Past Project Topics

Here are some ideas for possible course projects. Keep in mind that we are not interested in merely understanding a specific paper, implementing the presented algorithms and demonstrating that you understand their contributions well enough to reproduce it yourself. The watchwords are innovation, creativity, and novelty. As always, depth will always bring its rewards (just as it does in paper presentations, in discussions led, and in the subsequent summaries prepared).

In addition to these suggestions, I am happy to listen to other ideas for projects, if you have any of your own. I am also happy to work with you on creating other project ideas. No matter which project you choose, I will be available to discuss with you any technical issues related to your project.

Each project can either take the shape of a paper or an implementation. It’s your choice. Each team may contain up to two people. (If the course enrollment changes significantly, we will revisit this rule.) Regardless of whether you do a project alone or as a team of two, my expectation will be that every individual does the same amount of work. Teams must be formed by Friday, January 15. Project choices should be made by Wednesday, January 20. Here, then are the project ideas. (More details on the project schedule and milestones will be posted soon.) 

1. Social Network Computing: Social nets such as facebook and del.ico.us have facilitated massive data, resource and opinion sharing, and in general online discourse. The resources can range from online resources like videos, photos, and blogs to material objects like lawnmowers and bikes. (If you are wondering about what material objects are doing in a social net, talk to me!) The opinions range from political opinions to impressions about the job done by the recently hired handyman. Additionally, the blogosphere is awash with information. On the one hand, the information in social nets is mostly free text and is thus largely unstructured. Thus, traditional IR techniques as well as techniques based on centrality notions such as pagerank can be effectively used to facilitate search over social nets. On the other hand, though, social nets have their own structure, bringing the notion of a seeker’s social neighborhood to the context of search. Just focusing on search alone, there are interesting questions that need to be studied:
Note: This is not one project. By focusing on different angles, more than one project can be formulated around the above description. 

2. Link Prediction and Network Evolution: Substantial work has been done on link prediction in social networks and on modeling the evolution of the network. Two possible project ideas follow: 
(a) Monitoring and Tracking of underlying network in newsgroups and/or blogs: Analyze the communication structure in newsgroups or blogs and discover the underlying social network present there. The framework should be parameterizable (e.g., strength of links, period of activity, etc.) and should be queriable (e.g., topic of conversation, who started a particular discussion, etc.). Visualize the network in creative and interactive ways. 
(b) Predict links and build models of network evolution: Given a social network together with properties of nodes and/or edges (in the form of keywords or more structured attributes), what is the state of the art in link prediction that takes all available information into account? How can we go beyond it? Can we incorporate time in modeling? 

3. Viral Marketing: 

4. Trust & Reputation: 

5. Recommender Systems: 

6. Top-k Query/Search: 

7. Opinion Mining & Social Networks: