My research focuses on studying how the users are consuming information on Online Social Networks. In particular, I am interested in exploring what sort of information diets are the users producing or consuming on social media and in evaluating what role the recommendation systems are playing in shaping their diets.
I work at MPI-SWS in the Networked Systems group with Dr. Krishna Gummadi as my advisor.
I am a recipient of the Google European Doctoral Fellowship in Social Networking for the year 2011. I am also a Google Anita Borg scholar for the year 2013.
Education
- Jul 2011 – Present: PhD Student, MPI-SWS
Advisor: Dr. Krishna Gummadi - Oct 2009 – Present: Doctoral Candidate, Graduate School of Computer Science, Saarland University
Mentor: Prof. Dr-Ing. Holger Hermanns
Degree Obtained: M.Sc. in Computer Science - Jul 2007 – Jun 2009: Master's Student, Institute of Informatics and Communication, University of Delhi
Degree Obtained: M.Sc. in Informatics - Jul 2004 –- Jun 2007: Bachelor's Student, Sri Venkateswara College, University of Delhi
Degree Obtained: B.Sc. (Hons) in Physics
Publications
-
Characterizing Information Diets of Social Media Users
Juhi Kulshrestha, Muhammad Bilal Zafar, Lisette Espin Noboa , Krishna P. Gummadi, Saptarshi Ghosh
Proc. of the 9th International AAAI Conference of Web and Social Media (ICWSM), Oxford, UK, May 2015
(acceptance rate 18.37%)
[pdf] | [bibtex] | [Twitter-app] | [slides] -
Deep Twitter Diving: Exploring Topical Groups in Microblogs at Scale
Parantapa Bhattacharya, Saptarshi Ghosh, Muhammad Bilal Zafar, Juhi Kulshrestha, Mainack Mondal, Niloy Ganguly, Krishna P. Gummadi
Proc. of the 17th ACM Conference on Computer Supported Cooperative Work and Social Computing (CSCW), Baltimore, MD, February 2014
(acceptance rate 26.96%)
-
Geographic Dissection of the Twitter Network
Juhi Kulshrestha, Farshad Kooti, Ashkan Nikravesh, Krishna P. Gummadi
Proc. International AAAI Conference on Weblogs and Social Media (ICWSM), June 2012
(acceptance rate 20%)
[pdf] | [bibtex] | [Visualization]
-
A Verified Dependable Wireless Safety Critical Hard Real-Time Design
Hernan Baro Graf, Holger Hermanns, Juhi Kulshrestha, Jens Peter, Anjo Vahldiek, Aravind Vasudevan
Proc. IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM), June 2011
-
Congestion Control and Fairness for Real-time Media Transmission
Juhi Kulshrestha
Master's Thesis, University of Saarland, 2011
Advisor : Prof. Dr-Ing. Thorsten Herfet, Telecommunication Lab, University of Saarland
Projects
Current Projects
- Characterizing Information Diets of social media users
With the widespread adoption of social media sites like Twitter and Facebook, there has been a shift in the way information is produced and consumed. Earlier, the only producers of information were traditional news organizations, which broadcast the same carefully-edited information to all consumers over mass media channels. Whereas, now, in online social media, any user can be a producer of information, and every user selects which other users she connects to, thereby choosing the information she consumes. We define a concept of information diet - which is the composition of a given set of information items (e.g., tweets) - to characterize the information produced and consumed by various types of users in the popular Twitter social media. The composition of information can be defined in many aspects : topical, perspectives or opinions, source diversity etc. In our first piece of work we measure the information diets by computing the topical composition.
- Evaluating social recommendation systems
Personalized recommendation systems are today being deployed on all popular social networking sites such as Twitter, Facebook, and YouTube, to enable users to find interesting users and content. Though the exact recommendation algorithms (which are not publicly known) deployed in various OSNs may possibly be very different, all of them largely depend upon the social neighbourhood of a target user for finding interesting items to recommend to her; hence these are also known as social recommendation algorithms. A user in such a network has two means of gathering information -- (i) via word of mouth, i.e., from the other users whom she connects to, and (ii) through the recommendations given to her -- and the quality of content received by a user is often decided by the collective interplay between these two sources of information. Social recommendation algorithms are today evaluated in isolation, whereas they should be evaluated taking into consideration their interplay with the word of mouth propagation. We propose to evaluate social recommendations based on the additional benefits they provide a certain target user over and above what she receives through word of mouth.
- Geographic Dissection of the Twitter Network
Geography plays an important role in shaping societal interactions in the offline world. However, as more and more social interactions occur online via social networking sites like Twitter and Facebook, users can interact with others unconstrained by their geolocations, raising the question: does offline geography still matter in online social networks? We attempt to address this question by dissecting the Twitter social network based on users' geolocations and investigating how users' geolocation impacts their participation in Twitter, including their connections to others and the information they exchange with them.
- Characterizing Information Trade on Twitter
In this work, we studied how Twitter users trade information with other users both within and across national boundaries. This was the first attempt towards understanding how the offline boundaries manifest themselves on the online world.
Past Projects
Teaching
- Teaching Assistant: "Human vs. Algorithmic-Decision Making: Bias, Fairness & Transparency" (Seminar, University of Saarland, Winter Semester 2015-16)
- Teaching Assistant: "Readings in Social Computing Systems" (Seminar, University of Saarland, Summer Semester 2013)
- Teaching Assistant: "Future Media Internet" (Advanced Lecture, University of Saarland, Winter Semester 2010-11)
