Student research opportunities

Real-time Social Media Recommender Systems

Project Code: CECS_776

This project is available at the following levels:
Honours, Summer Scholar, Masters, PhD

Keywords:

Recommender Systems, Social Media, Real-time, Social Stream, Web Mining

Supervisor:

Dr Huizhi (Elly) Liang

Outline:

The recent increase of real-time data provided by users on social media and networking services (such as twitter.com) has leveraged an importance gain of the real-time processing of social streams. Processing the streams in real-time can help enhance search engines, news media, and many other systems by feeding them with fresh knowledge about current affairs. Performing such analysis in real-time is of utmost importance for early reporting of breaking news, events, trends, and any other knowledge related to current affairs. However, analyzing social streams in real-time makes the task more challenging as it requires making decisions without clue of what will be next in the stream.

Goals of this project

This project is to design and implement algorithms to conduct real-time social media recommendations. The issues of improving the scalability and quick response time of algorithms for large scale stream data will also be explored.

Requirements/Prerequisites

Having attended courses in algorithms and data structures
Good programming skills.
knowledge about data mining or machine learning a plus.

Student Gain

A student working on this project will learn about recommender systems, data mining techniques especially advanced web mining techniques to analyze the real world emergent data from Twitter.com, improving the scalability of recommender systems to very large databases, and developing parallel recommendation techniques.

Background Literature

1.Badrul Sarwar et. al., Item-based Collaborative Filtering Recommendation Algorithms, WWW’01.
2.Gediminas Adomavicius et. al., Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Transactions on Knowledge and Data Engineering.