious questions! Well rest assured, you will atleast be get answers that make some sense! You can read more about it here and also check out the really cool video of "dubya press briefing"!  Oh! and here is Kal's fantastic version of "dancin dubya" ... quite close to the real version!
 

Well he is a real puppet arite!

Kal also plans to take dubya to live audiences and host a show soon. Soon we should expect to have syndicated, interactive 3D cartoon strips on many online newspapers! Good luck Kal, the maverick cartoonist 2.0!

Social Media and Social Causes

Whoever said social network was meant only for people who were interested in dating and getting together with a bunch for friends for a beer? One of the most amazing Facebook apps I have seen is causes. It was developed by Project Agape . Causes is an application that lets me publicize and advocate for social causes I am most passionate about. It is truly amazing that the even just the top five social causes have raised over $119,469 on Facebook. 

 

More coverage on Techcrunch. Another noteworthy social good application is DonorsChoose. It connects donors to specific school projects that they can choose to help fund. It enables a personal level of involvement with the project and makes the donor feel connected to the cause.

Additionally Google posts certain public service advertisements. I am not sure if there is something like this already out there -- I think a not-for-profit advertising network that also let users decide which causes they chose to host on their blogs, would also be a worthy effort.

While some people prefer to be discrete about their social causes and donations, publicizing causes one is passionate about has its own merits. At the very least, they serve a greater purpose -- that of educating people in your social network about the world and what we can do to make it a better place!