As we move further into the big data era, people are motivated in numerous ways to proactively generate, share and exchange diverse digital contents online every day. While the increasing amount of information greatly facilitates people’s decision makings, it also brings great challenges. For example, the vast amount of information makes it difficult for an individual user to retrieve useful information efficiently. In addition, driven by the huge profits behind the big data economy, malicious attacks are emerging rapidly to mislead normal users’ decision making process by providing carefully designed false information.

This talk will discuss the above mentioned two challenges in details through three sample projects, as (1) A Dynamic Trust based Two-layer Neighbor Selection Scheme towards Online Recommender Systems; (2) Optimizing New User Preference Elicitation for Recommender Systems through Latent Factors; and (3) Efficiently Promoting Product Online Outcome: An Iterative Rating Attack Utilizing Product and Market Property.