"With pervasive devices such as smart phones and smart watches and applications such as Facebook and Twitter, human users have created massive amounts of data such as exercises, sleep, geolocation, social media posts, social connections, and other information. Big social data brings much more information and choice to people. However, it also increases the burden of retrieving useful information and making decisions, known as information overload. Recommender Systems attempt to help users solve the information overload issue, through suggesting content and services that tailored to individuals based on knowledge about their preferences and behaviours. Current recommender systems face signiﬁcant challenges in the era of big data.
Hashing is a key technique to analyse big data. It has been popularly used for dimensionality reduction and data size reduction. However, current hashing techniques such as Locality Sensitive Hashing(LSH) fail to consider the rich relations of data, the sentiment orientation of users, or handle noisy, incomplete data. Targeting these problems, this project proposes to employ reinforcement learning to develop novel hashing algorithms to sample, compress, and index big social and pervasive data to facilitate effective and eﬃcient recommendation and personalisation. This project will contribute to the new solutions to make better usage and processing of big data.
Eilgibility Requirement: First degree in computer science, physics, engineering, and mathematics with 2:1 or above. MSc degree in the relevant subject areas is desired. "