Picture of me

Amit Sharma

Ph.D. Candidate, Computer Science
Cornell University

Twitter LinkedIn Google Scholar Dribbble Quora

Update 2015/07: I have graduated! All future updates will be at amitsharma.in.

Research Summary

How do social processes affect our preferences and interests? How do some items stay "niche" while others end up becoming widely popular?

Answers to these questions can help us understand how information diffuses through society, support sharing of information in online social systems and create better recommendation systems.
I use online traces of human activity to make progress on these broad, largely open, questions. I employ online experiments and data mining from a variety of domains such as entertainment, e-commerce and collaborative online activity to create general models for preference evolution and diffusion.

At Cornell, I am a Ph.D. student in the Reimagination Lab, advised by Dan Cosley. I have also been an intern at Google, LinkedIn and IBM Research. Before graduate school at Cornell, I studied computer science at IIT Kharagpur.

Quick Links

The role of social explanations in affecting our preferencesWWW 2013, Link

Recommendations using the ego network ICWSM 2013, Link

Personalization in Social Networks: Modeling the Underlying Social ProcessesD2D@WSDM 2014, Link

Work Experience

Microsoft Research

New York, USA
May - August 2014

Worked with Jake Hofman and Duncan Watts.
Estimation of causal impact of recommender systems.

Google Inc.

Mountain View, USA
May - August 2013

Worked with Gueorgi Kossinets.
Inference of attributes for local businesses, studying the evolution of their rating.

LinkedIn Corp.

Mountain View, USA
May - August 2012

Worked with Baoshi Yan.
Novel pairwise models for learning implicit user feedback on recommendations.


Lausanne, Switzerland
May - July 2009

Worked with Frederic Kaplan and Pierre Dillenbourg.
Prosodic analysis of speech and visualizations for supporting collaborative dialogue.

IBM Research

New Delhi, India
May - July 2008

Worked with Akshat Verma and Gargi Dasgupta.
Local-optimal search algorithms for dynamic composition of web services.


Conference Papers

Journal Papers

Workshop and Demos


Honors and Awards

Datasets for social recommendation and diffusion

When I started working on recommendations within social networks, there were not many datasets available that had both social connections and people's preferences. Even the ones that existed were hard to find, so I am listing out relevant datasets that are useful for studying people's preferences in social networks and designing social recommender systems.

Domain-specific social networks

  • Flickr social network with photo favorites
    [Data | Paper]
  • Flixster social network with movie ratings
    [ Data | Paper]
  • Goodreads social network with book ratings
    [Data | Paper]

General-purpose social networks

  • Twitter social network with hashtag usage
    [Data | Paper]
  • Twitter social network with URL retweets
    [Data | Paper]
  • Facebook social network with movie Likes
    [Data | Paper]
  • Facebook social network with music Likes
    [Data | Paper]

Contact Me